Model Auditing

Ask about this topic

Momentum

105 papers in the last four weeks, up 133% on the four weeks before. 1.0% of all new papers.

Jul 13Week of Sep 28
View on map

Latest papers 538

All topics
CardsList

  1. PairAudit: Guiding Human Review with Graph Tokens under Distribution Shift

    Oct 7, 2026Jiran Tao, Binyan JiangModel Auditing

    The Hong Kong Polytechnic University

  2. Comprehension Audits to Mitigate Risks from Automated AI Research

    Oct 7, 2026Ronald J. Bodkin, Bahrad A. Sokhansanj, Gillian K. HadfieldCode QualityModel Auditing

    Independent · Institute for Law and AI · Johns Hopkins University

  3. Shared and structured inputs undermine collective random choice by reasoning AI agents

    Oct 7, 2026Takahiro Ezaki, Naoto Imura, Katsuhiro NishinariRandomModel Auditing

    Research Center for Advanced Science and Technology, The University of Tokyo 4-6-1 Komaba, Meguro-ku, Tokyo 153-8904, Japan · Department of Aeronautics and Astronautics, School of Engineering, The University of Tokyo 7-3-1 Hongo, Bunkyo-ku, Tokyo 113-8656, Japan

  4. Finding Blind Spots in AppWorld and WorkArena Task Verifiers

    Oct 6, 2026Richard AbrichVerification FrameworkModel Auditing

    OpenAdapt.AI (MLDSAI Inc.)

  5. Learning to Report Unsafe Tasks in a Multi-Agent Game

    Oct 6, 2026Avyay M. Casheekar, Hariganesh TangiralaModel Auditing

    University of Michigan Law School Ann Arbor, USA · School of Computing National University of Singapore Singapore, Singapore

  6. CHARTER: Auditing Reference Substitution in Hierarchical Compact-Evidence Evaluation for Computational Pathology

    Oct 6, 2026Hyun Do Jung, Jungwon Choi, Soojung Choi +2Model AuditingComparison

    Yonsei University · KAIST · Hallym University Chuncheon Sacred Heart Hospital

  7. Harmful SFT Leaves a Continuous Trace in LLM Checkpoint Updates

    Oct 5, 2026Ziqun Bao, Xinyu Zhang, Yuchen Shao +1Large Language Model SafetySupervised Finetuning

    SEI, East China Normal University

  8. Auditable Claims about AI Agents

    Oct 5, 2026Yue Zhao, Jiate Li, Li Li +4Model Auditing

    University of Southern California, Los Angeles, CA, USA · Arizona State University, Tempe, AZ, USA

  9. Correct Verdicts, Flawed Reasoning: Structured Auditing of LLM-based Vulnerability Reasoning

    Oct 5, 2026Boyue Caroline Hu, Kaivalya Ahir, Ronghao Ni +1Model Auditing

    Carnegie Mellon University, Pittsburgh, Pennsilvanya, USA

  10. Measurement-First Auditing of Agentic Leaderboards: Contamination Susceptibility, Matched-Control Re-evaluation, and Scorer Validation

    Oct 5, 2026Dishu Yang, Qi Su, Hongbo Qin +1LeaderboardModel Auditing

    Khoury College of Computer Sciences Northeastern University San Jose, CA, USA · School of Engineering and Applied Science The George Washington University Bellevue, WA, USA · Khoury College of Computer Sciences Northeastern University Boston, MA, USA +1

  11. SALUS: Automated Auditing of NL-to-SQL Benchmarks through Weak Supervision of Multi-Agent Output

    Oct 4, 2026Shiyuan Zhou, Ashwin Gerard Colaco, Sainyam Galhotra +1Legal Natural Language Processing BenchmarksModel Auditing

    University of California, Irvine, Irvine, California, USA · Cornell University, Ithaca, New York, USA

