Refusals

Ask about this topic

Momentum

16 papers in the last four weeks, down 6% on the four weeks before. 0.2% of all new papers.

Jul 13Week of Sep 28
View on map

Latest papers 137

All topics
CardsList

  1. TRACE: Trajectory Return Attribution and Contrastive Erasure for Multi-Turn Safety

    Oct 1, 2026Fengpeng Li, Kemou Li, Qizhou Wang +3Large Language Model SafetyAttack-Success Rate

    PRADA Lab, King Abdullah University of Science and Technology · State Key Laboratory of Internet of Things for Smart City, University of Macau · Imperfect Information Learning Team, RIKEN Center for Advanced Intelligence Project +1

  2. Deny Without Disabling: Authorization-Paired Evaluation and Control for Multi-Agent Systems

    Sep 30, 2026Yunbei Zhang, Saiyue Lyu, Janet Wang +4AuthorizationModel-Based Multi-Agent Systems

    Tulane University · University of British Columbia · Independent Researcher +1

  3. Refusals That Bend: Measuring and Predicting Task Malleability in Embodied VLM Planners

    Sep 30, 2026Leo Y. Lin, Mikhail Kuznetsov, Muslum Ozgur Ozmen +1Safety AlignmentRefusals

    Purdue University · Amazon · Arizona State University

  4. CompOrca: Corpus-Scale Compliance Labelling of Instruction-Tuning Data

    Sep 29, 2026Philipp E. Glass, Alina MironComplianceRefusals

    Department of Computer Science, Brunel University of London

  5. Safer Content or Firmer Refusals? A Hybrid Perturbation Defense for Alignment under Harmful Fine-tuning

    Sep 29, 2026Muhammad Zeeshan Akram, Mufid Kamel Marican, Anvesh Reddy Yenugu +2Model-Agnostic DefenseLarge Language Model Safety

    University of Louisville Louisville, Kentucky, USA

  6. Less Sycophancy, Stronger Refusal? Lessons for AI Safety from Mechanistic Interpretability

    Sep 28, 2026Xu Wang, Difan Zou, Xuansheng WuSycophancyRefusals

    The University of Hong Kong · Shenzhen Loop Area Institute · Shanghai Artificial Intelligence Laboratory

  7. Tool Mediation Alters Refusal Mechanisms in Large Language Models

    Sep 28, 2026Abel Rodríguez, Giuseppe Garofalo, Lieven Desmet +1Large Language Models FailRefusals

    DistriNet, KU Leuven

  8. DeShortcut-Align: Decoupling Spurious Shortcuts for Robust Safety Alignment in Large Reasoning Models

    Sep 28, 2026Qirui Liu, Yichen Sun, Yan Wang +4Safety AlignmentLarge Language Model Alignment

    The State Key Laboratory of Blockchain and Data Security, Zhejiang University · Ant Group · Chongqing Ant Consumer Finance Co., Ltd

  9. AgentBoundary: Counterfactual Evaluation of Safety in Tool-Using LLM Agents

    Sep 27, 2026Tianzhuo Yang, Zirui Mi, Yantao Huang +4RefusalsEvaluation Benchmarks

    Peking University · Beijing Academy of Artificial Intelligence

  10. EnigmaForge: The Question Is Hidden in the Story

    Sep 24, 2026Daniel EisnerFrontier ModelsLanguage Model Computes

  11. AEGIS: Audio Endogenous Guarding via Internal Signals Against Large Audio-Language Model Jailbreaks

    Sep 24, 2026Yu-Ling Liao, Tzu-Chin Chiu, Zong-You Chen +2Large Language Model JailbreaksRefusals

    National Taiwan University

  12. A Policy Profile for Croissant: Refusal as a Property of the Dataset

    Sep 17, 2026Alexander ChernovGeneration ProvenanceTaco

    Independent Researcher Toronto, Ontario, Canada

  13. First Token Matters: Understanding Safety Collapse in Large Reasoning Models

    Sep 16, 2026Yizheng Yang, Haining Yu, Yuechen Wang +4Large Language Model SafetyLarge Reasoning Models

    Harbin Institute of Technology, Harbin, China · Guangzhou University, Guangzhou, China · City University of Macau, Macau, China

  14. Benchmarking Factual Robustness of LLMs via Multi-conversation Persuasion

    Sep 15, 2026Zhuoang CaiAttacker Large Language ModelPersuasion

    The Hong Kong University of Science and Technology

  15. Refusal Reads Only a Slice of What the Model Knows: Harm-Keyed Routing and Its Exceptions Across Model Families

    Sep 13, 2026Orion Reblitz-RichardsonRefusalsMoral Reasoning

    Distiller Labs.

