最近 7 天
12
次命中
Keyword Tracking
关键词追踪：alignment
这个页面会长期追踪你配置里关心的关键词，并把命中的论文按日期沉淀下来。
最近 30 天
59
次命中
全部历史
175
次命中
近期走势
最近一次命中来自 LM：In-Context Model Predictive Generation: Open-Vocabulary Motion Synthesis from Language Models to Physics
2026-06-15
0
2026-06-16
4
2026-06-17
3
2026-06-18
4
2026-06-19
1
2026-06-20
0
2026-06-21
0
2026-06-22
0
2026-06-23
4
2026-06-24
2
2026-06-25
4
2026-06-26
2
2026-06-27
0
2026-06-28
0
命中明细
按日期回看匹配到这个关键词的论文标题，并保留来源 feed 信息。
2026-06-26
In-Context Model Predictive Generation: Open-Vocabulary Motion Synthesis from Language Models to Physics
Synthesizing human motion from textual descriptions is essential for immersive digital applications, yet existing methods face a persistent trade-off between semantic fidelity and…
Just how sure are you? Improving Verbalized Uncertainty Calibration in Medical VQA
Multimodal large language models (MLLMs) applied to Medical Visual Question Answering (VQA) tend to produce overconfident outputs regardless of actual correctness, and existing ve…
2026-06-25
RAS: Measuring LLM Safety Through Refusal Alignment
Safety evaluation of large language models (LLMs) is commonly performed by querying models with unsafe or jailbreak prompts and judging whether their outputs violate a safety poli…
SpeechEQ: Benchmarking Emotional Intelligence Quotient in Socially Aware Voice Conversational Models
As multimodal conversational systems increasingly engage in spoken interaction, their ability to navigate paralinguistic social cues has become a critical bottleneck for natural h…
SARA: Unlocking Multilingual Knowledge in Mixture-of-Experts via Semantically Anchored Routing Alignment
Sparse Mixture-of-Experts (MoE) architectures have emerged as an increasingly influential paradigm as they offer a strategic balance between parameter scalability and computationa…
The Unfireable Safety Kernel: Execution-Time AI Alignment for AI Agents and Other Escapable AI Systems
AI agents are granted access to tools, APIs, and other infrastructure, making them active principals in those systems. The dominant approach places controls inside the agent's own…
2026-06-24
EG-VQA: Benchmarking Verifiable Video Question Answering with Grounded Temporal Evidence
Recent advances in Video Large Language Models (Video-LLMs) have yielded promising performance on video question answering (VideoQA). Nevertheless, existing benchmarks are predomi…
PHANTOM: A Large-Scale Dataset of Multimodal Adversarial Attacks for Vision-Language Models
We introduce a large-scale, open-source dataset of pre-generated adversarial attacks for vision-language models (VLMs). The dataset is designed to be diverse, representative, and…
2026-06-23
Distribution-Aware Diffusion-LLM for Robust Ultra-Long-Term Time Series Forecasting
Time series forecasting is a fundamental machine learning task. Recent work has explored Large Language Models (LLMs) for this purpose due to their strong generalization, pattern…
On the Limits of Prompt-Conditioned Language Models as General-Purpose Learners
Large Language Models (LLMs) are frequently portrayed as general-purpose solvers capable of solving arbitrary tasks. We argue that this view overlooks a fundamental constraint: la…
Measuring & Mitigating Over-Alignment for LLMs in Multilingual Criminal Law Courts
While the wider applicability of LLMs in the legal field is currently debated due to their reliability and the gravity of any errors, narrow uses with well-understood and mitigate…
Capable but Careless: Do Computer-Use Agents Follow Contextual Integrity?
Computer-use agents (CUAs) now act on a user's behalf across personal applications such as email, calendars, and to-do lists. This cross-application access is useful, but it also…
2026-06-19
Your Mouse and Eyes Secretly Leak Your Preference: LLM Alignment using Implicit Feedback from Users
To align a Large Language Model (LLM), most existing methods collect explicit human feedback and train a reward model to predict the human preference based on the response text. T…
2026-06-18
Quantifying and Auditing LLM Evaluation via Positive--Unlabeled Learning
Large Language Models (LLMs) are increasingly used as judges for scalable evaluation, yet such LLM--as--a--Judge systems exhibit systematic biases that are decoupled from semantic…
Beyond Tokenization: Direct Timestep Embedding and Contrastive Alignment for Time-Series Question Answering
Recent advances in large language models (LLMs) have given rise to time-series question answering (TSQA), which formulates time-series analysis as natural-language question answer…
G-IdiomAlign: A Gloss-Pivoted Benchmark for Cross-Lingual Idiom Alignment
Idioms are difficult to transfer across languages due to their non-compositionality and weak surface-form grounding, making literal mappings unreliable. We present G-IdiomAlign, a…
Beyond Safe Data: Pretraining-Stage Alignment with Regular Safety Reflection
To achieve deeper safety alignment for large language models (LLMs), recent efforts have studied how to push safety interventions earlier into the pretraining stage, primarily by…
2026-06-17
LLM Consumer Behavior Theory: Foundations of a Novel Research Field
Large language models (LLMs) are increasingly deployed as autonomous agents that make consumption decisions on behalf of users. This shift raises fundamental questions for consume…
RubricsTree: Scalable and Evolving Open-Ended Evaluation of Personal Health Agents across Health Memory and Medical Skills
The LLM-empowered personal health agents with user health (sensor) metrics have offered a promising pathway to alleviate global disparities in healthcare access. However, large-sc…
ProvenanceGuard: Source-Aware Factuality Verification for MCP-Based LLM Agents
Tool-using LLM agents increasingly use the Model Context Protocol (MCP) to answer from heterogeneous evidence sources, including search, APIs, databases, clinical records, and for…
2026-06-16
LabOSBench: Benchmarking Computer Use Agents for Scientific Instrument Control
Current computer-use benchmarks primarily focus on software operation tasks in virtualized systems, whereas scientific instrumentation scenarios require coordinated control over c…
Contrastive-Difference CKA Reveals Concept-Specific Structural Alignment Across Language Model Architectures
Do different LLM architectures encode high-level concepts in structurally compatible ways? We systematically characterize a geometric-functional universality dissociation: across…
DoubtProbe: Black-Box Jailbreak Defense via Structural Verification and Semantic Auditing
