SIGIR

Rules, Resources, and Restrictions: A Taxonomy of Task-Based Information Request Intents

规则、资源与限制：任务导向信息请求意图的分类

Melanie A. Kilian, David Elsweiler

AI总结 本文提出任务导向信息请求意图的分类，以弥补传统查询方法与AI任务支持需求之间的差距。

Comments 11 pages, 1 figure, to be published in: 2026 ACM SIGIR Conference on Human Information Interaction and Retrieval (CHIIR '26), March 22-26, 2026, Seattle, WA, USA. ACM, New York, NY, USA, 11 pages. https://doi.org/10.1145/3786304.3787863

Information Farming: From Berry Picking to Berry Growing

信息耕作：从摘Berry到种Berry

Leif Azzopardi, Adam Roegiest

AI总结 本文提出信息耕作概念，认为生成式AI使人们从碎片化信息采集转向主动信息培养，标志着人类与信息互动方式的根本转变。

Comments ACM CHIIR 2026

Journal ref ACM SIGIR Conference on Human Information Interaction and Retrieval 2026

A Transfer Framework for Enhancing Temporal Graph Learning in Data-Scarce Settings

一种用于数据稀缺场景下增强时序图学习的迁移框架

Sidharth Agarwal, Tanishq Dubey, Shubham Gupta, Srikanta Bedathur

机构 * Indian Institute of Technology, Delhi（印度理工学院德里） 纠错

AI总结 本文提出一种迁移框架，通过解耦节点表示与特征，提升时序图学习在数据稀缺场景下的性能。

Journal ref SIGIR 2025: Proceedings of the 48th International ACM SIGIR Conference on Research and Development in Information Retrieval

From SERPs to Agents: A Platform for Comparative Studies of Information Interaction

从搜索结果页面到代理：一个用于信息交互比较研究的平台

Saber Zerhoudi, Michael Granitzer

AI总结 UXLab是一个开源平台，用于比较信息交互系统，通过无代码实验设计支持多模态交互研究。

Journal ref Proceedings of the 2026 ACM SIGIR Conference on Human Information Interaction and Retrieval (CHIIR '26)

In-Browser Agents for Search Assistance

浏览器中的搜索助手代理

Saber Zerhoudi, Michael Granitzer

AI总结 本文提出了一种浏览器内隐私保护的搜索助手代理，结合自适应概率模型与小语言模型，提升搜索效率同时保障用户隐私。

Journal ref Proceedings of the 2026 ACM SIGIR Conference on Human Information Interaction and Retrieval (CHIIR '26)

PersonaRAG: Enhancing Retrieval-Augmented Generation Systems with User-Centric Agents

PersonaRAG: 通过以用户为中心的代理增强检索增强生成系统

Saber Zerhoudi, Michael Granitzer

AI总结 PersonaRAG通过引入以用户为中心的代理，提升检索增强生成系统对用户需求的适应能力，实现更精准的个性化回答。

Journal ref Information Retrieval's Role in RAG Systems (IR-RAG) workshop at SIGIR, 2024, Washington D.C., USA

Expression Syntax Information Bottleneck for Math Word Problems

表达式语法信息瓶颈用于数学文字问题

Jing Xiong, Chengming Li, Min Yang, Xiping Hu, Bin Hu

机构 * Sun Yat-sen University（中山大学） ； SIAT, Chinese Academy of Sciences（中国科学院软件研究所） ； Lanzhou University（兰州大学） ； Institute for Clarity in Documentation（文档清晰研究所） 纠错

AI总结 本文提出ESIB方法，通过信息瓶颈理论提取数学文字问题的表达式语法本质特征，通过多模型相互学习和自蒸馏损失提升模型泛化能力与解题多样性。

Comments This paper has been accepted by SIGIR 2022. The code can be found at https://github.com/menik1126/math_ESIB

Towards Two-Stage Counterfactual Learning to Rank

迈向两阶段反事实学习排序

Shashank Gupta, Yiming Liao, Maarten de Rijke

AI总结 本文提出了一种两阶段反事实学习排序方法，通过联合训练候选生成器和排序器，解决大规模文档下的排序问题。

Comments Accepted at ICTIR 2025 (co-located with SIGIR 2025)

A Chain-of-Thought Approach to Semantic Query Categorization in e-Commerce Taxonomies

