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

Teacher Knows It Best: Spontaneous Symmetry Breaking and Tipping Points in Networked Langevin Dynamics AI Sycophancy
Jul 27, 2026Sayantari Ghosh, Saumik Bhattacharya, Partha Pratim ChakrabartiLLM Sycophancy Langevin Dynamics
National Institute of Technology Durgapur, Durgapur, India · Indian Institute of Technology Kharagpur, Kharagpur, India
Tag Questions and the Generational Reversal of Sycophancy Across 45 Language Models
Jul 27, 2026Tapan ParikhLLM Evaluation LLM Sycophancy
Cornell Tech
Beyond Sycophancy: Structured Resistance and Compliance in LLM Moral Reasoning
Jul 23, 2026Baihui Wang, Bernard KochLLM Sycophancy Moral Reasoning in Language Models
University of Chicago · 2Yale School of Management
Gotta Catch them all: the modes of Sycophancy
Jul 22, 2026Shreyans Jain, Alexandra Yost, Amirali AbdullahLLM Sycophancy LLM Interpretability
Thoughtworks · Southern Utah University (SUU)
How Does Alignment Tuning Shape Representations of Sycophancy and Related Cue-Induced Biases in LLMs?
Jul 20, 2026Prakhar Gupta, Terry Jingchen Zhang, Florent Draye +2LLM Sycophancy LLM Alignment
University of Michigan · Jinesis Lab, University of Toronto & Vector Institute · Max-Planck Institute for Intelligent Systems, Tübingen, Germany +2
TD-DPO: Difference-Aware Preference Optimization for Mitigating Sycophancy in Clinical Autism Intervention Dialogue
Jul 17, 2026Shuzhong Lai, Junhong Lai, Chenxi Li +5LLM Sycophancy Direct Preference Optimization
1Nanhu Brain-Computer Interface Institute · 2MOE Frontiers Science Center for Brain and Brain-Machine Integration, Zhejiang University · College of Computer Science and Technology, Zhejiang University +3
The Severance Problem: LLMs are Unaware of the Person Beyond the Prompt
Jul 15, 2026Dor Litvak, Liu LeqiLLM Sycophancy LLM Hallucination Mitigation
The University of Texas at Austin
Agents Don't Just Agree, They Remember: Benchmarking Persistent Sycophancy in Self-Improving Personal Agents
Jul 12, 2026Xutao Mao, Liangjie Zhao, Leyao Wang +6LLM Sycophancy LLM Agent Memory
City University of Hong Kong · Adelaide University · Yale University +3
Mitigating LLM Sycophancy in Code Smell Detection Using Evidence-Guided Reasoning Prompts
Jul 11, 2026Istiaq Ahmed Fahad, Kamruzzaman Asif, Md. Nurul Ahad TawhidLLM Sycophancy Static Code Analysis
Institute of Information Technology · University of Dhaka · Dhaka, Bangladesh
Creativity, honesty and designed forgetting emerge in small hyperbolic language models
Jul 10, 2026Kwan Soo Shin, In Seok Kang, Yunkyung MinLLM Sycophancy Memory-Augmented Language Models
PolymathMinds Lab, Seoul, Republic of Korea. · Department of Chemical Engineering, POSTECH, Pohang, and aSSIST University, Seoul, Republic of Korea. · Korean Educational Development Institute, Jincheon, Republic of Korea.
Dissociating the Internal Representations of Sycophancy in LLMs
Jul 8, 2026Anthony Baez, Sheer Karny, Pat PataranutapornLLM Sycophancy LLM Interpretability
Media Lab, MIT, Massachusetts, USA.
Agentic Scaffolding Amplifies Sycophantic Behavior in Large Language Models
Jul 6, 2026Thantham JitthamLLM Sycophancy LLM Reliability
Cornell University
Robust for the Wrong Reasons: The Representational Geometry of LLM Robustness to Science Skepticism
Jul 2, 2026Minjong CheonLLM Sycophancy Language Model Robustness
Department of Computer Science and Engineering, Sejong University
MemSyco-Bench: Benchmarking Sycophancy in Agent Memory
Jul 1, 2026Zhishang Xiang, Zerui Chen, Yunbo Tang +5Agent Memory LLM Sycophancy
1Xiamen University · 2Jilin University
A Mechanistic View of Authority Hierarchy in LLM Sycophancy
Jul 1, 2026Emil Joswin, Srujananjali Medicherla, Priyanka Mary MammenLLM Sycophancy LLM Interpretability
Independent Research · University of Massachusetts Amherst
Detecting and Controlling Sycophancy with Cascading Linear Features
Jun 23, 2026Maty Bohacek, Rishub Jain, Nicholas Dufour +3LLM Sycophancy Language Model Steering
Stanford University · Google DeepMind
Warning labels shift perceptions of sycophantic AI, but not its influence
Jun 19, 2026Lujain Ibrahim, Myra Cheng, Cinoo Lee +4LLM Sycophancy AI Safety Evaluation
University of Oxford. · 2Stanford University. · 3Microsoft. +1
Escape from Delusional Echo Trap: Symmetry Breaking, Stochastic Dynamics and Mathematical Mitigation Strategies for Algorithmic Sycophancy
Jun 16, 2026Sayantari Ghosh, Saumik Bhattacharya, Partha Pratim ChakrabartiBelief Revision LLM Sycophancy
National Institute of Technology Durgapur, Durgapur, India · Indian Institute of Technology Kharagpur, Kharagpur, India
Sycophancy as Material Failure under Pushback Loading: A Multi-Axis Characterization Across Three Loading Cases and up to Seventeen Material Charges
Jun 15, 2026Ferdinand M. SchesslLLM Sycophancy
LLM-as-an-Investigator: Evidence-First Reasoning for Robust Interactive Problem Diagnosis
Jun 11, 2026Fabrizio Marozzo, Pietro LiòLLM Sycophancy LLM Agent Evaluation
University of Calabria, Italy · University of Cambridge, United Kingdom
Recalling Too Well: Sycophancy Evaluation and Mitigation in Memory-Augmented Models
Jun 9, 2026Shelly Bensal, Axel Magnuson, Aparna Balagopalan +1LLM Sycophancy Memory-Augmented Language Models
Writer, Inc.
BenSyc: Benchmarking Conversational Sycophancy and Human Alignment in LLMs for Bengali Contexts
Jun 8, 2026Kazi Noshin, Sajib Acharjee Dip, Ranat Das Prangon +4Multilingual Language Model Evaluation LLM Evaluation
University of Illinois Urbana-Champaign, USA · Virginia Tech, USA · Bangladesh University of Engineering and Technology, Bangladesh +2
Emergent Misalignment Can Be Induced by Sycophancy and Reversed via Alignment Gating
Jun 8, 2026Sicheng Wang, Xiangyang Zhu, Han Wang +6LLM Sycophancy LLM Alignment
Shanghai AI Lab, Shanghai, China.
Sycophancy Towards Researchers Drives Performative Misalignment
Jun 7, 2026David D. Baek, Xinnuo Li, Anay Gupta +4LLM Sycophancy LLM Alignment
Massachusetts Institute of Technology, Cambridge, MA, USA · University of Michigan, Ann Arbor, MI, USA · Georgia Institute of Technology, Atlanta, GA, USA +1
Testing the Black Box: Structural Barriers to Independent Evaluation of Consumer-Facing Health LLMs
Jun 7, 2026Rahul Gorijavolu, Kaushik Madapati, Pritika Vig +7LLM Evaluation LLM Sycophancy
MIT Critical Data, Massachusetts Institute of Technology, Cambridge, MA, USA · School of Medicine, Johns Hopkins University, Baltimore, MD, USA · Department of Biomedical Engineering, Johns Hopkins University, Baltimore, MD, USA +10
Sycophancy as a Multilingual Alignment Failure: How Safety Degrades Across Languages, Topics, and Models
Jun 7, 2026Arya Shah, Himanshu Beniwal, Mayank Singh +1Multilingual Language Models Multilingual Language Model Evaluation
IIT Gandhinagar · Asian Institute of Technology
"I understand your perspective": LLM Persuasion and Sycophancy through the Lens of Communicative Action Theory
Jun 6, 2026Esra Dönmez, Agnieszka FalenskaLLM Sycophancy Computational Argumentation
Institute for Natural Language Processing, University of Stuttgart · Interchange Forum for Reflecting on Intelligent Systems, University of Stuttgart
The AI Epistemic Deference Index: A Continuous Measure of Sycophancy
Jun 5, 2026Alejandro Botas, Paul de Font-Reaulx, Luke HewittLLM Evaluation LLM Sycophancy
Independent · University of Michigan, Ann Arbor · Transluce
Sycophantic Praise: Evaluating Excessive Praise in Language Models
Jun 5, 2026Daniel Vennemeyer, Phan Anh Duong, Meryl Ye +2LLM Evaluation LLM Sycophancy
University of Cincinnati · Carnegie Mellon University · Texas A&M University
Decomposing Factual Sycophancy in Language Models: How Size and Instruction Tuning Shape Robustness
Jun 4, 2026Victor De Marez, Luna De Bruyne, Walter DaelemansLLM Evaluation LLM Sycophancy
Centre for Computational Linguistics, Psycholinguistics and Sociolinguistics University of Antwerp Antwerp, Belgium

