# Most LLM Conformity Needs No Speaker: Measuring the Speaker-Free Floor in Peer-Pressure Benchmarks

arXiv: https://arxiv.org/abs/2607.05545 · HTML: https://mlsanity.com/paper/2607.05545/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 45 references that are in the map.
- First posted on arXiv 6 Jul 2026.

## Builds on (most cited first, 25 of 25)

- [Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge](https://mlsanity.com/paper/1803.05457/) (2018)
- [TruthfulQA: Measuring How Models Mimic Human Falsehoods](https://mlsanity.com/paper/2109.07958/) (2021)
- [MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmark](https://mlsanity.com/paper/2406.01574/) (2024)
- [Improving Factuality and Reasoning in Language Models through Multiagent Debate](https://mlsanity.com/paper/2305.14325/) (2023)
- [Language Models Don't Always Say What They Think: Unfaithful Explanations in Chain-of-Thought Prompting](https://mlsanity.com/paper/2305.04388/) (2023)
- [Encouraging Divergent Thinking in Large Language Models through Multi-Agent Debate](https://mlsanity.com/paper/2305.19118/) (2023)
- [Emergent social conventions and collective bias in LLM populations](https://mlsanity.com/paper/2410.08948/) (2024)
- [Are self-explanations from Large Language Models faithful?](https://mlsanity.com/paper/2401.07927/) (2024)
- [Are You Sure? Challenging LLMs Leads to Performance Drops in The FlipFlop Experiment](https://mlsanity.com/paper/2311.08596/) (2023)
- [Do as We Do, Not as You Think: the Conformity of Large Language Models](https://mlsanity.com/paper/2501.13381/) (2025)
- [Sycophancy Is Not One Thing: Causal Separation of Sycophantic Behaviors in LLMs](https://mlsanity.com/paper/2509.21305/) (2025)
- [TRUTH DECAY: Quantifying Multi-Turn Sycophancy in Language Models](https://mlsanity.com/paper/2503.11656/) (2025)
- [DarkBench: Benchmarking Dark Patterns in Large Language Models](https://mlsanity.com/paper/2503.10728/) (2025)
- [Interaction Context Often Increases Sycophancy in LLMs](https://mlsanity.com/paper/2509.12517/) (2025)
- [When LLMs Play the Telephone Game: Cultural Attractors as Conceptual Tools to Evaluate LLMs in Multi-turn Settings](https://mlsanity.com/paper/2407.04503/) (2024)
- [LLMs Can't Handle Peer Pressure: Crumbling under Multi-Agent Social Interactions](https://mlsanity.com/paper/2508.18321/) (2025)
- [When Your AI Agent Succumbs to Peer-Pressure: Studying Opinion-Change Dynamics of LLMs](https://mlsanity.com/paper/2510.19107/) (2025)
- [Whose Facts Win? LLM Source Preferences under Knowledge Conflicts](https://mlsanity.com/paper/2601.03746/) (2026)
- [Conformity Dynamics in LLM Multi-Agent Systems: The Roles of Topology and Self-Social Weighting](https://mlsanity.com/paper/2601.05606/) (2026)
- [Conformity Generates Collective Misalignment in AI Agents Societies](https://mlsanity.com/paper/2605.10721/) (2026)
- [Belief in Authority: Impact of Authority in Multi-Agent Evaluation Framework](https://mlsanity.com/paper/2601.04790/) (2026)
- [Old Habits Die Hard: How Conversational History Geometrically Traps LLMs](https://mlsanity.com/paper/2603.03308/) (2026)
- [Large Language Models Exhibit Normative Conformity](https://mlsanity.com/paper/2604.19301/) (2026)
- [Controllable Fake Document Infilling for Cyber Deception](https://mlsanity.com/paper/2210.09917/) (2022)
- [Who Do LLMs Trust? Human Experts Matter More Than Other LLMs](https://mlsanity.com/paper/2602.13568/) (2026)

## Built on by (most cited first, 5 of 5)

- [When Local Monitors Miss Compositional Harm: Diagnosing Distributed Backdoors in Multi-Agent Systems](https://mlsanity.com/paper/2607.11751/) (2026)
- [Silence Is Endorsement: Verification-Status Laundering in LLM Agent Pipelines](https://mlsanity.com/paper/2609.20211/) (2026)
- [Early Detection of Distributed Backdoors in Multi-Agent LLM Systems: A Characterization Study](https://mlsanity.com/paper/2607.24893/) (2026)
- [The Evaluator Is Part of the Experiment: Measuring Open-Ended LLM Conformity](https://mlsanity.com/paper/2608.04463/) (2026)
- [Silent Dissent: LLM Agents That Yield to the Majority Still Represent Their Original Premise](https://mlsanity.com/paper/2610.02702/) (2026)

## Abstract (arXiv)

LLM conformity is often used to describe cases where a model changes a correct answer toward a peer or group response. We show that most of this apparent conformity survives even after the peer is removed. The reason is a confound: standard conformity prompts mix two cues at once, the presence of a speaker and the repeated wrong answer itself. Existing benchmarks vary these cues together, so they cannot tell how much of the revision actually depends on the speaker. We introduce a no-source condition: the same asserted answer with the explicit speaker removed. Across six open-weight LLMs and seven QA and reasoning datasets, this condition alone causes harmful revision in 66.5% of initially correct cases, compared with 10.3% under a plain re-ask. The effect also remains when the repeated answer is paraphrased and when answer options are hidden in an open-ended setting. Source framing mainly modulates this floor: expert-panel framing raises it, while minimal person labels do not reliably raise it. When models flip, they are usually confidently wrong, and simple recalibration does not recover the original answer. Source attribution still matters, but it should be measured as an increment above this speaker-free floor. The methodological lesson is that conformity benchmarks should first measure what remains after the speaker is removed; without this step, benchmarks may mistake repeated text for social influence.