  16. Style Over Substance: Content-Invariant Wrappers Flip LLM Safety-Judge Verdicts

    Sep 8, 2026Yongxi Zhou, Wenbo Ye, Yuanzhe Liu +2Large Language Model SafetyJailbreak Success Rates

    Northeastern University, Massachusetts, USA · University of Southern California, California, USA · Georgia Institute of Technology, Georgia, USA

  17. Mitigating LLM Over-Refusal via Dynamic Semantic Routing Calibration

    Sep 6, 2026Zixuan Wang, Bingjie Zhang, He Zhao +1Large Language Model SafetyRefusals

    School of Artificial Intelligence, Jilin University · CSIRO, Australia · Center of Excellence for Generative AI, King Abdullah University of Science and Technology

  18. Beyond Shallow Alignment: How Post-Training Methods Determine Refusal Circuits And Steering Robustness

    Sep 3, 2026Hoang Cuong Nguyen, Mark Dras, Usman NaseemRefusalsLarge Language Model Alignment

    Macquarie University, Sydney, Australia

  19. Extracting Forgotten Prompts from Targeted Unlearned Models

    Sep 3, 2026Au Ashley Hoi-Ting, Meghdad Kurmanji, William F. Shen +2Exact UnlearningPrompt Engineering

    University of Warwick · University of Cambridge

  20. When Safety Routing Breaks: Understanding Alignment Fragility under Benign Fine-Tuning

    Sep 1, 2026Yitong Guo, Xiaoyi Chen, Siyuan Zhang +2FragilityModel Fine-Tuning

    Indiana University Bloomington · Tsinghua University · Nanyang Technological University

  21. A Unified Mechanistic Analysis of Knowledge- and Safety-Based Refusals

    Sep 1, 2026Yuri Son, Seunghee Kim, Hyuhng Joon Kim +1RefusalsLLM Reasoning Strategies

    1Hanyang University · 2Samsung Electronics

  22. Same Request, Different Boundary: Evaluating Cybersecurity Assistance across Conversational Contexts

    Sep 1, 2026Rui Yang, Yang Hong, Yichao Xu +3Large Language Model SafetyCybersecurity

    Johns Hopkins University

  23. Beyond Token Positions: Safety Alignment Across Denoising Steps in Diffusion Language Models

    Aug 31, 2026Guoli Wang, Haonan Shi, Tu Ouyang +1Diffusion Language ModelsLarge Language Model Safety

    Case Western Reserve University 10900 Euclid Avenue, Cleveland, OH 44106, USA

  24. Controlling Refusal Behavior of LLMs via Stiefel-Constrained Rotation Steering

    Aug 31, 2026Kirill Bunin, Dmitry Bylinkin, Vladimir Aletov +3Linear Activation SteeringSteering

    1Basic Research of Artificial Intelligence Laboratory (BRAIn Lab) · 2Kandinsky Lab · 3Innopolis University

  25. You Shouldn't Have Asked: A Pragmatics-Inspired Taxonomy for Evaluating LLM Refusals

    Aug 31, 2026Ruoxuan Li, Pinqiao Wang, Sheng Li +1RefusalsImplications

    Stony Brook University · University of Virginia

  26. The Safety Relay in Roleplay Jailbreaks: A Component-Resolved Causal Analysis of Harm Recognition and Refusal

    Aug 31, 2026Md Mokarram Chowdhury, Ernie Chang, Yang LiJailbreaksJailbreak Attacks

    Department of Computer Science, Iowa State University, United States · Meta, United States

  27. ALTSTEER: Selective Safety Steering for Moving Beyond Hard Refusals to Constructive Alternatives

    Aug 31, 2026Hoejoon Kwon, Byeonggeuk Lim, Kahyeon Kim +1SteeringRefusals

    Department of Artificial Intelligence, Chung-Ang University · Graduate School of Advanced Imaging Science, Multimedia & Film, Chung-Ang University

  28. Refusal geometry reflects refusal training: diverse refusal prefixes can raise stable rank and weaken refusal vector ablation attacks

    Aug 26, 2026Andrey LabunetsRefusalsLarge Language Models Fail

    UC San Diego

  29. An Empirical Study of Reward Specification and Benchmark Reliability in GRPO-based LLM Unlearning

    Aug 18, 2026Rubén Balbastre, Juan Manuel Orduña, Mariano PérezLarge Language Model UnlearningUnlearning Method

    University of Valencia

  30. Refusing Intent, Not Form: Wrapper-Based Intent-Group Supervision for LLM Safety

    Aug 13, 2026Ping Wu, Haibo Tong, Feifei Zhao +7RefusalsLarge Language Model Safety