基于链式思维的电子商务分类语义查询分类方法

Jetlir Duraj, Ishita Khan, Kilian Merkelbach, Mehran Elyasi

机构 * eBay Inc, USA（eBay公司） ； eBay Inc, Germany（eBay公司） 纠错

AI总结 本文提出基于链式思维的电子商务查询分类方法，结合树搜索与LLM语义评分，提升分类准确性和扩展性。

Comments 9 pages, accepted at SIGIR eCom 2025

Journal ref Proceedings of the SIGIR eCom 2025 Workshop, CEUR-WS.org, Vol-4123

Accurate and Diverse Recommendations via Propensity-Weighted Linear Autoencoders

通过倾向加权线性自编码器实现准确且多样的推荐

Kazuma Onishi, Katsuhiko Hayashi, Hidetaka Kamigaito

AI总结 本文提出一种基于sigmoid函数的倾向评分方法，用于改善推荐系统中推荐的准确性和多样性。

Comments Published in the proceedings of SIGIR-AP'25

Journal ref SIGIR-AP 2025: Proceedings of the 2025 Annual International ACM SIGIR Conference on Research and Development in Information Retrieval in the Asia Pacific Region, pp. 153-159

Progressive Refinement of E-commerce Search Ranking Based on Short-Term Activities of the Buyer

基于买家短期行为的电商搜索排名渐进细化

Taoran Sheng, Sathappan Muthiah, Atiq Islam, Jinming Feng

机构 * eBay Inc.（eBay公司） 纠错

AI总结 本文提出基于买家短期行为的电商搜索排名渐进优化方法，通过逐步引入上下文信息提升搜索结果质量。

Journal ref SIGIR '25: The 48th International ACM SIGIR Conference on Research and Development in Information Retrieval, Padua Italy, July 13 - 18, 2025

Large Language Models as Search Engines: Societal Challenges

大语言模型作为搜索引擎：社会挑战

Zacchary Sadeddine, Winston Maxwell, Gaël Varoquaux, Fabian M. Suchanek

AI总结 本文探讨大语言模型取代搜索引擎带来的社会挑战，分析了提供者、创作者和用户的角色，并提出缓解策略与未来研究方向。

Journal ref SIGIR Forum 2025

EZYer: A simulacrum of high school with generative agent

EZYer: 一种高中学校的模拟体与生成代理

Jinming Yang, Zimu Ji, Weiqi Luo, Gaoxi Wang, Bin Ma, Yueling Deng

AI总结 EZYer通过生成代理技术模拟高中教学环境，提供结构化教学材料和互动笔记生成，确保学术严谨性和教学适宜性，实验表明其生成内容质量高，应用前景广阔。

Comments AgentIR@SIGIR 2025

ADORE: Autonomous Domain-Oriented Relevance Engine for E-commerce

ADORE：面向电商的自主领域导向相关性引擎

Zheng Fang, Donghao Xie, Ming Pang, Chunyuan Yuan, Xue Jiang, Changping Peng, Zhangang Lin, Zheng Luo

机构 * JD.COM Beijing China（京东公司） 纠错

AI总结 ADORE通过规则意识、错误类型感知和关键属性增强的创新，实现电商搜索中高效且认知对齐的相关性建模。

Comments Accepted by SIGIR 2025

Beyond GeneGPT: A Multi-Agent Architecture with Open-Source LLMs for Enhanced Genomic Question Answering

Haodong Chen, Guido Zuccon, Teerapong Leelanupab

机构 * The University of Queensland（昆士兰大学） 纠错

Comments This paper has been accepted to SIGIR-AP 2025

ScaleFormer: Span Representation Cumulation for Long-Context Transformer

Jiangshu Du, Wenpeng Yin, Philip Yu

机构 * University of Illinois Chicago（伊利诺伊大学芝加哥分校） ； The Pennsylvania State University（宾夕法尼亚州立大学） 纠错

Comments Accepted by SIGIR-AP'25

Personality over Precision: Exploring the Influence of Human-Likeness on ChatGPT Use for Search

Mert Yazan, Frederik Bungaran Ishak Situmeang, Suzan Verberne

机构 * Amsterdam University of Applied Sciences（阿姆斯特丹应用科学大学） ； University of Leiden（莱顿大学） 纠错

