LLM Sycophancy

LLM: Large Language Model

Follow this topic Ask about this topic

Momentum

13 papers in the last four weeks, up 160% on the four weeks before. 0.1% of all new papers.

Jul 13Week of Sep 28

Latest papers 96

All topics

BeliefScope: Diagnosing Evidence-Driven Revision and Pressure-Induced Shifts in Large Language Models
Oct 8, 2026Shuai Guo, Yidong CuiBelief Updating in LLMs LLM Auditing
Beijing University of Posts and Telecommunications Beijing, China
Anatomy of LLM Sycophancy: What a Flip Rate Hides
Oct 5, 2026Haonan HuangLLM Evaluation LLM Sycophancy
Princeton University
Memadapter: Counterfactual Adaptation Against Memory-induced Sycophancy
Oct 4, 2026Ruqing Ning, Haibo Meng, Zhishang Xiang +4LLM Sycophancy LLM Agent Memory
Jilin University · Xiamen University
Mitigating Social Sycophancy via Pluralistic Preference Optimization
Oct 1, 2026Stephane Hatgis-Kessell, Myra Cheng, Xiaoxuan Hou +4LLM Sycophancy Preference Optimization
Department of Computer Science, Stanford University · Amazon · Department of Computer Science, University of Washington
FIGS: Evaluating Multi-Turn Sycophancy Without Penalizing Empathy
Sep 30, 2026Sidharth Pulipaka, Ruta Binkyte, Ivaxi Sheth +1LLM Sycophancy Multi-Turn Dialogue Evaluation
Independent · German Research Center for Artificial Intelligence (DFKI) · ELLIS Institute Tübingen +2
Authority Bias in Language Models: Source Deference and User Agreement Are Not Interchangeable
Sep 29, 2026Abhinav Rajeev Kumar, Paras ChopraLLM Sycophancy LLM Reliability
Lossfunk
Less Sycophancy, Stronger Refusal? Lessons for AI Safety from Mechanistic Interpretability
Sep 28, 2026Xu Wang, Difan Zou, Xuansheng WuLLM Sycophancy Language Model Safety Evaluation
The University of Hong Kong · Shenzhen Loop Area Institute · Shanghai Artificial Intelligence Laboratory
Reset Is Not Recovery: Evaluating Recoverability from False Conversational Context via Sycophancy Hysteresis
Sep 27, 2026Adi ShnaidmanLLM Sycophancy Knowledge Conflicts in Language Models
University of Pennsylvania · Work conducted while affiliated with DeepKeep.
Low-Cost Assays for Measuring Model Behavior Across Vendors and Releases
Sep 24, 2026Tapan ParikhLLM Sycophancy AI Agent Evaluation
Cornell Tech
Receptiveness, Not Sycophancy: Distinguishing Engagement from Deference in Language Models
Sep 22, 2026Calvin Isley, Johann Gaebler, Max Lamparth +2LLM Sycophancy
Harvard Kennedy School, Harvard University, Cambridge, MA 02138, USA · Department of Statistics, Harvard University, Cambridge, MA 02138, USA · Computer Science, Stanford University, Stanford, CA 94305, USA
Recovering Agentic Sovereignty: Mitigating the Consensus Paradox via Contrastive Epistemic Decoding
Sep 22, 2026Dahlia Shehata, Ming LiLLM Sycophancy Adversarial Attacks on LLMs
University of Waterloo Canada
XYEval: Agents say yes to bad advice
Sep 20, 2026Zhengxuan Wu, Yuxuan Li, Oyvind Tafjord +1LLM Sycophancy AI Agent Evaluation
Google DeepMind
AfriSyCo: Measuring Assertive Framing, Verification, and Wording Sensitivity Around African-Language Content
Sep 15, 2026David Ababio Awuni, Rose-Mary Owusuaa Mensah Gyening, Elvis Gyasi OwusuMultilingual Language Model Evaluation Prompt Sensitivity
Measuring LLM Sycophancy under Sustained Multi-Turn Pressure
Sep 8, 2026Leyuan Tang, Kangda Wei, Tianyu Jiang +1LLM Safety Benchmarks LLM Evaluation
Department of Computer Science and Engineering, Texas A&M University · Department of Computer Science, University of Cincinnati
How AI Models Manage Epistemic Authority: A Taxonomy and Comparative Analysis of Responses to User Disagreement
Sep 7, 2026Riyadh Alnasser, Yusuf Mücahit Çetinkaya, Sumin Zhao +1LLM Evaluation LLM Sycophancy
University of Edinburgh · Middle East Technical University
AI Should Not Only Be Helpful. It Should Be Contingent. Artificial Intimacy, Sycophancy, and the Future of Social Learning
Aug 31, 2026Scott Compton, Arjun NagendranLLM Sycophancy Human-AI Interaction
Sycophantic Agreement Transfers with Neutral Data via Contrastive Preference Optimization
Aug 31, 2026Camila Blank, Zhuofan Ying, Christopher Potts +2LLM Sycophancy Emergent Misalignment in Language Models
1Stanford University · 2Columbia University
WildSEEK: Evaluating Language Models for Information-Seeking
Aug 31, 2026Tanise Ceron, Joachim Baumann, Elisa Bassignana +3LLM Safety Benchmarks LLM Sycophancy
1Bocconi University · 2Stanford University · 3IT University of Copenhagen +1
Group Alignment-Induced Sycophancy: A Two-Sided Evaluation of Steerable Pluralistic Alignment
Aug 12, 2026Haokai Zhao, Yunze Xiao, Weihao Xuan +3LLM Sycophancy LLM Alignment
University of New South Wales · Carnegie Mellon University · University of Tokyo
FaithformBench: Benchmarking Faithfulness of Mathematical Chain-of-Thought Autoformalisation
Aug 11, 2026Rob Cornish, Iacopo Ghinassi, Po-Hung Yeh +7CoT Faithfulness LLM Sycophancy
Nanyang Technological University, Singapore · University of Oxford, United Kingdom · The University of Edinburgh, United Kingdom
Mitigating Over-Personalization in LLMs via Structured Memory
Aug 8, 2026Hakeem Hannoon, Andrew Zhao, Mihir Narayan +2LLM Sycophancy Persistent Memory for Language Models
University of Saskatchewan · University of California–Irvine · University of Wisconsin–Madison +2
Confirming Our Biases? Evaluating the Capabilities, Risks, and Societal Impact of Large Language Models
Aug 7, 2026Mudar Adas, Polina Tsvilodub, Michael Franke +1Prompt Sensitivity LLM Sycophancy
Neuro-Cognitive Modeling Group, University of Tübingen, Sand 14, 72076 Tübingen, Germany · Department of Linguistics, University of Tübingen, Keplerstraße 2, 72074 Tübingen
Poli-Bias: Understanding and Measuring Large Language Model Biases in International Political Conflicts
Aug 6, 2026Massi-Nissa Abboud, Aladin Djuhera, Elena Cabrio +1LLM Sycophancy LLM Auditing
Université Côte d’Azur · Technical University Munich
Measuring and Detecting Harmful AI Sycophancy
Aug 6, 2026Bohan Jiang, Dawei Li, Yasin Silva +1LLM Sycophancy Language Model Safety Evaluation
1Arizona State University · 2Loyola University Chicago
Language Models Encode the Contextual Truth of Propositions
Aug 4, 2026Rupak Sarkar, Pritika Ramu, Rachel RudingerLLM Sycophancy Knowledge Conflicts in Language Models
University of Maryland, College Park
MedPRESS: A Multi-turn Benchmark for Patient-Pressure-Induced Medical Sycophancy in LLMs
Aug 3, 2026Saman Sarker Joy, Niloy FarhanLLM Safety Benchmarks LLM Sycophancy
Universiti Malaya, Malaysia · BRAC University, Bangladesh
Why LLMs Give In: Conversational Factors and Reasoning Behind Medical Sycophancy
Aug 2, 2026Kaike Ping, Buse Çarık, Caleb Wohn +3LLM Sycophancy Language Modeling
Virginia Tech · Shanghai Tongren Hospital, Shanghai Jiao Tong University School of Medicine · Emory University
Token-Level Diagnosis of Sycophancy in LLMs with Attribution-Guided Steering
Jul 31, 2026Hieu Nguyen, Mahammed Kamruzzaman, Anshuman Chhabra +1LLM Sycophancy LLM Interpretability
Bellini College of AI, Cybersecurity and Computing University of South Florida
Talked Out of the Truth: Sycophancy in the Reasoning Chains of Multimodal Models
Jul 30, 2026Mahir Numayeer Islam, Gakuto Okuyama, Nikolaus Siauw +3LLM Sycophancy Multimodal CoT Reasoning
Adelaide University · Akita International University · RNA Tech +2
Individual-level interventions against sycophantic AI reduce its appeal but not its persuasiveness
Jul 28, 2026Meryl Ye, Robert Kraut, Steve RathjeLLM Sycophancy Human-AI Interaction
1Carnegie Mellon University. · 2New York University.

