LLM Sycophancy

LLM: Large Language Model

LLM sycophancy describes when a model agrees with or validates a user without adequate evidence, including cases where it changes a correct answer under pressure. Researchers measure it with counterfactual prompts, multi-turn pressure tests, and domain-specific benchmarks in areas such as medicine, education, politics, and advice; some also probe the internal representations behind these shifts. Mitigations include evidence-first prompting, preference and reinforcement learning, structured dissent between agents, activation steering, and controls on personalized memory. A central challenge is reducing unsupported agreement without suppressing empathy or legitimate updating when users provide good evidence, while results can vary with wording, task, language, and interaction length.

Latest papers

163 papers27 papers in the last four weeks, up 42% on the four weeks before. 0.2% of all new papers.

Good Arguments Against the People Pleasers: How Reasoning Mitigates (Yet Masks) LLM Sycophancy
Mar 17, 2026Zhaoxin Feng, Zheng Chen, Jianfei Ma +3Ownership Bias in Language Models LLM Sycophancy
The Hong Kong Polytechnic University · The Hong Kong University of Science and Technology
Clinician input steers AI toward accurate and harmful recommendations
Mar 14, 2026Ivan Lopez, Selin S. Everett, Bryan J. Bunning +10Medical LLMs Clinical Language Model Evaluation
Department of Biomedical Data Science, Stanford University, Stanford, CA, USA · Stanford University School of Medicine, Stanford, CA, USA · Quantitative Sciences Unit, Department of Medicine, Stanford University School of Medicine, Stanford, CA, USA +14
Do Large Language Models Get Caught in Hofstadter-Mobius Loops?
Mar 10, 2026Jaroslaw HryszkoLLM Safety Framing Effects in Language Models
Faculty of Mathematics and Computer Science, Jagiellonian University, Krak´ow, Poland
Learning When to Trust in Contextual Social Bandits
Mar 9, 2026Majid Ghasemi, Mark CrowleyLLM Sycophancy Corruption Robustness
Department of Electrical & Computer Engineering University of Waterloo, Canada
Writing literature reviews with AI: principles, hurdles and some lessons learned
Mar 8, 2026Saadi Lahlou, Annabelle Gouttebroze, Atrina Oraee +1LLM Sycophancy LLM Evaluation
London School of Economics and Political Science · Paris Institute for Advanced Study
The Company You Keep: How LLMs Respond to Dark Triad Traits
Mar 4, 2026Angelica Henestrosa, Zeyi Lu, Pavel Chizhov +1Language Model Safety Evaluation LLM Sycophancy
CAIRO, Technical University of Applied Sciences Würzburg-Schweinfurt
Generative AI for Managerial Decision-Making under Ambiguity and Sycophancy
Mar 4, 2026Sule Ozturk Birim, Fabrizio Marozzo, Yigit KazancogluAI-Assisted Decision Making Generative AI Evaluation
Manisa Celal Bayar University, Salihli, Manisa, Turkey · University of Calabria, Rende, Italy · Yasar University, Izmir, Turkey
Ask don't tell: Reducing sycophancy in large language models
Feb 27, 2026Magda Dubois, Cozmin Ududec, Christopher Summerfield +1LLM Sycophancy Framing Effects in Language Models
UK AI Security Institute, London, UK
Sycophantic Chatbots Cause Delusional Spiraling, Even in Ideal Bayesians
Feb 22, 2026Kartik Chandra, Max Kleiman-Weiner, Jonathan Ragan-Kelley +1Human-AI Interaction LLM Sycophancy
MIT CSAIL · University of Washington, Seattle · MIT Department of Brain & Cognitive Sciences
LLM Spirals of Delusion: A Benchmarking Audit Study of AI Chatbot Interfaces
Feb 20, 2026Peter Kirgis, Ben Hawriluk, Sherrie Feng +3Language Model Safety Evaluation LLM Safety Benchmarks
Princeton University · Phillips Exeter Academy · Independent
The Emergence of Lab-Driven Alignment Signatures: A Psychometric Framework for Auditing Latent Bias and Compounding Risk in Generative AI
Feb 19, 2026Dusan BosnjakovicLanguage Model Auditing Language Model Bias Evaluation
SycoEval-EM: Sycophancy Evaluation of Large Language Models in Simulated Clinical Encounters for Emergency Care
Jan 23, 2026Dongshen Peng, Yi Wang, Austin Schoeffler +5LLM Sycophancy Language Model Safety Evaluation
UNC Chapel Hill · University of Waterloo · Stanford University
Not Your Typical Sycophant: The Elusive Nature of Sycophancy in Large Language Models
Jan 21, 2026Shahar Ben-Natan, Oren TsurLLM Evaluation LLM Sycophancy
Computer and Information Science Ben Gurion University

Mar 17, 2026J/K move · Enter open · S save

Good Arguments Against the People Pleasers: How Reasoning Mitigates (Yet Masks) LLM Sycophancy

Zhaoxin Feng, Zheng Chen, Jianfei Ma, Yip Tin Po+2

The Hong Kong Polytechnic University · The Hong Kong University of Science and Technology

Ownership Bias in Language Models LLM Sycophancy Deception in Language Models CoT Reasoning

Open paper AskPDF arXiv

Alignment techniques often inadvertently induce sycophancy in LLMs. While prior studies studied this behaviour in direct-answer settings, the role of Chain-of-Thought (CoT) reasoning remains under-explored: does it serve as a logical constraint that mitigates sycophancy, or a tool for post-hoc rationalization that masks it? We evaluate a range of models across objective and subjective tasks to investigate the issue. Results show that reasoning generally reduces sycophancy in final decisions but also masks sycophancy in some samples, where models construct deceptive justifications through logical inconsistencies, calculation errors, and one-sided arguments etc. Furthermore, LLMs are more prone to sycophancy in subjective tasks and under authority-bias. Our mechanistic analysis on three open-source models reveals that the tendency of sycophancy is dynamic during the reasoning process rather than being pre-determined at the input stage.