Researcher — paper.dinq.me

2026 顶会论文

作者位次 #5/5NeurIPS 2026Poster

Effective Knowledge Conflict Detection via Joint Agentic Optimization

Yi Hong · Wenchao Bai · Jiaqi Jiang · Siyuan Huang · Jiahui Jin

智能体与工具检索与知识OpenReview

作者位次 #4/4NeurIPS 2026Poster

Optimizing Agent Tool-Use via Trajectory-based Insight Evolution

Hanchen Qiu · Haojia Zhu · Yifan Meng · Jiahui Jin

智能体与工具OpenReview

作者位次 #7/8ACL 2026Poster· Natural Language Processing

Don’t Be Misled by Style: A Style-Adaptive Reranker for Capturing Effective Knowledge in Retrieval-Augmented Generation

Ruwen Zhang · Bo Liu · Zhang Sheng Xiang · Yida Chen · Hantao Zhao · Ding Ding · Jiahui Jin · Jiuxin Cao

摘要

Rerankers are critical in Retrieval-Augmented Generation (RAG) for filtering evidence that enhances the accurate generation of LLMs. With the extension to open-domain scenarios, rerankers are inevitably deployed on mixed-style corpora, whereas most existing rerankers are mainly trained on well-ed...

检索与知识对齐与偏好安全OpenReview 项目页

作者位次 #3/4KDD 2026Oral· Knowledge Discovery & Data Mining