Comments Accepted at NIP-IR@SIGIR'25

Human vs. Agent in Task-Oriented Conversations

Zhefan Wang, Ning Geng, Zhiqiang Guo, Weizhi Ma, Min Zhang

Comments SIGIR-AP 2025

CogPlanner: Unveiling the Potential of Agentic Multimodal Retrieval Augmented Generation with Planning

Xiaohan Yu, Zhihan Yang, Chong Chen

Comments Accepted by SIGIR-AP 2025

Can We Hide Machines in the Crowd? Quantifying Equivalence in LLM-in-the-loop Annotation Tasks

Jiaman He, Zikang Leng, Dana McKay, Damiano Spina, Johanne R. Trippas

Comments Accepted at SIGIR-AP 2025

Knowing You Don't Know: Learning When to Continue Search in Multi-round RAG through Self-Practicing

Diji Yang, Linda Zeng, Jinmeng Rao, Yi Zhang

机构 * University of California Santa Cruz（加州大学圣克ruz分校） ； The Harker School（哈克尔学校） 纠错

Comments Proceedings of the 48th International ACM SIGIR 2025

AI Guided Accelerator For Search Experience

Jayanth Yetukuri, Mehran Elyasi, Samarth Agrawal, Aritra Mandal, Rui Kong, Harish Vempati, Ishita Khan

机构 * eBay Inc（eBay公司） 纠错

Comments Accepted at SIGIR eCom'25. https://sigir-ecom.github.io/eCom25Papers/paper_25.pdf

Evaluating Sakana's AI Scientist: Bold Claims, Mixed Results, and a Promising Future?

Joeran Beel, Min-Yen Kan, Moritz Baumgart

机构 * University of Siegen（Siegen大学） ； National University of Singapore（新加坡国立大学） 纠错

Comments 20 pages

Journal ref SIGIR Forum 2025

A Worrying Reproducibility Study of Intent-Aware Recommendation Models

Faisal Shehzad, Maurizio Ferrari Dacrema, Dietmar Jannach

Journal ref Proceedings ACM SIGIR 2025

REGENT: Relevance-Guided Attention for Entity-Aware Multi-Vector Neural Re-Ranking

Shubham Chatterjee

机构 * Missouri University of Science and Technology（密苏里科学与技术大学） ； Department of Computer Science（计算机科学系） 纠错

Comments To be published in: Proceedings of the 2025 Annual International ACM SIGIR Conference on Research and Development in Information Retrieval in the Asia Pacific Region (SIGIR-AP 2025)

QDER: Query-Specific Document and Entity Representations for Multi-Vector Document Re-Ranking

Shubham Chatterjee, Jeff Dalton

机构 * Missouri University of Science and Technology（密苏里科技大学） ； Department of Computer Science（计算机科学系） ； The University of Edinburgh（爱丁堡大学） 纠错

Comments Published in: Proceedings of the 48th International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR 2025)

VeriCite: Towards Reliable Citations in Retrieval-Augmented Generation via Rigorous Verification

Haosheng Qian, Yixing Fan, Jiafeng Guo, Ruqing Zhang, Qi Chen, Dawei Yin, Xueqi Cheng

Journal ref In Proceedings of the 2025 Annual International ACM SIGIR Conference on Research and Development in Information Retrieval in the Asia Pacific Region (SIGIR-AP 2025)

Distilling a Small Utility-Based Passage Selector to Enhance Retrieval-Augmented Generation

Hengran Zhang, Keping Bi, Jiafeng Guo, Jiaming Zhang, Shuaiqiang Wang, Dawei Yin, Xueqi Cheng

机构 * State Key Laboratory of AI Safety, Institute of Computing Technology, Chinese Academy of Sciences（人工智能安全国家重点实验室，计算技术研究所，中国科学院） ； University of Chinese Academy of Sciences（中国科学院大学） ； Baidu Inc（百度公司） 纠错

Comments Accepted by SIGIR-AP25

Queries Are Not Alone: Clustering Text Embeddings for Video Search

Peyang Liu, Xi Wang, Ziqiang Cui, Wei Ye

Comments Accepted by International ACM SIGIR Conference on Research and Development in Information Retrieval 2025

ISMIE: A Framework to Characterize Information Seeking in Modern Information Environments

Shuoqi Sun, Danula Hettiachchi, Damiano Spina

Comments This paper has been accepted to SIGIR-AP 2025