arXivDaily arXiv每日学术速递 周一至周五更新

期刊&会议

ACM SIGIR Conference on Research and Development in Information Retrieval · 会议 · Information Retrieval

2026-06-16 至 2026-06-16 共收录 4
2606.15998 2026-06-16 cs.IR cs.AI cs.CL cs.LG 新提交

Entity Labels Are Not Entity Signals: A Framework for Observable Relevance in Document Re-Ranking

实体标签并非实体信号:文档重排序中可观测相关性的框架

Utshab Kumar Ghosh, Shubham Chatterjee

机构 * Department of Computer Science, Missouri University of Science and Technology(计算机科学系,密苏里科技大学)

AI总结 提出实体可观测相关性(OER)与概念相关性(CER)的区分,证明CER监督效果差,而OER对齐可显著提升重排序性能。

Comments ICTIR '26

Journal ref Proceedings of the 2026 International ACM SIGIR Conference on Innovative Concepts and Theories in Information Retrieval (ICTIR)

详情

展开后加载摘要…

URL PDF HTML 收藏
2605.05855 2026-06-16 cs.IR cs.CL 版本更新

Bridging Passive and Active: Enhancing Conversation Starter Recommendation via Active Expression Modeling

桥接被动与主动:通过主动表达建模增强对话启动推荐

Yiqing Wu, Haoming Li, Guanyu Jiang, Jiahao Liang, Yongchun Zhu, Jingwu Chen, Feng Zhang

机构 * Bytedance Beijing China(字节跳动北京中国)

AI总结 针对LLM驱动的对话搜索中被动推荐陷入回声室的问题,提出PA-Bridge框架,通过对抗分布对齐器桥接被动推荐与主动表达之间的分布差异,并引入语义离散化器实现流行度去偏,在线实验显著提升特征渗透率和用户活跃天数。

Comments Accepted by SIGIR 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2604.17301 2026-06-16 cs.CL cs.AI cs.HC cs.IR cs.LG 版本更新

RoTRAG: Rule of Thumb Reasoning for Conversation Harm Detection with Retrieval-Augmented Generation

RoTRAG: 基于经验法则推理的检索增强生成对话有害内容检测

Juhyeon Lee, Wonduk Seo, Junseo Koh, Seunghyun Lee, Haihua Chen, Yi Bu

机构 * Peking University(北京大学) Enhans University of North Texas(北得克萨斯大学)

AI总结 提出RoTRAG框架,通过检索外部道德规范(RoTs)增强LLM的多轮对话有害内容检测,实现基于规范推理和分类,平均F1提升约40%,分布误差降低8.4%。

Comments Accepted by SIGIR-ICTIR 2026, Oral Presentation

Journal ref Proceedings of the 2026 International ACM SIGIR Conference on Innovative Concepts and Theories in Information Retrieval (ICTIR '26), July 25, 2026, Melbourne, VIC, Australia. ACM, New York, NY, USA, 12 pages

详情

展开后加载摘要…

URL PDF HTML 收藏
2602.14710 2026-06-16 cs.IR cs.AI 版本更新

Orcheo: A Modular Full-Stack Platform for Conversational Search

Orcheo: 一个用于对话式搜索的模块化全栈平台

Shaojie Jiang, Svitlana Vakulenko, Maarten de Rijke

机构 * University of Amsterdam(阿姆斯特丹大学) AI Colleagues(AI同事) WU Vienna University of Economics and Business(维也纳经济与商业大学)

AI总结 提出Orcheo开源平台,通过模块化架构、生产级基础设施和45+即用组件,解决对话式搜索研究中框架统一与原型部署的难题。

Comments Accepted to SIGIR 2026

详情

展开后加载摘要…

URL PDF HTML 收藏