LLM Honesty

LLM: Large Language Model

The field asks whether a model communicates its knowledge and uncertainty faithfully, not merely whether its answers happen to be correct. Researchers test this with controlled tasks and benchmarks for abstention, confidence calibration, sycophancy, strategic lying, omissions, and compliance under incentives. Interventions include honesty-focused fine-tuning or reinforcement learning, prompting and retrieval-based uncertainty cues, activation steering, and weight editing; interpretability probes seek signals of knowledge or deceptive intent. A central challenge is separating deception from ignorance or evaluation artifacts while ensuring methods generalize across domains and incentives without sacrificing useful capabilities or teaching models to hide their behavior.

Latest papers

36 papers3 papers in the last four weeks, level with the four weeks before. 0.0% of all new papers.

CAT-alyzing Honesty: Continuous Adversarial Training for Transferable LLM Honesty
Oct 15, 2026Yuan-Chen Chang, Niklas Herbster, Gauthier Gidel +1LLM Honesty LLM Alignment
Tara Research · Mila – Quebec AI Institute · Technical University of Munich
Resisting Harmful Instructions through Training-Free Weight Editing
Oct 15, 2026Ali Ebrahimpour-Boroojeny, Xiaocong Yang, Samuel Schapiro +4LLM Safety LLM Safety Alignment
Language Models Are "Insecure" Reporters
Sep 28, 2026Jenny Y. Huang, Jiameng Fan, Ahmed Imtiaz Humayun +5Language Model Safety Evaluation Deception in Language Models
Massachusetts Institute of Technology · Google Research · Harvard University
When Honesty is Not Enough in AI Debate
Sep 24, 2026Rayne Holland, Liming Zhu, Jason XueScalable Oversight Multi-Agent Debate
CSIRO
Judging by the Cover: Cleaning LLM Truthfulness Benchmarks to Avoid Surface-Level Feature Leakage
Sep 11, 2026Foad Namjoo, Remy Ogasawara, Amirali Abdullah +3Data Leakage LLM Evaluation
University of Utah · Thoughtworks · University of Massachusetts Amherst +1
Do Large Language Models Know What They Don't Know II? A Fully Behavioral, Non-Cognitive Measure of Epistemic Honesty
Sep 7, 2026Ali Şenol, H. Russell Bernard, Huan LiuLLM Evaluation LLM Honesty
Department of Computer Engineering, Tarsus University, Tarsus 33400, Mersin, Türkiye · School of Computing and Augmented Intelligence (SCAI), Arizona State University (ASU), Tempe, AZ 85281, USA · Institute for Social Science Research and School of Human Evolution and Social Change, Arizona State University (ASU), Tempe, AZ 85287, USA
Knowledge-Verified Emergent Deception in LLM Agents Under Conflicting Incentives
Aug 26, 2026Zheyuan Liu, Weiliang Zhao, Xiangchi Yuan +3Deception in Language Models LLM Honesty
University of Notre Dame · Columbia University · Georgia Institute of Technology +1
From Interpretability to Control: Insights from Six Years of the TrustNLP Workshop
Aug 11, 2026Rahul Gupta, Abhinav Mohanty, Anaelia Ovalle +10LLM Interpretability LLM Safety Alignment
Amazon AGI · Meta · Autodesk +3
Paying for Honesty Without Knowing the Truth: Reputation-Penalty Design for LLM Marketplace Agents
Jul 30, 2026Mingdai Yang, Shicheng Fan, Kejing Yu +5Agent Reliability Deception in Language Models
Univ. of Illinois Chicago Chicago, IL, USA · Springbrand Inc. Hangzhou, China · Beijing University of Posts and Telecommunications Beijing, China +2
Instrument Effects in Language-Model Honesty Evaluation: An Auditable Single-System Demonstration
Jul 15, 2026Justin BronderLLM Evaluation LLM Honesty
Corabo Inc.
When Is Delegated Play Truthful? Within-Range Regret and the Trilemma of Aligned Delegation
Jul 15, 2026Taksch DubeMechanism Design LLM Alignment
Kent State University, Kent, OH, USA
Safety from Honesty in a Disinterested AI Predictor
Jun 28, 2026Yoshua Bengio, Oliver Richardson, Tomáš Gavenčiak +13AI Alignment AI Safety
LawZero · Universit´e de Montr´eal · Mila +6
Odyssey: Constructing Verifiable Local Truth-Preserving Foundation Models
Jun 25, 2026Sridhar MahadevanLLM Grounding Formal Verification
Adobe Research · University of Massachusetts, Amherst
The Impossibility of Eliciting Latent Knowledge
Jun 10, 2026Korbinian Friedl, Francis Rhys Ward, Paul Yushin Rapoport +2AI Agent Safety LLM Honesty
The London School of Economics and Political Science · Independent
Janus: A Benchmark for Goal-Conditioned Information Distortion in LLMs
Jun 9, 2026Polydoros Giannouris, Mohsinul Kabir, Sophia AnaniadouLLM Evaluation Deception in Language Models
Department of Computer Science, National Center for Text Mining, The University of Manchester
Truthful AI Advisors: A Pre-Specified Benchmark for Large Language Model Honesty Under Preference Misalignment
May 31, 2026Hamidreza Hasani Balyani, Seyed Pouyan Mousavi Davoudi, Alireza Amiri-Margavi +2LLM Evaluation LLM Alignment
Amazon Lab126, HW Tech Org. Sunnyvale, CA, USA · Independent Researcher in AI and Statistics Tehran, Iran · Computational Modeling and Simulation University of Pittsburgh Pittsburgh, PA, USA +1
Used Car Salesbots? Honesty and Credulity of LLMs as Bargaining Agents under Partial Information
May 29, 2026Antonio Valerio Miceli-Barone, Vaishak Belle, Shay B. CohenMulti-Agent LLM Systems Multi-Agent Negotiation
University of Edinburgh
It's Not Always Sycophancy: Measuring LLM Conformity as a Function of Epistemic Uncertainty
May 26, 2026Kevin H. Guo, Chao Yan, Avinash Baidya +5LLM Evaluation LLM Sycophancy
1Vanderbilt University · 2Vanderbilt University Medical Center · 3Intuit AI Research
Confidently Deceptive: On the Relationship Between Confidence and Deception in LLMs
May 12, 2026Ali Asad, Stephen Obadinma, Anshul Pattoo +2Language Model Safety Evaluation Confidence Estimation in Language Models
Department of Electrical and Computer Engineering & Ingenuity Labs Research Institute Queen’s University, Kingston, Canada
SciIntegrity-Bench: A Benchmark for Evaluating Academic Integrity in AI Scientist Systems
May 11, 2026Zonglin Yang, Xingtong Liu, Xinyan XuAI Agents for Scientific Discovery AI Agent Evaluation
Readraft Lab · Peking University · Tongji University +1
Unlearners Can Lie: Evaluating and Improving Honesty in LLM Unlearning
May 9, 2026Renjie Gu, Jiazhen Du, Yihua Zhang +1LLM Unlearning LLM Honesty
Fudan University · Central South University · Michigan State University
The Moltbook Files: A Harmless Slopocalypse or Humanity's Last Experiment
May 8, 2026William Brach, Federico Torrielli, Stine Lyngsø Beltoft +3Privacy Leakage in Language Models Multi-Agent Systems
University of Turin Dept. of Computer Science Torino, Italy · University of Southern Denmark Odense, Denmark
AstroAlertBench: Evaluating the Accuracy, Reasoning, and Honesty of Multimodal LLMs in Astronomical Classification
May 7, 2026Claire Chen, Jiabao Sean Xiao, Shuze Daniel Liu +7Multimodal Reasoning Multimodal Model Evaluation
1California Institute of Technology · 2Massachusetts Institute of Technology · 3Purdue University
The Compliance Gap: Why AI Systems Promise to Follow Process Instructions but Don't
May 3, 2026Kwan Soo ShinAI Agent Benchmarks LLM Honesty
PolymathMinds AI Lab
"I Don't Know" -- Towards Appropriate Trust with Certainty-Aware Retrieval Augmented Generation
May 1, 2026Daan Di Scala, Maaike de Boer, Pınar YolumRetrieval-Augmented Generation LLM Reliability
TNO Netherlands Organisation for Applied Scientific Research, Department Data Science · Utrecht University, Department of Information and Computing Sciences
The Granularity Gap: A Multi-Dimensional Longitudinal Audit of Sycophancy in Gemini Models
Apr 19, 2026Patrick KeoughLLM Sycophancy LLM Alignment
Independent Researcher Bremerton, WA, USA
Activation Steering for Aligned Open-ended Generation without Sacrificing Coherence
Apr 9, 2026Niklas Herbster, Martin Zborowski, Alberto Tosato +2LLM Safety Alignment Language Model Robustness
Tara Research · Technical University of Munich · Mila Quebec AI Institute
Entropy and Attention Dynamics in Small Language Models: A Trace-Level Structural Analysis on the TruthfulQA Benchmark
Apr 4, 2026Adeyemi Adeseye, Aisvarya Adeseye, Hannu Tenhunen +1Small Language Models LLM Honesty
Brilloconnetz Partners avoin yhtiö, Turku, Finland · University of Turku, Turku, Finland · Royal Institute of Technology, Stockholm, Sweden
Truth as a Compression Artifact in Language Model Training
Mar 12, 2026Konstantin KrestnikovKnowledge Conflicts in Language Models LLM Honesty
Think Before You Lie: How Reasoning Leads to Honesty
Mar 10, 2026Ann Yuan, Asma Ghandeharioun, Carter Blum +6Deception in Language Models LLM Honesty
Google DeepMind · Carnegie Mellon University · Harvard University

