{"total":105,"rows":[{"id":"2411.15124","title":"Tulu 3: Pushing Frontiers in Open Language Model Post-Training","created":"2024-11-22","cited_by_count":1053,"area":"lr"},{"id":"2409.05907","title":"Programming Refusal with Conditional Activation Steering","created":"2024-09-06","cited_by_count":206,"area":"mechinterp"},{"id":"2506.01937","title":"RewardBench 2: Advancing Reward Model Evaluation","created":"2025-06-02","cited_by_count":150,"area":"alignment"},{"id":"2506.09038","title":"AbstentionBench: Reasoning LLMs Fail on Unanswerable Questions","created":"2025-06-10","cited_by_count":145,"area":"lr"},{"id":"2407.18418","title":"Know Your Limits: A Survey of Abstention in Large Language Models","created":"2024-07-25","cited_by_count":121,"area":null},{"id":"2505.08054","title":"FalseReject: A Resource for Improving Contextual Safety and Mitigating Over-Refusals in LLMs via Structured Reasoning","created":"2025-05-12","cited_by_count":58,"area":"lr"},{"id":"2506.07022","title":"AlphaSteer: Learning Refusal Steering with Principled Null-Space Constraint","created":"2025-06-08","cited_by_count":49,"area":"safety"},{"id":"2410.14632","title":"Diverging Preferences: When do Annotators Disagree and do Models Know?","created":"2024-10-18","cited_by_count":47,"area":"alignment"},{"id":"2503.05021","title":"Safety is Not Only About Refusal: Reasoning-Enhanced Fine-tuning for Interpretable LLM Safety","created":"2025-03-06","cited_by_count":39,"area":"lr"},{"id":"2503.01807","title":"Large-Scale Data Selection for Instruction Tuning","created":"2025-03-03","cited_by_count":35,"area":null},{"id":"2506.17209","title":"Fine-Tuning Lowers Safety and Disrupts Evaluation Consistency","created":"2025-06-20","cited_by_count":27,"area":"safety"},{"id":"2602.02132","title":"There Is More to Refusal in Large Language Models than a Single Direction","created":"2026-02-02","cited_by_count":26,"area":"mechinterp"},{"id":"2505.12025","title":"Spotlight Your Instructions: Instruction-following with Dynamic Attention Steering","created":"2025-05-17","cited_by_count":21,"area":null},{"id":"2509.09708","title":"Beyond I'm Sorry, I Can't: Dissecting Large Language Model Refusal","created":"2025-09-07","cited_by_count":19,"area":"safety"},{"id":"2409.10566","title":"Eureka: Evaluating and Understanding Large Foundation Models","created":"2024-09-13","cited_by_count":18,"area":null},{"id":"2503.02574","title":"LLM-Safety Evaluations Lack Robustness","created":"2025-03-04","cited_by_count":18,"area":"alignment"},{"id":"2503.16870","title":"Sparse Logit Sampling: Accelerating Knowledge Distillation in LLMs","created":"2025-03-21","cited_by_count":16,"area":"distill"},{"id":"2507.14987","title":"AlphaAlign: Incentivizing Safety Alignment with Extremely Simplified Reinforcement Learning","created":"2025-07-20","cited_by_count":15,"area":"alignment"},{"id":"2601.12471","title":"Knowing When to Abstain: Medical LLMs Under Clinical Uncertainty","created":"2026-01-18","cited_by_count":15,"area":null},{"id":"2606.28733","title":"Agentic Abstention: Do Agents Know When to Stop Instead of Act?","created":"2026-06-27","cited_by_count":15,"area":"agents"},{"id":"2412.06748","title":"Refusal Tokens: A Simple Way to Calibrate Refusals in Large Language Models","created":"2024-12-09","cited_by_count":14,"area":null},{"id":"2504.01205","title":"Epistemic Alignment: A Mediating Framework for User-LLM Knowledge Delivery","created":"2025-04-01","cited_by_count":14,"area":null},{"id":"2507.10587","title":"Anthropomimetic Uncertainty: What Verbalized Uncertainty in Language Models is Missing","created":"2025-07-11","cited_by_count":14,"area":null},{"id":"2604.17073","title":"Abstain-R1: Calibrated Abstention and Post-Refusal Clarification via Verifiable RL","created":"2026-04-18","cited_by_count":14,"area":"lr"},{"id":"2409.09041","title":"Acceptable Use Policies for Foundation Models","created":"2024-08-29","cited_by_count":12,"area":null},{"id":"2410.17234","title":"Fine-Tuning Large Language Models to Appropriately Abstain with Semantic