As large language models (LLMs) are increasingly deployed in user-facing systems, black-box jailbreak defense has become an important practical problem. Existing defenses often re…
Adaptive and Explicit safe: Triggering Latent Safety Awareness in Large Reasoning Models
While Large Reasoning Models (LRMs) excel at complex tasks, they remain highly vulnerable to sophisticated jailbreaks and direct harmful queries. To address this vulnerability, pr…
2026-06-12
Leveraging Audio-LLMs to Filter Speech-to-Speech Training Data
Large-scale mined corpora provide abundant training data for end-to-end speech-to-speech translation (S2ST) but may contain noise, misalignment, and semantic errors. Filtering noi…
2026-06-11
OpenMedReason: Scientific Reasoning Supervision for Medical Vision-Language Models
High-stakes clinical use of large vision-language models (LVLMs) requires reasoning that is grounded in visual evidence and clinical knowledge, not just correct final answers. We…
ALIGNBEAM : Inference-Time Alignment Transfer via Cross-Vocabulary Logit Mixing
Domain fine-tuning degrades the safety of large language models: fine-tuned specialists readily comply with harmful prompts framed in domain language. Existing inference-time defe…
Which Speech Representation Better Matches Text-Native Reasoning? A Study of Speech-Text Alignment on Frame Rate and Representation
Spoken dialogue models typically start from text LLM backbones, yet reasoning often degrades when conditioning on speech instead of text. We attribute part of this modality gap to…
Grammar-Constrained Decoding Can Jailbreak LLMs into Generating Malicious Code
Large Language Models (LLMs) are increasingly used for code generation, raising concerns that they may be misused to produce malicious code. Meanwhile, Grammar-Constrained Decodin…
2026-06-10
Role-Agent: Bootstrapping LLM Agents via Dual-Role Evolution
Although Large Language Model (LLM) agents have demonstrated strong performance on complex tasks, their learning is often limited by inefficient interaction feedback and static tr…
The Shibboleth Effect: Auditing the Cross-Lingual Distributional Skew of Large Language Models
This study investigates cross-lingual distributional skew (the Shibboleth Effect) in frontier large language models (LLMs) subjected to sustained adversarial conditions. We develo…
Does Reasoning Preserve Alignment? On the Trustworthiness of Large Reasoning Models
Instruction-tuned LLMs are increasingly converted into reasoning models through post-training to improve multi-step task performance. This conversion is usually optimized for reas…
Null-Space Constrained Low-Rank Adaptation for Response-Specified Large Language Model Unlearning
Large language model unlearning aims to suppress designated undesirable knowledge while preserving benign capabilities. Many unlearning objectives focus on suppressing undesired a…
It Takes One to Bias Them All: Breaking Bad with One-Shot GRPO
Warning: This paper contains several toxic and offensive statements. Modern large language models (LLMs) are typically aligned through large-scale post-training to ensure fair and…
When the Chain of Thought Knows Better: Failure Modes in Multi-Turn Reasoning Models
Failures in multi-turn reasoning models are largely invisible to terminal-score evaluation. A model can lock onto an unsafe stance early in a long dialogue, yet its final-turn ref…
2026-06-09
Gradient-Guided Reward Optimization for Inference-time Alignment
Ensuring the reliability of Large Language Models (LLMs) under distribution drift requires inference-time adaptation. While inference-time alignment methods such as Best-of-$N$ an…
IS-CoT: Breaking the Long-form Generation Collapse via Interleaved Structural Thinking
Generating coherent and controllable long-form content remains a persistent challenge for Large Language Models (LLMs). While reasoning-enhanced models have demonstrated success i…
The Neutral Mask: How RLHF Provides Shallow Alignment while Leaving Partisan Structure Intact in a Large Language Model
The ambition behind alignment training is to make large language models safe and useful. The primary mechanism, reinforcement learning from human feedback (RLHF), shapes the behav…
UXBench: Benchmarking User Experience in AI Assistants
As AI assistants serve millions of users daily, evaluating user experience (UX) beyond general model capability has become increasingly important. We present UXBench, the first us…
2026-06-05
CollabSim: A CSCW-Grounded Methodology for Investigating Collaborative Competence of LLM Agents through Controlled Multi-Agent Experiments
Multi-agent systems (MAS) built on large language models have shown growing promise, with their effectiveness resting on agents' ability to coordinate through text-based channels…
Beyond tokens: a unified framework for latent communication in LLM-based multi-agent systems
Multi-agent systems built on large language models (LLMs) have become a prevailing paradigm for tackling complex reasoning, planning, and tool-use tasks. The dominant communicatio…
A Komi-Yazva--Russian Parallel Corpus and Evaluation Protocol for Zero- and Few-Shot LLM Translation
We present the first Komi-Yazva--Russian parallel corpus together with an explicit evaluation protocol for studying LLM translation in an endangered, extremely low-resource settin…
Safety Paradox: How Enhanced Safety Awareness Leaves LLMs Vulnerable to Posterior Attack
Large language models (LLMs) are rigorously aligned to refuse harmful requests, a process that inherently cultivates a latent capacity to evaluate and recognize unsafe content. In…
The Granularity Gap: A Multi-Dimensional Longitudinal Audit of Sycophancy in Gemini Models
Large language models are increasingly deployed as high-stakes advisors, yet standard alignment benchmarks treat sycophancy as a binary failure mode. We introduce the Granularity…
2026-06-04
Large Language Models in K-12 Education: Alignment with State Curriculum Standards and Student Personas
As Large Language Models (LLMs) become increasingly popular in educational settings, they raise important questions about the ethical implications of their use. Publicly available…
GRAIL: Gradient-Reweighted Advantages for Reinforcement Learning with Verifiable Rewards
Reinforcement learning with verifiable rewards (e.g. GRPO) is now a common way to improve mathematical reasoning in Large Language Models (LLMs). However, current methods usually…
The Meta-Agent Challenge: Are Current Agents Capable of Autonomous Agent Development?
