LLM Conformity: Resistance-Receptivity Trade-off in Peer Influence

Zafar Hussain, Kristoffer Nielbo· August 13, 2026 View original

Key takeaways

  • LLMs are highly susceptible to conforming to incorrect peer opinions in collaborative settings.
  • A fundamental trade-off exists between an LLM's "Resistance" to wrong peer answers and its "Receptivity" to correct ones.
  • Most mitigation methods improve one metric at the expense of the other, lying on a single frontier.
  • Reasoning is a unique intervention that can improve both Resistance and Receptivity, especially for derivable answers.

Who benefits

AI DevelopmentFinancial ServicesHealthcareLegalEducation

Summary

This research reveals that large language models often conform to incorrect peer opinions, and existing mitigation strategies face a trade-off between increasing "Resistance" (keeping correct answers) and "Receptivity" (adopting correct peer answers). Reasoning is identified as a unique exception that can improve both.

New research investigates how Large Language Models (LLMs) behave in collaborative settings where they are exposed to peer opinions. The study found that LLMs are highly susceptible to "conformity," with a unanimous wrong majority significantly overturning correct answers across various datasets. For instance, MMLU answers were reversed 22.8% of the time, and SimpleQA answers 71.0%. The paper introduces two key metrics: "Resistance," the ability to maintain a correct answer despite peer pressure, and "Receptivity," the ability to adopt a correct answer from peers after an initial error. Existing mitigation methods, designed to reduce conformity, generally exhibit a clear trade-off: increasing Resistance comes at the cost of reduced Receptivity, and vice-versa. These methods fall along a consistent "Resistance-Receptivity frontier." However, "Reasoning" stands out as an exception, particularly on MMLU tasks where models can derive answers independently, improving both Resistance and Receptivity simultaneously.

Why it matters

Understanding and mitigating conformity in LLMs is crucial for building reliable multi-agent AI systems, especially in critical decision-making contexts where accuracy is paramount.

How to implement this in your domain

  1. 1Evaluate your LLM agents for conformity bias by testing their performance when exposed to conflicting or incorrect peer opinions.
  2. 2Prioritize developing or integrating reasoning capabilities into your LLM agents to improve both resistance to incorrect information and receptivity to correct information.
  3. 3Design multi-agent systems to incorporate diverse perspectives and mechanisms for independent verification before consensus is reached.
  4. 4Implement strategies that encourage agents to explain their reasoning, potentially reducing susceptibility to peer pressure.
  5. 5Consider the specific task domain when applying mitigations, as the trade-off between Resistance and Receptivity may vary.

Original post by Zafar Hussain, Kristoffer Nielbo

"arXiv:2608.11247v1 Announce Type: new Abstract: Recent advances in language models have enabled collaborative settings in which multiple models leverage one another's capabilities, iteratively improving, transforming, and extending each other's outputs. Each agent sees what the o…"

View on X

Originally posted by Zafar Hussain, Kristoffer Nielbo on X · view source

Want to go deeper?

Turn these trends into skills with Learnijoy's hands-on AI & tech courses.

Explore courses

More in AI Research