  12. A Comparative Explainability Framework for DeBERTa-v3 in Zero-Shot Medical Abstract Classification

    Oct 1, 2026Javier Diaz Esteban-Herreros, David Muñoz-Valero, Raquel Martínez-España +2ExplainabilityBert-Based Models

    Department of Technologies and Information Systems, Universidad de Castilla-La Mancha, Avenida Carlos III, s/n, Toledo, 45071, Spain · University of Murcia, Avenida Teniente Flomesta, 5, Murcia, 3003, Spain · Murcian Bio-Health Institute (IMIB-Arrixaca), Pabellón Docente del Hospital Clínico Universitario Virgen de la Arrixaca, Murcia, 3120, Spain

  13. Counterfactual Auditing of Bias in Open-Source Large Language Models for Clinical Triage

    Oct 1, 2026Manar Aljohani, Brandon Ho, Kenneth McKinley +2Large Language Model BiasTriage

    Department of Computer Science Virginia Tech Blacksburg, VA, US · Division of Emergency Medicine University of Washington and Seattle Children’s Hospital Seattle, WA, USA · Children’s National Hospital Washington DC, USA

  14. How the Audit Rule Shapes Faithful Factor Explanations in LLMs

    Oct 1, 2026Taolin Zhang, Hanyu Wang, Jiuheng Wan +2Model AuditingLarge Language Model Reliability

    Hefei University of Technology · East China Normal University · Alibaba Cloud Computing

  15. OpenMTB-Audit: Exposing Over-Refusal and Clinical Expert Perspectives in LLM-Based Molecular Tumor Board Safety Evaluation

    Oct 1, 2026Negin Ashrafi, Jia Luo, Stacey M. Frumm +1Multidisciplinary Tumor BoardsClinical

    Department of Biomedical Data Science, Stanford University, Stanford, CA, USA · Lowe Center for Thoracic Oncology, Dana-Farber Cancer Institute, and Harvard Medical School, Boston, MA, USA

  16. Auditing Routing Entropy as an Uncertainty Signal in Attention-Residual Transformers

    Oct 1, 2026Wenhao Liang, Lin Yue, Wei Emma Zhang +3Transformer Residual StreamsModel Auditing

    Adelaide University, Adelaide, Australia

  17. Verify Claims, Not Scores: Evidence-Based Verification of Modular Agents

    Oct 1, 2026Ali Atiah AlzahraniAgentic EvaluationsModel Auditing

  18. When the Judge Acts: Auditing VLM-Guided Image Selection on Culturally Situated Prompts

    Oct 1, 2026Huichan SeoLarge Language Model JudgesJudges

    Independent Researcher

  19. Auditing Action Settlement in LLM Agent Environments: Order, Progress, and Replay

    Oct 1, 2026Haotian Chen, Bowen Ye, Yuning Zhang +1Large Language Model AgentsContracts

    School of Cyber Science and Technology, University of Science and Technology of China · School of Education, Shanghai Jiao Tong University · SWJTU-Leeds Joint School, Southwest Jiaotong University

  20. Beyond Final Accuracy: Auditing Communication in LLM Multi-Agent Systems

    Oct 1, 2026Shixuan Li, Wei Yang, Peiyu Zhang +3Multi-Agent CommunicationModel Auditing

    Ming Hsieh Department of Electrical and Computer Engineering University of Southern California, Los Angeles, CA 90089, USA · Thomas Lord Department of Computer Science University of Southern California, Los Angeles, CA 90089, USA

  21. Beyond Answer Confidence: A Controlled Audit of Self-Knowledge in a Black-Box Decision Model

    Oct 1, 2026Sharath M Shankaranarayana, Davor Runje, Jan JanninkModel AuditingSelf-Knowledge

  22. Tolerance-Based Fairness Auditing: Violation Certification and Sensitivity Screening

    Oct 1, 2026Jie Tang, Chuanlong Xie, Lixing ZhuFairness AuditsAlgorithmic Fairness

