用多个AI角色协作生成更高质量的学术书目。
Enhancing Annotated Bibliography Generation with LLM Ensembles
- 让不同AI分工：写作、评审、摘要，协同完成任务。
- 相比单个AI，书目相关性提升38%，内容重复减少51%。
- 适合需要高效产出高质量文献综述的研究者。
本文提出一种基于大语言模型（LLM）集成的新方法，用于增强带注释的参考文献生成。通过系统性方法，引入多个扮演不同角色的LLM——可控文本生成、评估与摘要——来提升学术任务表现。集成生成的文本通过不同参数设置实现多样性，随后由一个作为评判者的LLM评估其相关性、准确性和连贯性。采用多种融合策略筛选并合并响应，再经摘要提炼与冗余消除进行优化。初步实验验证表明，集成输出在连贯性和相关性方面优于单一模型，注释质量提升38%，内容冗余降低51%，凸显了该方法在保持高质量标准前提下自动化复杂学术任务的潜力。
原文摘要 · Abstract (English)
This work proposes a novel approach to enhancing annotated bibliography generation through Large Language Model (LLM) ensembles. In particular, multiple LLMs in different roles -- controllable text generation, evaluation, and summarization -- are introduced and validated using a systematic methodology to enhance model performance in scholarly tasks. Output diversity among the ensemble that generates text is obtained using different LLM parameters, followed by an LLM acting as a judge to assess relevance, accuracy, and coherence. Responses selected by several combining strategies are then merged and refined through summarization and redundancy removal techniques. The preliminary experimental validation demonstrates that the combined outputs from the LLM ensemble improve coherence and relevance compared to individual responses, leading to a 38% improvement in annotation quality and a 51% reduction in content redundancy, thus highlighting the potential for automating complex scholarly tasks while maintaining high-quality standards.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。