Conformity Mitigations in Large Language Models Lie on a Single Resistance-Receptivity Frontier
4.20T1 sourcearXiv cs.MA
Source record
Published by arXiv cs.MA (T1 source). The original is at https://arxiv.org/abs/2608.11247.
Pipeline notes
The summary and note below are generated by the signal pipeline — they are Beyond Desk’s reading, not quotations from the source.
SummaryStudy of 23 open-weight language models finds that a unanimous wrong majority can overturn 22.8% to 71.0% of correct answers depending on dataset. Existing conformity mitigations improve resistance but reduce receptivity, falling on a single tradeoff frontier; reasoning is the only method that improves both on certain tasks.
Why it mattersDefines a Resistance-Receptivity frontier for multi-agent LLM setups with measurements of six mitigation methods. Directly relevant to designing agent collaboration workflows.
Cited by
No citations on record.