    School of Statistics, Beijing Normal University, Zhuhai, Guangdong 519087, China

  23. A Matched-Budget Audit Framework for Recaptioned Image-Text Supervision Distributions

    Oct 1, 2026Giyeong Oh, Junghun Park, Yuhan Bae +1Video CaptioningText-To-Image

    Seoul National University

  24. WorldAuditBench: Interactive 3D World Auditing with Multimodal Agents

    Sep 30, 2026Ziyan Jiang, Jingbo Yang, Jiabao Ji +53D WorldMultimodal Agents

    UC Santa Barbara · MIT CSAIL · MIT-IBM Watson AI Lab

  25. Cheap to Draw, Expensive to Trust: Certifying Test-Time Scaling Curves

    Sep 30, 2026Sohail, Sarkar, Shakuntala BaichooModel AuditingTest-Time Scaling

    Neel · PMCC AI Lab, Peter Munk Cardiac Centre, University Health Network, Toronto, Ontario, Canada

  26. Efficient Active Auditing of Multi-Group Fairness with Bias Probes

    Sep 30, 2026Ayoub Ajarra, Debabrota BasuFairness AuditsAlgorithmic Fairness

    ´Equipe Scool, Univ. Lille, Inria, CNRS, Centrale Lille, UMR 9189- CRIStAL

  27. Fyan: A Human--AI Harness with Semantic Auditing for Document-Level Formalization

    Sep 30, 2026Wei Zhao, Yangshuo Zou, Chengxiang Ding +5FormalizationProof

    School of Mathematical Sciences, Shanghai Jiao Tong University, Shanghai 200240, China · University of California, Berkeley, CA 94720, USA · Zhiyuan College, Shanghai Jiao Tong University, Shanghai 200240, China +4

  28. From Verification Failures to Reusable Guidance for Coding Agents

    Sep 30, 2026Yuqing Zhai, Xiaohong Chen, Lingming Zhang +2Coding AgentsAgentic Evaluations

    University of Illinois Urbana-Champaign

  29. Routing Probes Can Improve Without New Information: An Exact-Null Audit of Uncertainty Beyond Model Outputs

    Sep 30, 2026Wenhao Liang, Lin Yue, Wei Emma Zhang +3Detection PerformanceModel Checkpoints

  30. Whose Voice Survives the Summary? A Voice-Retention Audit of LLM Employee Listening

    Sep 30, 2026Thilo Tamme, Anton Hantel, Bijan Khosrawi-RadSummarizationModel Auditing

    Technical University of Munich · Massachusetts Institute of Technology · Leuphana University Lüneburg

  31. Where the Evidence Lives: Auditing AI Companions' Self-Descriptions

    Sep 30, 2026Seiya Ikeda, Shin-nosuke IshikawaModel AuditingStylistic Fidelity

    AI Consulting Division, Mamezo Co., Ltd. Tokyo, Japan · AI Technical Sector, Mamezo Co., Ltd. Tokyo, Japan · Graduate School of Artificial Intelligence and Science, Rikkyo University Tokyo, Japan

  32. Where Scientific Search Agents Fail: Decision-Checkpoint Auditing of Exposure and Inspection Attempts

    Sep 29, 2026Hongmin Li, Wanli ZhaoScientific AgentsSearch Algorithms

    School of Life Science and Technology, Institute of Science Tokyo Tokyo, Japan · Department of Computational Biology and Medical Sciences Graduate School of Frontier Sciences, The University of Tokyo Kashiwa, Japan · Department of Information Science Graduate School of Advanced Science and Engineering, Hiroshima University Higashihiroshima, Japan

  33. E2E-SWE: Benchmarking LLMs on Building Working Codebases from Scratch

    Sep 29, 2026Hantian Ding, Chloe Bi, Jiacheng Zhu +5CodebasesModel Auditing

    Meta Superintelligence Labs

  34. Retrieve, Reproduce, Reveal: Dissecting Retrieval-Augmented Software Vulnerability Detection

    Sep 29, 2026Sabrina Kaniewski, Tim Krämer, Julius Bächle +3Model VulnerabilitiesSoftware