    BrainCog Lab, Institute of Automation, Chinese Academy of Sciences · School of Artificial Intelligence, University of Chinese Academy of Sciences · Beijing Key Laboratory of Safe AI and Superalignment +2

  31. How China-Origin Vision-Language Models Move from Refusal to Reframing in State Alignment

    Aug 12, 2026Guang Yang, Fengchen Liu, Alex Wang +2Large Language Model AlignmentRefusals

    University of California, Los Angeles · University of California, Berkeley · Stanford University

  32. Making Your LLMs More Objective: Stabilizing LLM Safety Behavior Across Traits with Trait-Invariant Safety Tuning

    Aug 12, 2026Lang CaoLarge Language Model SafetyRefusals

    University of Illinois Urbana-Champaign

  33. The Illusion of Cross-Lingual Safety in Low-Resource Languages

    Aug 11, 2026Abigail Oppong, P Sam Sahil, Tadesse Destaw Belay +12Multilingual SafetyLarge Language Model Safety

    Makerere University Center for Artificial Intelligence · University of Hamburg · Instituto Politécnico Nacional +9

  34. When Skills Meet Safety: Benchmarking and Characterizing the Adaptive Jailbreak Robustness of Skill-Merged LLMs

    Aug 9, 2026Yu Ma, Hongli Shi, Jing Li +2Safety AlignmentRefusals

    Google · University of New South Wales · University of Technology Sydney +2

  35. Decided Upstream, Written Late: Locating and Pricing the Cross-Lingual Refusal Circuit of a Multilingual MoE

    Aug 8, 2026Ramakrishna P. Kompella, Aadit MahajanMultilingual SafetyRefusals

    Gödel Machines · IIT Madras

  36. Mood Matters: How Syntactic Sensitivity Undermines Safety Alignment

    Aug 5, 2026Alina Klerings, Jannik Brinkmann, Heiner Stuckenschmidt +1Safety AlignmentLarge Language Model Alignment

    University of Mannheim · Technical University Clausthal

  37. Teaching MLLMs to Say No: Generalized Referring Expression Comprehension via Refusal Calibrated GRPO

    Aug 5, 2026Xuzheng Yang, Jun Ling, Tao Huang +2RefusalsLLM Reasoning Strategies

    School of Computer Science and Engineering, University of Electronic Science and Technology of China

  38. When Refusal Looks Safe: The Refusal-Cue Shortcut in Safety Guard Models

    Aug 4, 2026Yu Feng, Chunting Zang, Chen Shen +4RefusalsSuppression

    The University of Sydney · Alibaba Group · Jilin University +1

  39. DenialRAG: Single-Document RAG Poisoning via Embedded Parametric Denial

    Aug 2, 2026Abay Zhurekbay, Tao Liu, Fan LiAgentic Retrieval-Augmented Generation SystemsPoisoning

    Lawrence Technological University

  40. Moving the Safety Barrier: Dynamic Routing Adaptive Alignment Against White-Box Attacks

    Aug 2, 2026Shangze Li, Chuancheng Shi, Simiao Xie +6Model-Agnostic DefenseSafety Alignment

    1Nanjing University of Science and Technology · 2The University of Sydney · 5NExT++ Research Centre, National University of Singapore +2

  41. HopRefusalBench: Diagnosing Refusal Failures in Search-Augmented Agents for Multi-Hop Reasoning

    Aug 2, 2026Jianan Xie, Xin Sun, Zhongqi Chen +3Search AgentsMulti-Hop Reasoning

    ShanghaiTech University · NLPR, MAIS, CASIA · Ant Group

  42. Knowing When to Quit: Diagnosing and Training LLMs to Abort Futile Reasoning

    Jul 31, 2026Xinyan Guan, Jiali Zeng, Chunlei Xin +5RefusalsLarge Language Model Training

    1Chinese Information Processing Laboratory, Institute of Software, Chinese Academy of Sciences · University of Chinese Academy of Sciences · 3Weixin AI, Tencent Inc, China

  43. Rolling With Resistance: Preference-Optimized LLM Counselors Can Trade Goal Persistence for Relational Attunement in Motivational Interviewing

    Jul 30, 2026Weiying Chen, Junlong Shen, Zhexuan TangIntrinsic MotivationCounseling

    University of Alberta · University of Shanghai for Science and Technology

  44. Asymmetric Collapse in Model Merging: When Refusal Over- writes Recognition

    Jul 26, 2026Aarnav Choudhary, Matheus Fonseca Rocha, Jiwon Seo +2Continual Model MergingSafety Alignment

    UCLA · Algoverse · Purdue University +1

  45. Refusal-Gated Decoding: Preserving Refusal Behavior Under High-Temperature Sampling

    Jul 22, 2026Phillip Howard, Xin Su, Allen Roush +2RefusalsLarge Language Models Fail