Current AI benchmarks evaluate agents on task execution within human-designed workflows. These evaluations fundamentally fail to measure a critical next-level capability: whether…
Trustworthy AI Software Engineers
With the rapid rise of AI coding agents, the fundamental premise of what it means to be a software engineer is in question. In this vision paper, we examine what it means for an A…
2026-06-03
Exploring Adversarial Robustness and Safety Alignment in Multilingual Multi-Modal Large Language Models
Multimodal Large Language Models integrate visual perception into language reasoning, introducing a continuous attack surface susceptible to adversarial attacks. Prior work on MLL…
Can Factual Opinions Be Edited (Manipulated) in Large Language Models?
Large Language Models (LLMs) are increasingly integrated into various domains, making knowledge editing techniques crucial yet potentially hazardous. Current editing methods prima…
Fully Automated Identification of Lexical Alignment and Preference-Stage Shifts in Large Language Models
The language used by digital chat assistants such as ChatGPT can diverge from human expectations (misalignment). Research, mostly on Scientific English, has described both what di…
Selective Token-Level Cryptographic Redaction for Privacy-Preserving Clinical Deployment of Large Language Models
While large language models (LLMs) are increasingly used for clinical applications, many existing pipelines require sending raw sensitive health information to remote servers for…
Hallucinations as Orthogonal Noise: Inference-Time Manifold Alignment via Dynamic Contextual Orthogonalization
Hallucination in Large Language Models (LLMs), characterized by the generation of content inconsistent with contextual facts or logical constraints -- remains a persistent challen…
Which Defense Closes Which Threat? Attributing OWASP-LLM-Top-10 Coverage and Its Brittleness Under Paraphrasing
Production LLM applications stack several defense families -- refusal-phrase filters, token-budget controls, model allowlists, rate limits, tool-registry authentication -- yet exi…
Dependency-Guided Repository-Level C-to-Rust Translation with Reinforcement Alignment
Automating C-to-Rust migration is critical for improving software security without sacrificing performance. Traditional rule-based methods struggle with diverse C idioms, often pr…
Automated Repair of Requirements for Cyber-Physical Systems in Simulink Requirements Tables
The development of complex software systems, e.g., cyber-physical systems (CPSs), involves continuous evolution of both system implementations and their requirements. These two ar…
2026-06-02
Mitigating Perceptual Judgment Bias in Multimodal LLM-as-a-Judge via Perceptual Perturbation and Reward Modeling
Recent multimodal large language models have demonstrated strong reasoning ability, yet their reliability as automated evaluators remains limited by a critical weakness: when visu…
SafeSteer: Localized On-Policy Distillation for Efficient Safety Alignment
Aligning Large Language Models (LLMs) with human values often degrades their general capabilities, termed the alignment tax. Existing methods mitigate this by balancing dual objec…
Jailbreaking Multimodal Large Language Models using Multi-Clip Video
As multimodal large language models (MLLMs) have advanced to process video inputs, concerns have emerged about their potential for malicious misuse. Prior jailbreak studies have s…
2026-05-29
CIRF: Tokenizing Chain-of-Thoughts into Reusable Functional Units for Efficient Latent Reasoning in Large Language Models
Implicit Chain-of-Thought (CoT) reduces the inference cost of large language models by internalizing the explicit rationales. However, existing approaches typically lack alignment…
Argument Quality Assessment with Large Language Models: A Pairwise Bradley-Terry Approach
Large Language Models (LLMs) have demonstrated remarkable capabilities in tasks related to reasoning and judgment. However, assessing the quality of arguments requires a rigorous…
Modeling Community Attitude through Reaction Tone: A Human-AI Collaborative Framework for Evaluating LLM Alignment with Linguistic Behaviors in Online Communities
Large language models (LLMs) are increasingly utilized as proxies for computational social analysis; yet, their ability to faithfully represent the "thick descriptions" (Geertz, 1…
Framing Matters: Addressing Framing Sensitivity in Decision-Making through Behaviorally-Grounded Value Alignment
Large Language Models (LLMs) are increasingly deployed in high-stakes decision-making settings such as legal reasoning, where consistency under factually equivalent inputs is crit…
HELEA: Hard-Negative Benchmark and LLM-based Reranking for Robust Entity Alignment
Entity Alignment (EA) is essential for knowledge graph (KG) fusion, but existing benchmarks often allow models to exploit name overlap rather than relational structure. This makes…
AgentDoG 1.5: A Lightweight and Scalable Alignment Framework for AI Agent Safety and Security
Modern open-world agents such as OpenClaw exhibit powerful cross-environment execution capabilities yet introduce broad new safety risk sources. Meanwhile, advanced frontier AI mo…
2026-05-28
MemTrace: Tracing and Attributing Errors in Large Language Model Memory Systems
Memory is essential for enabling large language models to support long-horizon reasoning, yet existing memory systems remain unreliable and difficult to debug. Tracing memory's dy…
MUSE: Benchmarking Manufacturable, Functional, and Assemblable Text-to-CAD Generation
Large language models (LLMs) have recently advanced text-driven 3D generation, yet Text-to-CAD remains far from supporting industrial product design. Existing benchmarks focus pri…
VLMs May Not Globally Enhance Human Alignment over LLMs During Natural Reading
