Table of Contents

• TopicTune: A Topic Alignment Approach to Improve LLMs Reasoning on Social QuestionsMaryam Amirizaniani, Baktash Ansari, Chirag Shah 0001, Afra Mashhadi. 1-11 [doi]
• Preventing Content Leakage in LLM-Based Medical RAG: Structure-Only Retrieval for Faithful Clinical SummarizationAleka Melese Ayalew, Tapio Seppänen, Mourad Oussalah 0002. 12-22 [doi]
• Uncertainty Quantification for Multimodal Retrieval Augmented GenerationSimon Binz, Heydar Soudani, Faegheh Hasibi. 23-33 [doi]
• DeepResearchGym: A Free, Transparent, and Reproducible Sandbox for Deep ResearchJoão Coelho, Jingjie Ning, Jingyuan He, Kangrui Mao, Abhijay Sai Paladugu, Pranav Setlur, Jiahe Jin, Jamie Callan, João Magalhães, Bruno Martins 0001, Chenyan Xiong. 34-43 [doi]
• LLM-Driven Usefulness Judgment for Web Search EvaluationMouly Dewan, Jiqun Liu, Aditya Gautam, Chirag Shah 0001. 44-55 [doi]
• Bridging the Gap between Subsampled and Full-Corpus EvaluationMichael Dinzinger, Kanishka Ghosh Dastidar, Laura Caspari, Jelena Mitrovic, Michael Granitzer. 56-61 [doi]
• From Noise to Order: Learning to Rank via Denoising DiffusionSajad Ebrahimi 0001, Bhaskar Mitra 0001, Negar Arabzadeh, Ye Yuan 0017, Haolun Wu, Fattane Zarrinkalam, Ebrahim Bagheri. 62-72 [doi]
• Ranking Passages in Relevant Documents Using LLMsEyal El Ani, Eilon Sheetrit, Oren Kurland. 73-81 [doi]
• Towards Adaptive and Retriever-friendly Retrieval-augmented Generation via Reinforcement LearningYubo Fang, Hai-Tao Yu, Hideo Joho, Sumio Fujita. 82-93 [doi]
• A Theoretical Framework for Risk Analysis of Stochastic RankersDebasis Ganguly. 94-104 [doi]
• Reasoning with Large Language Models for Relevance JudgementsLouis Geiger, Danula Hettiachchi, Falk Scholer, Johanne R. Trippas. 105-110 [doi]
• Adaptive Re-RankingAta Cinar Genc, Emir Kaan Korukluoglu, James Allan 0001. 111-117 [doi]
• Entity Labels Are Not Entity Signals: A Framework for Observable Relevance in Document Re-RankingUtshab Kumar Ghosh, Shubham Chatterjee. 118-128 [doi]
• Does Form Affect Function? An Extended Study of LLM Re-Ranking BehaviorReyhaneh Goli, Alistair Moffat. 129-138 [doi]
• To Believe or Not To Believe: Comparing Supporting Information Tools to Aid Human Judgments of AI VeracityJessica Irons, Patrick S. Cooper, Necva Bölücü, Andreas Duenser, Roelien C. Timmer, Huichen Yang, Changhyun Lee, Brian Jin, Stephen Wan 0001. 139-150 [doi]
• A Replicability Study of XTRRohan Jha, Reno Kriz, Benjamin Van Durme. 151-158 [doi]
• Rank, Don't Generate: Statement-level Ranking for Explainable RecommendationBen Kabongo, Arthur Satouf, Vincent Guigue. 159-170 [doi]
• Adaptive Token-Aware Query Reformulation for Text-to-Image RetrievalSeonah Kim, Minkeon Kim, Youjin Lee, Jaekwang Kim 0001, Jinyoung Han, Eunil Park. 171-175 [doi]
• RecQuest: Towards Estimating User Domain Knowledge in Conversational Recommender SystemsIvica Kostric, Ujwal Gadiraju, Krisztian Balog. 176-186 [doi]
• Analysis of Reasoning-Intensive Retrieval in JapaneseHiroki Kurokawa, Hirotaka Kameko, Shinsuke Mori. 187-198 [doi]
• Rank-ICL: Ranking-based In-context Learning for Search Result ExplanationArif Laksito, Aali Alqarni, Mark Stevenson 0001. 199-205 [doi]
• A Comprehensive Taxonomy of Temporal Dimensions in Natural Language QueriesIvano Lauriola. 206-217 [doi]
• RoTRAG: Rule of Thumb Reasoning for Conversation Harm Detection with Retrieval-Augmented GenerationJuhyeon Lee, Wonduk Seo, Junseo Koh, Seunghyun Lee, Haihua Chen 0002, Yi Bu 0001. 218-229 [doi]
