Protocol-dependent conformity in open-weight large language models under fixed wrong-peer signals
AI Agent · 2026
DOI: 10.20517/aiagent.2026.19 ↗Kurz gefasst
Studienprotokoll in der Zeitschrift AI Agent, 2026. Verfasst von Ling Xu und 4 weiteren Autor:innen. Die Arbeit nennt 24 Literaturangaben.
Abstract (Originalsprache)
Large language models (LLMs) may revise decisions after observing peer answers or conversational history. We study wrong-peer conformity - the conditional switch from a private answer to a preselected incorrect option supported by controlled peer-style signals - under a fixed-signal design. On 500-item CommonsenseQA (CSQA) and Massive Multitask Language Understanding (MMLU) samples, Qwen2.5-3B-Instruct, Phi-3.5-mini-instruct, and Gemma2-2B-it receive identical wrong targets and answer-only signals while presentation schedule, response schedule, retained history, or source-label wording varies. Sequential-Stepwise sharply reduces wrong-target adoption relative to Sequential-Final for Qwen and Phi but increases it for Gemma on both datasets. A seven-condition ablation shows that extra calls without retained outputs do not explain the Qwen difference; for Qwen2.5-3B, the same broad retained-history pattern appears on both CommonsenseQA and MMLU, where token-matched neutral assistant history reproduces much of the reduction and a short acknowledgment does not. Gemma does not show the same large reduction. In a separate token-matched control, replacing “Source” with “Model” suppresses wrong-target adoption for Qwen and Gemma on both benchmarks. Exploratory Qwen2.5 extensions further reveal sensitivity to checkpoint choice, peer count, and generic-justification message format. Paired inference, 30 aligned subset draws, and pre-exposure target-plausibility stratification support the directional protocol result. Thus, interaction protocol and contextual wording alter the effective conversational input, with effects that remain model- and setting-dependent.
Zitieren
APA
Xu, L., Xue, X., Zhu, Y., Zhang, J., & Xu, D. (2026). Protocol-dependent conformity in open-weight large language models under fixed wrong-peer signals. AI Agent. https://doi.org/10.20517/aiagent.2026.19
Vancouver
Xu L, Xue X, Zhu Y, Zhang J, Xu D. Protocol-dependent conformity in open-weight large language models under fixed wrong-peer signals. AI Agent. 2026. doi:10.20517/aiagent.2026.19
BibTeX
@article{Xu2026,
author = {Xu, Ling and Xue, Xucheng and Zhu, Ye and Zhang, Junwen and Xu, Dechang},
title = {Protocol-dependent conformity in open-weight large language models under fixed wrong-peer signals},
journal = {AI Agent},
year = {2026},
doi = {10.20517/aiagent.2026.19}
}
EUVIMED