Large language models (LLMs) have become increasingly useful computational models of human language processing, but it remains unclear whether vision-language learning makes text…
Evaluating the Realism of LLM-powered Social Agents: A Case Study of Reactions to Spanish Online News
LLM-powered social agents are increasingly used to simulate online social behavior, yet their realism remains difficult to validate. Existing work has largely relied on general-pu…
2026-05-27
MATCHA: Matching Text via Contrastive Semantic Alignment
Reliable evaluation is essential for understanding large language model (LLM) performance, yet today's go-to metrics, namely token-overlap scores (e.g., ROUGE) and embedding-based…
ENPMR-Bench: Benchmarking Proactive Memory Retrieval for Emotional Support Agents
Memory-augmented language agents are increasingly deployed in affective applications such as emotional support, where understanding and responding to users' latent emotional needs…
It's Not Always Sycophancy: Measuring LLM Conformity as a Function of Epistemic Uncertainty
Large language models (LLMs) are known to abandon their initial stance to conform to user pushback. While prior research largely attributes this behavior to sycophancy learned dur…
2026-05-26
Causal methods for LLM development and evaluation
Large language model (LLM) development is currently driven by large-scale empirical iteration over data mixtures, reward models, routing strategies, and evaluation pipelines. Here…
PolyGnosis 2.0: Enhancing LLM Reasoning via Agentic Harness Engineering for Polymarket and OSINT Insight Extraction
This paper introduces PolyGnosis 2.0, a pioneering multi-agent architecture designed to extract predictive intelligence by synthesizing Polymarket anomaly signals with global Open…
MAGIC: Multimodal Alignment & Grounding-aware Instruction Coreset for Vision-Language Models
Instruction tuning of large vision-language models (LVLMs) increasingly depends on massive multimodal corpora, yet these datasets contain samples with substantial redundancy, low…
2026-05-22
Agentic CLEAR: Automating Multi-Level Evaluation of LLM Agents
Agentic systems are becoming more capable: agents define strategies, take actions, and interact with different environments. This autonomy poses serious challenges for overseeing…
ChronoMedKG: A Temporally-Grounded Biomedical Knowledge Graph and Benchmark for Clinical Reasoning
Biomedical knowledge graphs (KGs) treat disease associations as static facts, but temporal information is crucial for clinical reasoning, e.g., a symptom diagnostic of one disease…
LANG: Reinforcement Learning for Multilingual Reasoning with Language-Adaptive Hint Guidance
Reinforcement learning has proven effective for enhancing multi-step reasoning in large language models (LLMs), yet its benefits have not fully translated to multilingual contexts…
From Parameters to Data: A Task-Parameter-Guided Fine-Tuning Pipeline for Efficient LLM Alignment
Adapting Large Language Models (LLMs) to specialized domains typically incurs high data and computational overhead. While prior efficiency efforts have largely treated data select…
Planning in the LLM Era: Building for Reliability and Efficiency
Growing attention to intelligent agents has put a spotlight on one of their central capabilities: planning. Early attempts to leverage large language models (LLMs) for planning re…
Cross-Lingual Consensus: Aligning Multilingual Cultural Knowledge via Multilingual Self-Consistency
Although Large Language Models (LLMs) demonstrate strong capabilities across various tasks, they exhibit significant performance discrepancies across languages. While prompting LL…
Polite on the Surface, Wrong in Practice: A Curated Dataset for Fixing Honorific Failures in Multilingual Bangla Generation
Recent advances in Multilingual Large Language Models (MLLMs) have significantly enhanced cross-lingual conversational capabilities, yet modeling culturally nuanced and context-de…
2026-05-21
Federated LoRA Fine-Tuning for LLMs via Collaborative Alignment
Low-rank adaptation (LoRA) has emerged as a powerful tool for parameter-efficient fine-tuning of large language models (LLMs). This paper studies LoRA under a federated learning s…
2026-05-20
SciCustom: A Framework for Custom Evaluation of Scientific Capabilities in Large Language Models
Large language models (LLMs) are increasingly applied to scientific research, yet existing evaluations often fail to reflect the fine-grained capabilities required in practice. Mo…
LambdaPO: A Lambda Style Policy Optimization for Reasoning Language Models
Group Relative Policy Optimization(GRPO) has become a cornerstone of modern reinforcement learning alignment, prized for its efficacy in foregoing an explicit value-critic by leve…
Robotics-Inspired Guardrails for Foundation Models in Socially Sensitive Domains
Foundation models are increasingly deployed in socially sensitive domains such as education, mental health, and caregiving, where failures are often cumulative and context-depende…
SimGym: A Framework for A/B Test Simulation in E-Commerce with Traffic-Grounded VLM Agents
A/B testing remains the gold standard for evaluating modifications to e-commerce storefronts, yet it diverts traffic, requires weeks to reach statistical significance, and risks d…
2026-05-19
CrossView Suite: Harnessing Cross-view Spatial Intelligence of MLLMs with Dataset, Model and Benchmark
Spatial intelligence requires multimodal large language models (MLLMs) to move beyond single-view perception and reason consistently about objects, visibility, geometry, and inter…
Estimating Item Difficulty with Large Language Models as Experts
Accurate estimates of item difficulty are essential for valid assessment and effective adaptive learning. However, for newly created tasks, response data are typically unavailable…
Ancient Greek to Modern Greek Machine Translation: A Novel Benchmark and Fine-Tuning Experiments on LLMs and NMT Models