• DoGMaTiQ: Automated Generation of Question-and-Answer Nuggets for Report EvaluationBryan Li, William Gantt Walden, Yu Hou, Gabrielle Kaili-May Liu, Dawn J. Lawrie, James Mayfield, Eugene Yang 0001, Chris Callison-Burch, Laura Dietz. 230-240 [doi]
• RAMP: Robust Ad Recommendation Under Limited Personalized-Feature Availability via Masking and Alignment PathwaysDairui Liu, Zhongyi Lu, Roger Zhe Li, Changhong Jin, Jitao Lu, Xinyang Shao, Bichen Shi, Mete Sertkan, Aghiles Salah, Aonghus Lawlor, Barry Smyth, Tri Kurniawan Wijaya, Ruihai Dong, Xingsheng Guo. 241-252 [doi]
• RIDRec: Retrieval-Enhanced Intent Diffusion for Anonymous Short-Session RecommendationPeilin Liu, Zhiquan Ji, Gang Yan 0002. 253-261 [doi]
• Exposure-Based Reinforcement Learning to RankHarrie Oosterhuis, Rolf Jagerman, Zhen Qin 0001, Xuanhui Wang. 262-273 [doi]
• Relaxed Term Matching for Neural Axiomatic DiagnosticsAndrew Parry, Maik Fröbe, Martin Potthast, Sean MacAvaney, Benno Stein 0001, Matthias Hagen, Debasis Ganguly. 274-284 [doi]
• RAAD: Retrieval-Augmented Ambiguity Detection via Answer DiversityParth Patel, Sarah Kamoun, Bita Azad, Faezeh Ensan. 285-292 [doi]
• Stability in Competitive Search with Results DiversificationItamar Reinman, Omer Madmon, Moshe Tennenholtz, Oren Kurland. 293-302 [doi]
• Interpretable Legal Similarity: From Embeddings to ObligationsAdam Roegiest, Johanne R. Trippas. 303-311 [doi]
• ARIC: A Cognitive Framework for Explanatory Narrative Evaluation in Conversational Information Seeking SystemsVahid Sadiri Javadi, Sadia Naseer, Ali Ather, Lucie Flek, Johanne R. Trippas. 312-323 [doi]
• Plan-and-Refine in RAG: Generating Diverse and Comprehensive Responses through Global Exploration and Local ExploitationAlireza Salemi, Chris Samarinas, Hamed Zamani. 324-336 [doi]
• Beyond Relevance: On the Relationship Between Retrieval and RAG Information CoverageSaron Samuel, Alexander Martin 0006, Eugene Yang 0001, Andrew Yates, Dawn Lawrie, Ian Soboroff, Laura Dietz, Benjamin Van Durme. 337-348 [doi]
• Model Merging as an Alternative to Fine-Tuning on Combined Data for a Multi-Domain Dense RetrieverTaiga Sasaki, Takehiro Yamamoto, Hiroaki Ohshima, Sumio Fujita. 349-355 [doi]
• MedQueryIntent: A Large-Scale Benchmark Dataset for Medical Search Intent ClassificationSamantha Schnell, Supriya Kottam, Yingcheng Sun. 356-363 [doi]
• Proposing an Evaluation Framework for Legal Case Retrieval Beyond Binary Relevance: A Bibliographic Coupling ApproachAtsuhito Sekiguchi, Masaharu Yoshioka, Calum Kwan. 364-369 [doi]
• Equity by Design? On the Trade-Offs in Fairness-Driven Recommendation in Heterogeneous Two-Sided MarketsDominykas Seputis, Alexander Timans, Rajeev Verma. 370-380 [doi]
• Effectiveness of Sparse Retrieval for Automated Fact-CheckingRitvik Setty, Vinay Setty. 381-391 [doi]
• A Design Science Framework for Human-Agent Teams in Information RetrievalChirag Shah 0001, Lynda Tamine, Mouly Dewan. 392-402 [doi]
• Search Arena Meets Nuggets: Towards Explanations and Diagnostics in the Evaluation of LLM ResponsesSahel Sharifymoghaddam, Shivani Upadhyay, Nandan Thakur, Ronak Pradeep, Jimmy Lin. 403-413 [doi]
• Prior-Data Fitted Networks as Tabular Foundation Models for Ranking in Low-Data SettingsDavid Vos, Samarth Bhargav 0001, Maarten de Rijke, Harrie Oosterhuis. 414-424 [doi]
• As We May SearchSaber Zerhoudi, Adam Roegiest, Jelena Mitrovic, Michael Granitzer. 425-435 [doi]
• Patent Representation Learning via Self-supervisionYou Zuo, Kim Gerdes, Éric de la Clergerie, Benoît Sagot. 436-445 [doi]