Silence is Not Consensus: Disrupting Agreement Bias in Multi-Agent LLMs via Catfish Agent for Clinical Decision Making
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866908381648781312 |
|---|---|
| author | Wang, Yihan Yan, Qiao Xing, Zhenghao Liu, Lihao He, Junjun Fu, Chi-Wing Hu, Xiaowei Heng, Pheng-Ann |
| author_facet | Wang, Yihan Yan, Qiao Xing, Zhenghao Liu, Lihao He, Junjun Fu, Chi-Wing Hu, Xiaowei Heng, Pheng-Ann |
| contents | Large language models (LLMs) have demonstrated strong potential in clinical question answering, with recent multi-agent frameworks further improving diagnostic accuracy via collaborative reasoning. However, we identify a recurring issue of Silent Agreement, where agents prematurely converge on diagnoses without sufficient critical analysis, particularly in complex or ambiguous cases. We present a new concept called Catfish Agent, a role-specialized LLM designed to inject structured dissent and counter silent agreement. Inspired by the ``catfish effect'' in organizational psychology, the Catfish Agent is designed to challenge emerging consensus to stimulate deeper reasoning. We formulate two mechanisms to encourage effective and context-aware interventions: (i) a complexity-aware intervention that modulates agent engagement based on case difficulty, and (ii) a tone-calibrated intervention articulated to balance critique and collaboration. Evaluations on nine medical Q&A and three medical VQA benchmarks show that our approach consistently outperforms both single- and multi-agent LLMs frameworks, including leading commercial models such as GPT-4o and DeepSeek-R1. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_21503 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Silence is Not Consensus: Disrupting Agreement Bias in Multi-Agent LLMs via Catfish Agent for Clinical Decision Making Wang, Yihan Yan, Qiao Xing, Zhenghao Liu, Lihao He, Junjun Fu, Chi-Wing Hu, Xiaowei Heng, Pheng-Ann Computation and Language Artificial Intelligence Machine Learning Other Quantitative Biology Large language models (LLMs) have demonstrated strong potential in clinical question answering, with recent multi-agent frameworks further improving diagnostic accuracy via collaborative reasoning. However, we identify a recurring issue of Silent Agreement, where agents prematurely converge on diagnoses without sufficient critical analysis, particularly in complex or ambiguous cases. We present a new concept called Catfish Agent, a role-specialized LLM designed to inject structured dissent and counter silent agreement. Inspired by the ``catfish effect'' in organizational psychology, the Catfish Agent is designed to challenge emerging consensus to stimulate deeper reasoning. We formulate two mechanisms to encourage effective and context-aware interventions: (i) a complexity-aware intervention that modulates agent engagement based on case difficulty, and (ii) a tone-calibrated intervention articulated to balance critique and collaboration. Evaluations on nine medical Q&A and three medical VQA benchmarks show that our approach consistently outperforms both single- and multi-agent LLMs frameworks, including leading commercial models such as GPT-4o and DeepSeek-R1. |
| title | Silence is Not Consensus: Disrupting Agreement Bias in Multi-Agent LLMs via Catfish Agent for Clinical Decision Making |
| topic | Computation and Language Artificial Intelligence Machine Learning Other Quantitative Biology |
| url | https://arxiv.org/abs/2505.21503 |