Machine Translation (MT) for Ancient Greek (AG) to Modern Greek (MG) is a low-resource task, constrained by the lack of large-scale, high-quality parallel data. We address this ga…
AMR-SD: Asymmetric Meta-Reflective Self-Distillation for Token-Level Credit Assignment
The alignment of Large Language Models (LLMs) for complex reasoning heavily relies on Reinforcement Learning with Verifiable Rewards (RLVR). However, standard algorithms like GRPO…
Query-Conditioned Knowledge Alignment for Reliable Cross-System Medical Reasoning
Cross-domain knowledge alignment is essential for integrating heterogeneous medical systems, yet existing approaches typically treat entity alignment as a static matching problem,…
Overeager Coding Agents: Measuring Out-of-Scope Actions on Benign Tasks
Coding agents now run autonomously with shell, file, and network privileges. When a user issues a benign request, the agent sometimes does more than asked: it deletes unrelated fi…
Acoustic Interference: A New Paradigm Weaponizing Acoustic Latent Semantic for Universal Jailbreak against Large Audio Language Models
The integration of audio modality into Large Audio Language Models (LALMs) significantly expands their attack surface. Existing jailbreak paradigms predominantly treat audio as a…
2026-05-15
Talk is (Not) Cheap: A Taxonomy and Benchmark Coverage Audit for LLM Attacks
We introduce a reusable framework for auditing whether LLM attack benchmarks collectively cover the threat surface: a 4$\times$6 Target $\times$ Technique matrix grounded in STRID…
Comparing Developer and LLM Biases in Code Evaluation
As LLMs are increasingly used as judges in code applications, they should be evaluated in realistic interactive settings that capture partial context and ambiguous intent. We pres…
2026-05-13
ORCE: Order-Aware Alignment of Verbalized Confidence in Large Language Models
Large language models (LLMs) often produce answers with high certainty even when they are incorrect, making reliable confidence estimation essential for deployment in real-world s…
Fill the GAP: A Granular Alignment Paradigm for Visual Reasoning in Multimodal Large Language Models
Visual latent reasoning lets a multimodal large language model (MLLM) create intermediate visual evidence as continuous tokens, avoiding external tools or image generators. Howeve…
Question Difficulty Estimation for Large Language Models via Answer Plausibility Scoring
Estimating question difficulty is a critical component in evaluating and improving large language models (LLMs) for question answering (QA). Existing approaches often rely on read…
Pretraining Exposure Explains Popularity Judgments in Large Language Models
Large language models (LLMs) exhibit systematic preferences for well-known entities, a phenomenon often attributed to popularity bias. However, the extent to which these preferenc…
2026-05-12
Conformity Generates Collective Misalignment in AI Agents Societies
Artificial intelligence safety research focuses on aligning individual language models with human values, yet deployed AI systems increasingly operate as interacting populations w…
DGPO: Beyond Pairwise Preferences with Directional Consistent Groupwise Optimization
Although Large Language Models (LLMs) have made remarkable progress, current preference optimization methods still struggle to align directional consistency while preserving reaso…
Intrinsic Guardrails: How Semantic Geometry of Personality Interacts with Emergent Misalignment in LLMs
Fine-tuning Large Language Models (LLMs) on benign narrow data can sometimes induce broad harmful behaviors, a vulnerability termed emergent misalignment (EM). While prior work li…
2026-05-08
Measuring Evaluation-Context Divergence in Open-Weight LLMs: A Paired-Prompt Protocol with Pilot Evidence of Alignment-Pipeline-Specific Heterogeneity
Safety benchmarks are routinely treated as evidence about how a language model will behave once deployed, but this inference is fragile if behavior depends on whether a prompt loo…
Evaluation Awareness in Language Models Has Limited Effect on Behaviour
Large reasoning models (LRMs) sometimes note in their chain of thought (CoT) that they may be under evaluation. Researchers worry that this verbalised evaluation awareness (VEA) c…
2026-05-07
Misaligned by Reward: Socially Undesirable Preferences in LLMs
Reward models are a key component of large language model alignment, serving as proxies for human preferences during training. However, existing evaluations focus primarily on bro…
Why Expert Alignment Is Hard: Evidence from Subjective Evaluation
Aligning large language models with expert judgment is especially difficult in subjective evaluation tasks, where experts may disagree, rely on tacit criteria, and change their ju…
2026-05-06
MOSAIC-Bench: Measuring Compositional Vulnerability Induction in Coding Agents
Coding agents often pass per-prompt safety review yet ship exploitable code when their tasks are decomposed into routine engineering tickets. The challenge is structural: existing…
Nora: Normalized Orthogonal Row Alignment for Scalable Matrix Optimizer
Matrix-based optimizers have demonstrated immense potential in training Large Language Models (LLMs), however, designing an ideal optimizer remains a formidable challenge. A super…
2026-05-05
MTA: Multi-Granular Trajectory Alignment for Large Language Model Distillation
Knowledge distillation is a key technique for compressing large language models (LLMs), but most existing methods align representations at fixed layers or token-level outputs, ign…
SRA: Span Representation Alignment for Large Language Model Distillation
Cross-Tokenizer Knowledge Distillation (CTKD) enables knowledge transfer between a large language model and a smaller student, even when they employ different tokenizers. While ex…
2026-05-01
Exploration Hacking: Can LLMs Learn to Resist RL Training?