Entropy","created":"2024-10-22","cited_by_count":11,"area":null},{"id":"2412.06483","title":"SafeWorld: Geo-Diverse Safety Alignment","created":"2024-12-09","cited_by_count":11,"area":"wm"},{"id":"2601.05503","title":"Over-Searching in Search-Augmented Large Language Models","created":"2026-01-09","cited_by_count":11,"area":null},{"id":"2410.16665","title":"SafetyAnalyst: Interpretable, Transparent, and Steerable Safety Moderation for AI Behavior","created":"2024-10-22","cited_by_count":10,"area":null},{"id":"2510.09913","title":"Don't Throw Away Your Pretrained Model","created":"2025-10-10","cited_by_count":10,"area":"lr"},{"id":"2511.21322","title":"TALES: A Taxonomy and Analysis of Cultural Representations in LLM-generated Stories","created":"2025-11-26","cited_by_count":10,"area":null},{"id":"2505.17441","title":"Discovering Forbidden Topics in Language Models","created":"2025-05-23","cited_by_count":9,"area":null},{"id":"2506.00643","title":"SATA-BENCH: Select All That Apply Benchmark for Multiple Choice Questions","created":"2025-05-31","cited_by_count":9,"area":null},{"id":"2508.12116","title":"DynamixSFT: Dynamic Mixture Optimization of Instruction Tuning Collections","created":"2025-08-16","cited_by_count":9,"area":null},{"id":"2510.10390","title":"RefusalBench: Generative Evaluation of Selective Refusal in Grounded Language Models","created":"2025-10-12","cited_by_count":9,"area":"rag"},{"id":"2603.11838","title":"DatedGPT: Preventing Lookahead Bias in Large Language Models with Time-Aware Pretraining","created":"2026-03-12","cited_by_count":8,"area":null},{"id":"2507.04569","title":"Nile-Chat: Egyptian Language Models for Arabic and Latin Scripts","created":"2025-07-06","cited_by_count":7,"area":null},{"id":"2512.18880","title":"Can LLMs Estimate Student Struggles? Human-AI Difficulty Alignment with Proficiency Simulation for Item Difficulty Prediction","created":"2025-12-21","cited_by_count":7,"area":null},{"id":"2602.05176","title":"Among Us: Measuring and Mitigating Malicious Contributions in Model Collaboration Systems","created":"2026-02-05","cited_by_count":7,"area":"agents"},{"id":"2504.14452","title":"ParaPO: Aligning Language Models to Reduce Verbatim Reproduction of Pre-training Data","created":"2025-04-20","cited_by_count":6,"area":"alignment"},{"id":"2507.04976","title":"Can Video LLMs Refuse to Answer? Alignment for Answerability in Video Large Language Models","created":"2025-07-07","cited_by_count":6,"area":"mllm"},{"id":"2510.18731","title":"Mitigating Lost in Multi-turn Conversation via Curriculum RL with Verifiable Accuracy and Abstention Rewards","created":"2025-10-21","cited_by_count":6,"area":null},{"id":"2512.16883","title":"AdaSearch: Balancing Parametric Knowledge and Search in Large Language Models via Reinforcement Learning","created":"2025-12-18","cited_by_count":6,"area":null},{"id":"2601.21257","title":"MoCo: A One-Stop Shop for Model Collaboration Research","created":"2026-01-29","cited_by_count":6,"area":null},{"id":"2509.13664","title":"Sparse Neurons Carry Strong Signals of Question Ambiguity in LLMs","created":"2025-09-17","cited_by_count":5,"area":null},{"id":"2510.17733","title":"Train for Truth, Keep the Skills: Binary Retrieval-Augmented Reward Mitigates Hallucinations","created":"2025-10-20","cited_by_count":5,"area":"rag"},{"id":"2511.04694","title":"Reasoning Up the Instruction Ladder for Controllable Language Models","created":"2025-10-30","cited_by_count":5,"area":"lr"},{"id":"2510.27087","title":"Characterizing Selective Refusal Bias in Large Language Models","created":"2025-10-31","cited_by_count":4,"area":"safety"},{"id":"2605.15000","title":"Quantifying and Mitigating Premature Closure in Frontier LLMs","created":"2026-05-14","cited_by_count":4,"area":null},{"id":"2605.20544","title":"The Yes-Man Syndrome: Benchmarking Abstention in Embodied Robotic Agents","created":"2026-05-19","cited_by_count":4,"area":"mllm"},{"id":"2607.07916","title":"Persona Cartography: Charting Language Model Personality Traits in Weight