    Institute for Secure Networked Systems, Esslingen University, Germany · Esslingen University, Germany · Institute for Intelligent Systems, Esslingen University, Germany +1

  35. When Does Randomized Oversight Align AI Agents That Can Conceal?

    Sep 29, 2026Joshua S. Gans, Richard HoldenModel AuditingSecurity Evaluation

    UNSW Business School

  36. Do Agent Benchmarks Do What They Say? An Executable-Contract Audit of Tool-Using Agent Environments

    Sep 29, 2026Rohith Reddy Bellibatlu, Zichong Wang, Wenbin ZhangAgentic BenchmarksModel Auditing

    Florida International University, Miami, FL, USA

  37. Selecting The Most Informative Tokens in Natural Language Autoencoders

    Sep 29, 2026Federico Torrielli, Gianluca Barmina, Andrea Blasi Núñez +4Explainable AI MethodsModel Activations

    Department of Computer Science, University of Turin, Italy · Department of Mathematics and Computer Science, University of Southern Denmark, Denmark

  38. REALHOP: Rethinking Multi-Hop Reasoning Evaluation via Behavioral Auditing

    Sep 29, 2026Jiawen Tao, Xiaokun Yuan, Yaoming Li +4Multi-Hop ReasoningReasoning Benchmark

    Hunyuan Team, Tencent · Peking University

  39. VStress: Correlation-Aware Auditing and Adaptive Budget Allocation for Repeated Verifiers

    Sep 29, 2026Miaobo Hu, Shuhao Hu, Xiaobo Guo +5Verification FrameworkStress Testing

    School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China · Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China

  40. Verifier Errors in RLVR: Reward Hacking, Limits of Feedback, and Selective Control

    Sep 28, 2026Christian Moya, Elliott Thornley, Guang LinReinforcement Learning With Verifiable RewardVerifiable Rewards

    Purdue University · National University of Singapore

  41. Audit the Scaffold, Not the Checkpoint: A Stationarity Dichotomy for Recursive Self-Improvement in Agentic Coding

    Sep 28, 2026Sebastian Bobadilla-Suarez, Bob Suh, Ryan FortinScaffoldsCoding Agents

    OnCorps

  42. DGF-Bench: A Benchmark for Simulating and Auditing Deception Against Multi-Agent Governance Boards

    Sep 28, 2026Jeremy CanaleGovernanceDeception

  43. PhysioTRACE: Provenance-Aware Stress Tests for Physiological Foundation Models

    Sep 28, 2026Ayana Mussabayeva, Anuar Aimoldin, Olivier Oullier +2Physiological DataElectroencephalography Foundation Models

    Mohamed bin Zayed University of Artificial Intelligence (MBZUAI), Abu Dhabi, UAE · McGill University, Montreal, Canada · Carnegie Mellon University, Pittsburgh, USA

  44. ReplayLens: Auditing Agents' Use of Outcomes

    Sep 28, 2026Dong Xu, Zhangfan Yang, Jiantao Wu +5ReplayInteraction History

    School of Artificial Intelligence, Shenzhen University · EasternDawn · School of Computer Science, University of Nottingham Ningbo

  45. Designing Reliable LLM-as-a-Judge Measurement Systems for Multi-Turn Business Agents

    Sep 27, 2026Kaiwen Luo, Ming GaoLlm-As-A-JudgeAgentic Evaluations

    Meta

  46. Auditing Agent Actions through Query-Conditioned Attribution

    Sep 27, 2026Yifan Liu, Praveen Venkateswaran, Abdulhamid Adebayo +1Model AuditingMean Average Precision

    University of Illinois Urbana-Champaign · IBM

  47. Audit-First VAPO: Risk-Certified Selective Updates under Imperfect Verification

    Sep 27, 2026Miaobo Hu, Shuhao Hu, Xiaobo Guo +5Finite-Sample CertificatesModel Auditing