Jul 27, 2026, physics.soc-phJ/K move · Enter open · S save

Teacher Knows It Best: Spontaneous Symmetry Breaking and Tipping Points in Networked Langevin Dynamics AI Sycophancy

Sayantari Ghosh, Saumik Bhattacharya, Partha Pratim Chakrabarti

National Institute of Technology Durgapur, Durgapur, India · Indian Institute of Technology Kharagpur, Kharagpur, India

LLM Sycophancy Langevin Dynamics Phase Transitions Computational Social Science Causal Intervention

Open paper AskPDF arXiv

We formulate a statistical physics framework to model a networked stochastic dynamical system exhibiting bistability, driven by additive noise and social conformity. We apply this model to understand and mitigate AI-induced delusional spiraling-a phenomenon where algorithmic sycophancy from Large Language Models continuously reinforces inaccurate beliefs within a socially interacting society. By partitioning the network into a majority of regular agents and a minority of "aware" nodes (Teachers) placed at topological hubs, we use a degree-weighted mean-field approximation to reduce high-dimensional coupled Langevin equations into a single macroscopic drift equation. We provide a closed-form analytical derivation for the deterministic critical tipping time through a saddle-node bifurcation. We validate this analytical boundary using finite-size scaling and demonstrate a universal data collapse across diverse network topologies. Finally, we optimize an intervention strategy under a strict budget constraint that balances the topological footprint against driving velocity. We prove mathematically that under certain conditions, a highly concentrated, rapid intervention targeting massive hubs strictly outperforms a distributed, slow approach to rescue the network.

Momentum

Related topics

Latest papers 96