cs.AI updates on arXiv.org 07月01日 02:45
Literature-Grounded Novelty Assessment of Scientific Ideas
index_new5.html
../../../zaker_core/zaker_tpl_static/wap/tpl_guoji1.html

 

本文提出了一种基于LLM的检索增强生成框架——Idea Novelty Checker,用于自动评估科学想法的新颖性。通过两阶段检索和重新排序,该框架在评估新颖性方面比现有方法提高了约13%的准确度。

arXiv:2506.22026v1 Announce Type: cross Abstract: Automated scientific idea generation systems have made remarkable progress, yet the automatic evaluation of idea novelty remains a critical and underexplored challenge. Manual evaluation of novelty through literature review is labor-intensive, prone to error due to subjectivity, and impractical at scale. To address these issues, we propose the Idea Novelty Checker, an LLM-based retrieval-augmented generation (RAG) framework that leverages a two-stage retrieve-then-rerank approach. The Idea Novelty Checker first collects a broad set of relevant papers using keyword and snippet-based retrieval, then refines this collection through embedding-based filtering followed by facet-based LLM re-ranking. It incorporates expert-labeled examples to guide the system in comparing papers for novelty evaluation and in generating literature-grounded reasoning. Our extensive experiments demonstrate that our novelty checker achieves approximately 13% higher agreement than existing approaches. Ablation studies further showcases the importance of the facet-based re-ranker in identifying the most relevant literature for novelty evaluation.

Fish AI Reader

Fish AI Reader

AI辅助创作,多种专业模板,深度分析,高质量内容生成。从观点提取到深度思考,FishAI为您提供全方位的创作支持。新版本引入自定义参数,让您的创作更加个性化和精准。

FishAI

FishAI

鱼阅,AI 时代的下一个智能信息助手,助你摆脱信息焦虑

联系邮箱 441953276@qq.com

相关标签

科学创新 LLM框架 检索增强生成
相关文章