    School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China · Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China

  48. The Selection Rule Decides the Winner: A Pre-Registered Audit of Open-Set Graph Anomaly Detection

    Sep 27, 2026Farhan Shahriyar Hossain, Taufikur Rahman Fuad, Md Abrar Jahin +1Generalist Graph Anomaly DetectionLogical Anomalies

    Islamic University of Technology · University of Southern California · Qatar Computing Research Institute (QCRI)

  49. How Reproducible Are Evaluation Conclusions? A Self-Audit of LLM-Inferred Prompt Structure

    Sep 24, 2026Dipankar SarkarLarge Language Model EvaluationReproducibility

    Skelf Research

  50. When Temporal Perturbations Act Like Sensor Biases: Label-Free Auditing of Wearable Activity Recognizers

    Sep 24, 2026Qingyu Wu, Yuan Wei, Renju Liu +1Human Activity RecognitionModel Auditing

    Defense Innovation Institute, Academy of Military Science, Beijing, China · School of Software Engineering, South China University of Technology, Guangzhou, China

  51. The Last Human Gate: Forward Deployed Engineering for Governance Automation

    Sep 24, 2026Jeremy CanaleGovernanceGating

  52. Claim-Gated Source-Risk Auditing for Generative Search

    Sep 24, 2026Kainan Zhou, Chuhong Xu, Gangzhen Qian +1CitationsModel Auditing

    Google LLC Mountain View, USA · Sony Corporate of America San Jose, USA · Intuit Inc Mountain View, USA

  53. Thinking Leakage: A Causal Audit of NoThink Post-Training in Hybrid Reasoning Models

    Sep 23, 2026Zehao Liu, Vasant G. HonavarLarge Reasoning ModelsPost-Training

    College of Information Sciences and Technology Pennsylvania State University

  54. Can LLMs Catch a Rigged Backtest? A Clean-Control Calibration Benchmark

    Sep 23, 2026Makar Ulesov, Vladislav Smirnov, Omar Ibrahim +1Model AuditingCode Quality

    Mohamed bin Zayed University of Artificial Intelligence (MBZUAI) · School of Computing and Information, University of Pittsburgh

  55. Auditability Is Not One Property: Rule Overlap, Behavioural Agreement, and Composition in Reinforcement Learning

    Sep 23, 2026Liu Hung MingModel AuditingBoltzmann Policies

    PARRAWA AI

  56. Compliant AI Infrastructure for Regulated Finance: A tiered multi-agent framework with DLT audit trails for financial operations in DACH

    Sep 23, 2026Walter Kurz, Reinhard MaggComplianceBanking

    Swissi Institute for AI

  57. When Entanglement Lower-Bounds Disparity: Auditing and Repairing Demographic Fairness in Audio Understanding Models

    Sep 23, 2026Kian Shamsaie, Iman ModarressiSpeakerDisparities

    People Make Things

  58. Beyond Mean Foils: Auditing Worst-Foil Specificity in Frozen CLIP Region Explanations

    Sep 23, 2026Kaixin Liu, Zhipeng Ye, Feng Jiang +2Semantic RegionFrozen Contrastive Language-Image Pre-Training Visual Encoder

    Taizhou Institute of Science and Technology, Nanjing University of Science and Technology, Taizhou 225300, Jiangsu, China

  59. Discover, Falsify, Revise: Auditing Input-Use Claims from Source Code to Predictive Contribution in Agent-Discovered Cell Models

    Sep 23, 2026Mengran Li, Bo Li, Chengyang Zhang +3Virtual CellModel Auditing

    Sun Yat-sen University · University of Macau · Sichuan University +3

  60. The Delegation Blind Spot: Auditing Product Decisions from Agent Choices

    Sep 22, 2026Shivam GuptaModel AuditingDecisions

    Independent Research