Reinforcement learning (RL) has become essential to the post-training of large language models (LLMs) for reasoning, agentic capabilities and alignment. Successful RL relies on su…
Agent-Agnostic Evaluation of SQL Accuracy in Production Text-to-SQL Systems
Text-to-SQL (T2SQL) evaluation in production environments poses fundamental challenges that existing benchmarks do not address. Current evaluation methodologies whether rule-based…
Design Structure Matrix Modularization with Large Language Models
Design Structure Matrix (DSM) modularization, the task of partitioning system elements into cohesive modules, is a fundamental combinatorial challenge in engineering design. Tradi…
2026-04-29
LLM-ReSum: A Framework for LLM Reflective Summarization through Self-Evaluation
Reliable evaluation of large language model (LLM)-generated summaries remains an open challenge, particularly across heterogeneous domains and document lengths. We conduct a compr…
DV-World: Benchmarking Data Visualization Agents in Real-World Scenarios
Real-world data visualization (DV) requires native environmental grounding, cross-platform evolution, and proactive intent alignment. Yet, existing benchmarks often suffer from co…
Think Before You Act -- A Neurocognitive Governance Model for Autonomous AI Agents
The rapid deployment of autonomous AI agents across enterprise, healthcare, and safety-critical environments has created a fundamental governance gap. Existing approaches, runtime…
Progressing beyond Art Masterpieces or Touristic Clichés: how to assess your LLMs for cultural alignment?
Although the cultural (mis)alignment of Large Language Models (LLMs) has attracted increasing attention -- often framed in terms of cultural bias -- until recently there has been…
Conditional misalignment: common interventions can hide emergent misalignment behind contextual triggers
Finetuning a language model can lead to emergent misalignment (EM) [Betley et al., 2025b]. Models trained on a narrow distribution of misaligned behavior generalize to more egregi…
2026-04-24
Transient Turn Injection: Exposing Stateless Multi-Turn Vulnerabilities in Large Language Models
Large language models (LLMs) are increasingly integrated into sensitive workflows, raising the stakes for adversarial robustness and safety. This paper introduces Transient Turn I…
Inferring High-Level Events from Timestamped Data: Complexity and Medical Applications
In this paper, we develop a novel logic-based approach to detecting high-level temporally extended events from timestamped data and background knowledge. Our framework employs log…
KD-CVG: A Knowledge-Driven Approach for Creative Video Generation
Creative Generation (CG) leverages generative models to automatically produce advertising content that highlights product features, and it has been a significant focus of recent r…
GATE: Graph and Text Exchange for Zero-Shot ECG Classification with LLM Prompts.
Electrocardiography (ECG) is a fundamental tool for diagnosing cardiovascular diseases, yet the scarcity of large-scale annotated data limits the applicability of supervised learn…
2026-04-23
V-tableR1: Process-Supervised Multimodal Table Reasoning with Critic-Guided Policy Optimization
We introduce V-tableR1, a process-supervised reinforcement learning framework that elicits rigorous, verifiable reasoning from multimodal large language models (MLLMs). Current ML…
ONOTE: Benchmarking Omnimodal Notation Processing for Expert-level Music Intelligence
Omnimodal Notation Processing (ONP) represents a unique frontier for omnimodal AI due to the rigorous, multi-dimensional alignment required across auditory, visual, and symbolic d…
Where and What: Reasoning Dynamic and Implicit Preferences in Situated Conversational Recommendation
Situated conversational recommendation (SCR), which utilizes visual scenes grounded in specific environments and natural language dialogue to deliver contextually appropriate reco…
Relative Principals, Pluralistic Alignment, and the Structural Value Alignment Problem
The value alignment problem for artificial intelligence (AI) is often framed as a purely technical or normative challenge, sometimes focused on hypothetical future systems. I argu…
Can "AI" Be a Doctor? A Study of Empathy, Readability, and Alignment in Clinical LLMs
Large Language Models (LLMs) are increasingly deployed in healthcare, yet their communicative alignment with clinical standards remains insufficiently quantified. We conduct a mul…
Physics-Informed Conditional Diffusion for Motion-Robust Retinal Temporal Laser Speckle Contrast Imaging
Retinal laser speckle contrast imaging (LSCI) is a noninvasive optical modality for monitoring retinal blood flow dynamics. However, conventional temporal LSCI (tLSCI) reconstruct…
2026-04-22
Four-Axis Decision Alignment for Long-Horizon Enterprise AI Agents
Long-horizon enterprise agents make high-stakes decisions (loan underwriting, claims adjudication, clinical review, prior authorization) under lossy memory, multi-step reasoning,…
Taming Actor-Observer Asymmetry in Agents via Dialectical Alignment
Large Language Model agents have rapidly evolved from static text generators into dynamic systems capable of executing complex autonomous workflows. To enhance reliability, multi-…
Discovering a Shared Logical Subspace: Steering LLM Logical Reasoning via Alignment of Natural-Language and Symbolic Views
Large Language Models (LLMs) still struggle with multi-step logical reasoning. Existing approaches either purely refine the reasoning chain in natural language form or attach a sy…
Beyond Rating: A Comprehensive Evaluation and Benchmark for AI Reviews
The rapid adoption of Large Language Models (LLMs) has spurred interest in automated peer review; however, progress is currently stifled by benchmarks that treat reviewing primari…
SafetyALFRED: Evaluating Safety-Conscious Planning of Multimodal Large Language Models
Multimodal Large Language Models are increasingly adopted as autonomous agents in interactive environments, yet their ability to proactively address safety hazards remains insuffi…
Lost in Translation: Do LVLM Judges Generalize Across Languages?