Space","created":"2026-07-08","cited_by_count":4,"area":null},{"id":"2409.16913","title":"Tell Me What You Don't Know: Enhancing Refusal Capabilities of Role-Playing Agents via Representation Space Analysis and Editing","created":"2024-09-25","cited_by_count":3,"area":null},{"id":"2506.07402","title":"Beyond Jailbreaks: Revealing Stealthier and Broader LLM Security Risks Stemming from Alignment Failures","created":"2025-06-09","cited_by_count":3,"area":"alignment"},{"id":"2601.03699","title":"RedBench: A Universal Dataset for Comprehensive Red Teaming of Large Language Models","created":"2026-01-07","cited_by_count":3,"area":"safety"},{"id":"2603.03323","title":"Discern Truth from Falsehood: Reducing Over-Refusal via Contrastive Refinement","created":"2026-02-10","cited_by_count":3,"area":"safety"},{"id":"2604.27093","title":"Useless but Safe? Benchmarking Utility Recovery with User Intent Clarification in Multi-Turn Conversations","created":"2026-04-29","cited_by_count":3,"area":"alignment"},{"id":"2605.25284","title":"Knowing but Not Showing: LLMs Recognize Ambiguity but Rarely Ask Clarifying Questions","created":"2026-05-24","cited_by_count":3,"area":null},{"id":"2606.25013","title":"Do Thinking Tokens Help with Safety?","created":"2026-06-23","cited_by_count":3,"area":"lr"},{"id":"2412.07430","title":"Knowledge Graph Guided Evaluation of Abstention Techniques","created":"2024-12-10","cited_by_count":2,"area":null},{"id":"2506.04051","title":"High Accuracy, Less Talk (HALT): Reliable LLMs through Capability-Aligned Finetuning","created":"2025-06-04","cited_by_count":2,"area":null},{"id":"2506.11604","title":"VLM@school -- Evaluation of AI image understanding on German middle school knowledge","created":"2025-06-13","cited_by_count":2,"area":"lr"},{"id":"2602.00906","title":"Hallucination is a Consequence of Space-Optimality: A Rate-Distortion Theorem for Membership Testing","created":"2026-01-31","cited_by_count":2,"area":null},{"id":"2602.05182","title":"The Single-Multi Evolution Loop for Self-Improving Model Collaboration Systems","created":"2026-02-05","cited_by_count":2,"area":"synth"},{"id":"2603.10243","title":"GR-SAP: Generative Replay for Safety Alignment Preservation during Fine-Tuning","created":"2026-03-10","cited_by_count":2,"area":"alignment"},{"id":"2604.06233","title":"Blind Refusal: Language Models Refuse to Help Users Evade Unjust, Absurd, and Illegitimate Rules","created":"2026-04-03","cited_by_count":2,"area":null},{"id":"2604.27019","title":"Dynamic Adversarial Fine-Tuning Reorganizes Refusal Geometry","created":"2026-04-29","cited_by_count":2,"area":"alignment"},{"id":"2605.12120","title":"To Whom Do Language Models Align? Measuring Principal Hierarchies Under High-Stakes Competing Demands","created":"2026-05-12","cited_by_count":2,"area":null},{"id":"2606.07812","title":"Scaling Participation in Modular AI Systems","created":"2026-06-05","cited_by_count":2,"area":null},{"id":"2606.11105","title":"PhantomBench: Benchmarking the Non-existential Threat of Language Models","created":"2026-06-09","cited_by_count":2,"area":null},{"id":"2608.01358","title":"HopRefusalBench: Diagnosing Refusal Failures in Search-Augmented Agents for Multi-Hop Reasoning","created":"2026-08-02","cited_by_count":2,"area":"lr"},{"id":"2410.21597","title":"Reducing the Scope of Language Models","created":"2024-10-28","cited_by_count":1,"area":null},{"id":"2506.00195","title":"Let Them Down Easy! Contextual Effects of LLM Guardrails on User Perceptions and Preferences","created":"2025-05-30","cited_by_count":1,"area":"alignment"},{"id":"2506.12382","title":"Exploring the Secondary Risks of Large Language Models","created":"2025-06-14","cited_by_count":1,"area":"alignment"},{"id":"2509.23108","title":"Artificial Phantasia: Emergent Mental Imagery in Large Language Models","created":"2025-09-27","cited_by_count":1,"area":null},{"id":"2510.27052","title":"VISTA: Verification In Sequential Turn-based Assessment","created":"2025-10-30","cited_by_count":1,"area":null},{"id":"2511.17161","title":"The PLLuM Instruction