樹狀辯論法：多人格辯論樹激發批判性思維，助力科學比較分析

摘要

隨著現代科技的進步和可及性的提升，科學研究的數量呈指數級增長，這使得科學發現在各個領域內部和跨領域之間變得日益碎片化。這種情況使得評估相關研究的重要性、新穎性、增量發現以及等價觀點變得尤為困難，尤其是對於來自不同研究群體的工作。近年來，大型語言模型（LLMs）展現出強大的定量和定性推理能力，而多智能體LLM辯論在處理複雜推理任務方面顯示出潛力，通過探索多樣化的觀點和推理路徑。受此啟發，我們引入了“辯論樹”（Tree-of-Debate, ToD）框架，該框架將科學論文轉化為LLM角色，讓它們就各自的新穎性進行辯論。為了強調結構化的批判性推理而非僅僅關注結果，ToD動態構建辯論樹，從而能夠對學術文章中的獨立新穎性論點進行細粒度分析。通過在多個領域的科學文獻上進行實驗，並由專家研究人員評估，我們證明ToD能夠生成信息豐富的論點，有效對比論文，並支持研究人員進行文獻綜述。

English

With the exponential growth of research facilitated by modern technology and improved accessibility, scientific discoveries have become increasingly fragmented within and across fields. This makes it challenging to assess the significance, novelty, incremental findings, and equivalent ideas between related works, particularly those from different research communities. Large language models (LLMs) have recently demonstrated strong quantitative and qualitative reasoning abilities, and multi-agent LLM debates have shown promise in handling complex reasoning tasks by exploring diverse perspectives and reasoning paths. Inspired by this, we introduce Tree-of-Debate (ToD), a framework which converts scientific papers into LLM personas that debate their respective novelties. To emphasize structured, critical reasoning rather than focusing solely on outcomes, ToD dynamically constructs a debate tree, enabling fine-grained analysis of independent novelty arguments within scholarly articles. Through experiments on scientific literature across various domains, evaluated by expert researchers, we demonstrate that ToD generates informative arguments, effectively contrasts papers, and supports researchers in their literature review.

樹狀辯論法：多人格辯論樹激發批判性思維，助力科學比較分析

Tree-of-Debate: Multi-Persona Debate Trees Elicit Critical Thinking for Scientific Comparative Analysis

摘要

Summary

Support

Support