LLMs Trust Their Own: Identity-Dependent Conformity in Multi-Agent Systems
cs.CL, cs.MA
Submitted: 2026-09-27
Updated: 2026-09-27
Terminology
Sources
- Sycophancy Mitigation Through Reinforcement Learning with Uncertainty-Aware Adaptive Reasoning Trajectories
- Conformity and Social Impact on AI Agents
- Large Language Models Exhibit Normative Conformity
- Reasoning Models Don't Always Say What They Think
- Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge
- I Am Not Them: Fluid Identities and Persistent Out-group Bias in Large Language Models
- From Simulation to Enaction: Post-trained language models recognize and react to their own generations
- Language model agents show in-group trust bias invisible to standard behavioural audits
- Truth or Tribe: How In-group Favoritism Prioritize Facts in Persona Agents
- Aligned Alone, Misaligned Together: Forecasting Adversarial Capture in LLM Agent Populations
- Easier to Mislead Than to Correct: Harmful and Beneficial Revision in LLM Conformity
- LLMs Can't Handle Peer Pressure: Crumbling under Multi-Agent Social Interactions
- When Agents See Humans as the Outgroup: Belief-Dependent Bias in LLM-Powered Agents
- Disentangling the Drivers of LLM Social Conformity: An Uncertainty-Moderated Dual-Process Mechanism
Related papers
- Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
- Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
- Subliminal Steering: Stronger Encoding of Hidden Signals
- MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
- The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
- Untangling the Mechanisms of Misleading Context in Medical Question Answering