    Thoughtworks

  46. Geometric Configurations of Perturbed Jailbreak Prompts

    Jul 22, 2026Lynn Delcon, Andres Algaba, Vincent GinisLarge Language Model JailbreaksJailbreak Attacks

    Department of Business Technology and Operations, Data Analytics Laboratory, Vrije Universiteit Brussel, Pleinlaan 2, 1050 Brussels, Belgium · imec-SMIT, Vrije Universiteit Brussel, Pleinlaan 9, 1050 Brussels, Belgium · School of Engineering and Applied Sciences, Harvard University, Cambridge, Massachusetts 02138, USA

  47. OPIUM: Mitigating Steering Externalities and Over-Refusal via Dual Objective Latent Optimization

    Jul 22, 2026Kavin Aravindan, Arihant Rastogi, Krishak Aneja +4Linear Activation SteeringModel Activations

    IIIT Hyderabad, India.

  48. Adaptive Capitulation: A Structural Failure Mode of LLM Responses in Vulnerability Contexts

    Jul 21, 2026Eunna LeeLarge Language Models FailRefusals

    Independent Researcher

  49. Abliteration Is Not a Scalpel: Off-Target Effects of Refusal Removal on Decision Disposition Across Model Families

    Jul 19, 2026Aleksander FafułaAblationRefusals

    independent researcher • funduszai.pl

  50. The Refusal Residue: When Probes Catch Alignment Faking and When They Don't

    Jul 15, 2026Aman MehtaFake NewsRefusals

    Snowflake AI Research

  51. Compile, Then Page: Executable SOP Programs and a Capability-Gated Runtime for Procedural LLM Agents

    Jul 13, 2026Chenglin Yu, Li Yin, Ying Yu +4Refusals

    Department of Industrial and Systems Engineering, The Hong Kong Polytechnic University · Department of Data and Systems Engineering, The University of Hong Kong · College of Economics and Management, Zhejiang Normal University +3

  52. The Paternalistic Filter: Epistemic Injustice and Differential Refusal in LLM-Mediated History Education for Marginalized Romanian Students

    Jul 13, 2026Alexis Popovici, Andrei Ionascu, Adrian-Marius DumitranEpistemic StatesTutors

    Universitatea din Bucuresti, Bucharest, Romania

  53. Capabilities of Claude Fable 5 on Biomedical Challenge Problems

    Jul 12, 2026Dominic Okonkwo, Magnus Hodgson, Temitope I. David +1Biomedical TextDiagnostic Benchmark

    School of Computing, University of Georgia · Department of Chemistry, University of Illinois · Institute of Bioinformatics, University of Georgia

  54. Minionese: Comprehensive Benchmark and Mechanistic Study of Multilingual LLM Safety

    Jul 11, 2026Chigozirim Ifebi, Brent Kong, Ayushi MehrotraMultilingual SafetyLarge Language Model Safety

    California Institute of Technology.

  55. Optimizing Against Safety Representations: Activation-Guided Adversarial Suffixes and the Geometry of Refusal

    Jul 9, 2026Ege Çakar, Hannah Guan, Kayden KeheSafety AlignmentRefusals

    Harvard University

  56. Beyond Refusal: A Same-Lineage Study of Aligned and Abliterated LLMs for Vulnerability Analysis

    Jul 7, 2026Mingchen Li, Meikang Qiu, Zifan Peng +4Large Language Model SafetyModel Vulnerabilities

    University of North Texas, USA · Augusta University, USA · Newcastle University, United Kingdom

  57. Faithfulness to Refusal: A Causal Audit of Neuron Selectors

    Jul 6, 2026Ananth Eswar, Pratinav Seth, Utsav Avaiya +1RefusalsCausal Intervention

    Lexsi Labs · Work done while at Lexsi Labs.

  58. Evaluating calibrated refusal and safe usefulness in dual-use biology settings

    Jul 6, 2026Edwin H. Wintermute, Harmon Bhasin, Christina M. Agapakis +13RefusalsScientific Workflows

    American Wetware, Boston, MA · LatchBio, San Francisco, CA

  59. Refused in Chat, Written in Code: Workflow-Level Jailbreak Construction in IDE Coding Agents

    Jul 4, 2026Abhishek Kumar, Carsten MapleCoding AgentsLarge Language Model Safety

    The Alan Turing Institute, London, United Kingdom

  60. Not All Refusals Are Equal: How Safety Alignment Fails Cybersecurity at Scale

    Jul 2, 2026Vadym Hadetskyi, Dario Pasquini, Artem SorokinSafety AlignmentCybersecurity

    Cracken AI