Automatic evaluators such as reward models play a central role in the alignment and evaluation of large vision-language models (LVLMs). Despite their growing importance, these eva…
Diff-SBSR: Learning Multimodal Feature-Enhanced Diffusion Models for Zero-Shot Sketch-Based 3D Shape Retrieval
This paper presents the first exploration of text-to-image diffusion models for zero-shot sketch-based 3D shape retrieval (ZS-SBSR). Existing sketch-based 3D shape retrieval metho…
MMControl: Unified Multi-Modal Control for Joint Audio-Video Generation
Recent advances in Diffusion Transformers (DiTs) have enabled high-quality joint audio-video generation, producing videos with synchronized audio within a single model. However, e…
2026-04-21
StepPO: Step-Aligned Policy Optimization for Agentic Reinforcement Learning
General agents have given rise to phenomenal applications such as OpenClaw and Claude Code. As these agent systems (a.k.a. Harnesses) strive for bolder goals, they demand increasi…
IceBreaker for Conversational Agents: Breaking the First-Message Barrier with Personalized Starters
Conversational agents, such as ChatGPT and Doubao, have become essential daily assistants for billions of users. To further enhance engagement, these systems are evolving from pas…
Weakly-Supervised Referring Video Object Segmentation through Text Supervision
Referring video object segmentation (RVOS) aims to segment the target instance in a video, referred by a text expression. Conventional approaches are mostly supervised learning, r…
AnchorSeg: Language Grounded Query Banks for Reasoning Segmentation
Reasoning segmentation requires models to ground complex, implicit textual queries into precise pixel-level masks. Existing approaches rely on a single segmentation token $\texttt…
Revisiting Change VQA in Remote Sensing with Structured and Native Multimodal Qwen Models
Change visual question answering (Change VQA) addresses the problem of answering natural-language questions about semantic changes between bi-temporal remote sensing (RS) images.…
OmniHuman: A Large-scale Dataset and Benchmark for Human-Centric Video Generation
Recent advancements in audio-video joint generation models have demonstrated impressive capabilities in content creation. However, generating high-fidelity human-centric videos in…
Denoise and Align: Diffusion-Driven Foreground Knowledge Prompting for Open-Vocabulary Temporal Action Detection
Open-Vocabulary Temporal Action Detection (OV-TAD) aims to localize and classify action segments of unseen categories in untrimmed videos, where effective alignment between action…
2026-04-20
Medic Training at Military-Civilian Partnerships-A Narrative Review.
INTRODUCTION: Military-Civilian Partnerships (MCP) were developed to mitigate degradation of combat medical readiness during peacetime. Although these programs have historically f…
2026-04-18
MILU: a consensus ensemble benchmark for multimodal medical imaging lecture understanding.
PURPOSE: Vision-language models (VLMs) are increasingly used to interpret multimodal educational materials, yet their reliability on diagram-, equation-, and text-dense scientific…
An explainable multi-head attention network for healthcare IoT threat detection based on the MedDefender-MHAN framework.
The rapid proliferation of Internet of Medical Things (IoMT) devices in healthcare environments has created critical cybersecurity vulnerabilities that demand both accurate and in…
2026-04-17
QuantCode-Bench: A Benchmark for Evaluating the Ability of Large Language Models to Generate Executable Algorithmic Trading Strategies
Large language models have demonstrated strong performance on general-purpose programming tasks, yet their ability to generate executable algorithmic trading strategies remains un…
AI-Assisted Requirements Engineering: An Empirical Evaluation Relative to Expert Judgment
Artificial Intelligence is increasingly introduced into systems engineering activities, particularly within requirements engineering, where quality assessment and validation remai…
Meituan Merchant Business Diagnosis via Policy-Guided Dual-Process User Simulation
Simulating group-level user behavior enables scalable counterfactual evaluation of merchant strategies without costly online experiments. However, building a trustworthy simulator…
RaTA-Tool: Retrieval-based Tool Selection with Multimodal Large Language Models
Tool learning with foundation models aims to endow AI systems with the ability to invoke external resources -- such as APIs, computational utilities, and specialized models -- to…
From Boundaries to Semantics: Prompt-Guided Multi-Task Learning for Petrographic Thin-section Segmentation
Grain-edge segmentation (GES) and lithology semantic segmentation (LSS) are two pivotal tasks for quantifying rock fabric and composition. However, these two tasks are often treat…
2026-04-16
GeoAgentBench: A Dynamic Execution Benchmark for Tool-Augmented Agents in Spatial Analysis
The integration of Large Language Models (LLMs) into Geographic Information Systems (GIS) marks a paradigm shift toward autonomous spatial analysis. However, evaluating these LLM-…
Character Beyond Speech: Leveraging Role-Playing Evaluation in Audio Large Language Models via Reinforcement Learning
The rapid evolution of multimodal large models has revolutionized the simulation of diverse characters in speech dialogue systems, enabling a novel interactive paradigm. Character…
MUSE: Multi-Domain Chinese User Simulation via Self-Evolving Profiles and Rubric-Guided Alignment
User simulators are essential for the scalable training and evaluation of interactive AI systems. However, existing approaches often rely on shallow user profiling, struggle to ma…
MAny: Merge Anything for Multimodal Continual Instruction Tuning
Multimodal Continual Instruction Tuning (MCIT) is essential for sequential task adaptation of Multimodal Large Language Models (MLLMs) but is severely restricted by catastrophic f…
2026-04-15
EvoSpark: Endogenous Interactive Agent Societies for Unified Long-Horizon Narrative Evolution
Realizing endogenous narrative evolution in LLM-based multi-agent systems is hindered by the inherent stochasticity of generative emergence. In particular, long-horizon simulation…
Challenging Vision-Language Models with Physically Deployable Multimodal Semantic Lighting Attacks
Vision-Language Models (VLMs) have shown remarkable performance, yet their security remains insufficiently understood. Existing adversarial studies focus almost exclusively on the…
Multimodal large language models in brain tumor imaging: clinical applications and future perspectives.