Corpus","created":"2025-11-21","cited_by_count":1,"area":null},{"id":"2602.11938","title":"Who is the richest club in the championship? Detecting and Rewriting Underspecified Questions Improve QA Performance","created":"2026-02-12","cited_by_count":1,"area":null},{"id":"2603.13359","title":"From Refusal Tokens to Refusal Control: Discovering and Steering Category-Specific Refusal Directions","created":"2026-03-09","cited_by_count":1,"area":"alignment"},{"id":"2604.18473","title":"Train Separately, Merge Together: Modular Post-Training with Mixture-of-Experts","created":"2026-04-20","cited_by_count":1,"area":"moe"},{"id":"2604.26419","title":"Delineating Knowledge Boundaries for Honest Large Vision-Language Models","created":"2026-04-29","cited_by_count":1,"area":"mllm"},{"id":"2605.21545","title":"RefusalBench: Why Refusal Rate Misranks Frontier LLMs on Biological Research Prompts","created":"2026-05-20","cited_by_count":1,"area":null},{"id":"2605.24154","title":"Palette: A Modular, Controllable, and Efficient Framework for On-demand Authorized Safety Alignment Relaxation in LLMs","created":"2026-05-22","cited_by_count":1,"area":"alignment"},{"id":"2606.00869","title":"Enhancing LLM Metacognition via Cognitive Pairwise Training","created":"2026-05-30","cited_by_count":1,"area":"lr"},{"id":"2608.30856","title":"You Shouldn't Have Asked: A Pragmatics-Inspired Taxonomy for Evaluating LLM Refusals","created":"2026-08-31","cited_by_count":1,"area":null},{"id":"2609.25049","title":"Mitigating LLM Over-Refusal via Dynamic Semantic Routing Calibration","created":"2026-09-06","cited_by_count":1,"area":"safety"},{"id":"2510.03527","title":"Sample, Align, Synthesize: Graph-Based Response Synthesis with ConGrs","created":"2025-10-03","cited_by_count":0,"area":null},{"id":"2601.03273","title":"A Multi-Perspective Benchmark and Moderation Model for Evaluating Safety and Adversarial Robustness","created":"2025-12-22","cited_by_count":0,"area":"safety"},{"id":"2601.09853","title":"MedRedFlag: Investigating how LLMs Redirect Misconceptions in Real-World Health Communication","created":"2026-01-14","cited_by_count":0,"area":null},{"id":"2605.16272","title":"Beyond Compliance: How AI Could Help Creative Writers by Refusing Them","created":"2026-04-03","cited_by_count":0,"area":null},{"id":"2605.20262","title":"Residual Paving: Diagnosing the Routing Bottleneck in Selective Refusal Editing","created":"2026-05-18","cited_by_count":0,"area":null},{"id":"2607.00572","title":"HARC: Coupling Harmfulness and Refusal Directions for Robust Safety Alignment","created":"2026-07-01","cited_by_count":0,"area":"alignment"},{"id":"2607.01104","title":"CausalMix: Data Mixture as Causal Inference for Language Model Training","created":"2026-07-01","cited_by_count":0,"area":null},{"id":"2607.14105","title":"Automatically Evolving Prompt Guidelines for Task-Specific Optimization","created":"2026-05-07","cited_by_count":0,"area":null},{"id":"2607.20472","title":"Robust Critics: Defending LLMs Against Multi-Turn Attacks","created":"2026-05-24","cited_by_count":0,"area":"safety"},{"id":"2608.06578","title":"From Behavior to Mechanism: Tracing Divergent Response Modes in Frontier Language Models","created":"2026-08-06","cited_by_count":0,"area":null},{"id":"2608.23870","title":"Granite.Trust Policy Tools: Shareable, Actionable Policies for Generative AI Applications","created":"2026-08-24","cited_by_count":0,"area":null},{"id":"2609.02707","title":"Door-in-the-Face Requests and Refusal Behaviour in Large Language Models","created":"2026-09-02","cited_by_count":0,"area":null},{"id":"2609.02771","title":"From Reweighting to Rewriting: Unlocking the Intervention Effects of Influential Samples in Training Data Attribution","created":"2026-09-02","cited_by_count":0,"area":null},{"id":"2609.04720","title":"Knowing What Not to Answer: Selective Non-Compliance in Vision-Language Models","created":"2026-09-04","cited_by_count":0,"area":"mllm"},{"id":"2609.23939","title":"XYEval: Agents say yes to bad advice","created":"2026-09-20","cited_by_count":0,"area":null}],"next_cursor":"100"}