Oct 15, 2026J/K move · Enter open · S save

CAT-alyzing Honesty: Continuous Adversarial Training for Transferable LLM Honesty

Yuan-Chen Chang, Niklas Herbster, Gauthier Gidel, Tommaso Tosato

Tara Research · Mila – Quebec AI Institute · Technical University of Munich

LLM Honesty LLM Alignment Adversarial Training Language Model Robustness

Open paper AskPDF arXiv

Large language models (LLMs) are becoming prevalent in scenarios where honesty is critical. However, despite alignment training, these models still exhibit dishonest behaviour, such as outputting claims that contradict some knowledge or are not supported by what is accessible in context. We introduce Continuous Adversarial Training for Consistent Honesty (CATCH), inspired by a method originally developed to robustly refuse harmful queries. CATCH trains the model towards an honest answer and away from a dishonest one while maintaining the model's capabilities. We evaluate two architectures (Llama-3.3-70B-Instruct and Qwen3-3.6-27B). We show that trained with only hundreds of targets built from self-reporting scenarios, CATCH learns an honest behaviour that robustly generalizes and transfers across distinct benchmarks. It consistently reduces dishonesty under pressure on MASK, increases confessions in the multi-agent game of Among Us, and improves the discovery rates of the model's hidden behaviours in AuditBench. We show that CATCH outperforms prompting and supervised fine-tuning in improving honesty, and it is on par with state-of-the-art honesty activation steering. However, CATCH surpasses honesty steering in maintaining utility, thanks to a novel choice of utility data.