The use of multimodal data is essential for the precise diagnosis and treatment of brain tumors. In this context, multimodal data encompass multisequence magnetic resonance imagin…
Bridging the Modality Gap in Medical Vision-Language Models: A Hybrid Contrastive-Optimal Transport Framework for Enhanced Cross-Modal Alignment.
Vision-language models in healthcare face a critical limitation, i.e., the modality gap, where image and text embeddings occupy distantly separated regions in shared representatio…
2026-04-14
RPA-Check: A Multi-Stage Automated Framework for Evaluating Dynamic LLM-based Role-Playing Agents
The rapid adoption of Large Language Models (LLMs) in interactive systems has enabled the creation of dynamic, open-ended Role-Playing Agents (RPAs). However, evaluating these age…
Detecting Safety Violations Across Many Agent Traces
To identify safety violations, auditors often search over large sets of agent traces. This search is difficult because failures are often rare, complex, and sometimes even adversa…
ClawGuard: A Runtime Security Framework for Tool-Augmented LLM Agents Against Indirect Prompt Injection
Tool-augmented Large Language Model (LLM) agents have demonstrated impressive capabilities in automating complex, multi-step real-world tasks, yet remain vulnerable to indirect pr…
Anthropogenic Regional Adaptation in Multimodal Vision-Language Model
While the field of vision-language (VL) has achieved remarkable success in integrating visual and textual information across multiple languages and domains, there is still no dedi…
Budget-Aware Uncertainty for Radiotherapy Segmentation QA Using nnU-Net
Accurate delineation of the Clinical Target Volume (CTV) is essential for radiotherapy planning, yet remains time-consuming and difficult to assess, especially for complex treatme…
HDR Video Generation via Latent Alignment with Logarithmic Encoding
High dynamic range (HDR) imagery offers a rich and faithful representation of scene radiance, but remains challenging for generative models due to its mismatch with the bounded, p…
Efficient KernelSHAP Explanations for Patch-based 3D Medical Image Segmentation
Perturbation-based explainability methods such as KernelSHAP provide model-agnostic attributions but are typically impractical for patch-based 3D medical image segmentation due to…
2026-04-08
Topological Characterization of Churn Flow and Unsupervised Correction to the Wu Flow-Regime Map in Small-Diameter Vertical Pipes
Churn flow-the chaotic, oscillatory regime in vertical two-phase flow-has lacked a quantitative mathematical definition for over $40$ years. We introduce the first topology-based…
MMEmb-R1: Reasoning-Enhanced Multimodal Embedding with Pair-Aware Selection and Adaptive Control
MLLMs have been successfully applied to multimodal embedding tasks, yet their generative reasoning capabilities remain underutilized. Directly incorporating chain-of-thought reaso…
Toward Consistent World Models with Multi-Token Prediction and Latent Semantic Enhancement
Whether Large Language Models (LLMs) develop coherent internal world models remains a core debate. While conventional Next-Token Prediction (NTP) focuses on one-step-ahead supervi…
Who Governs the Machine? A Machine Identity Governance Taxonomy (MIGT) for AI Systems Operating Across Enterprise and Geopolitical Boundaries
The governance of artificial intelligence has a blind spot: the machine identities that AI systems use to act. AI agents, service accounts, API tokens, and automated workflows now…
Lightweight Multimodal Adaptation of Vision Language Models for Species Recognition and Habitat Context Interpretation in Drone Thermal Imagery
This study proposes a lightweight multimodal adaptation framework to bridge the representation gap between RGB-pretrained VLMs and thermal infrared imagery, and demonstrates its p…
MMEmb-R1: Reasoning-Enhanced Multimodal Embedding with Pair-Aware Selection and Adaptive Control
MLLMs have been successfully applied to multimodal embedding tasks, yet their generative reasoning capabilities remain underutilized. Directly incorporating chain-of-thought reaso…
Lightweight Multimodal Adaptation of Vision Language Models for Species Recognition and Habitat Context Interpretation in Drone Thermal Imagery
This study proposes a lightweight multimodal adaptation framework to bridge the representation gap between RGB-pretrained VLMs and thermal infrared imagery, and demonstrates its p…
Scientific Graphics Program Synthesis via Dual Self-Consistency Reinforcement Learning
Graphics Program Synthesis is pivotal for interpreting and editing visual data, effectively facilitating the reverse-engineering of static visuals into editable TikZ code. While T…