Oct 8, 2026, cs.CLJ/K move · Enter open · S save

BeliefScope: Diagnosing Evidence-Driven Revision and Pressure-Induced Shifts in Large Language Models

Shuai Guo, Yidong Cui

Beijing University of Posts and Telecommunications Beijing, China

Belief Updating in LLMs LLM Auditing Causal Interventions in Language Models LLM Sycophancy

Open paper AskPDF arXiv

A language model may revise the same proposition after receiving genuinely relevant evidence or after receiving directional user pressure that adds no relevant fact. The observable response shift alone therefore does not reveal which source drove the change. We introduce BeliefScope, a controlled black-box framework for separating these two sources of influence around a fixed target proposition. BeliefScope crosses Evidence and Pressure with factor-specific local controls and measures response changes through probability reports, categorical judgments, and action recommendations on channel-appropriate scales. To determine when these observable contrasts support reliable attribution, we evaluate the observation design under controlled synthetic conditions. Known-truth recovery and targeted ablations establish where Evidence- and Pressure-related effects can be separated, while semi-synthetic stress tests map how that recoverability changes as the observation process becomes noisier and more heterogeneous. Across a 36-family Qwen/Llama study, with targeted 12-family checks that also include Gemma3-12B, the resulting profiles show substantial evaluation-context dependence: broad model-level differences can change under matched controls, decoding, or response interfaces, while some narrower within-model patterns remain stable. Instruction interventions further show that reduced target-aligned Pressure following can reflect either stable resistance or movement in the opposite direction. BeliefScope summarizes these measurements as a conditional belief-response profile that keeps diagnostic effects tied to the evaluation conditions under which they are observed, together with explicit validity boundaries for that diagnosis.

Momentum

Related topics

Latest papers 96