Programme: Main conference

Monday

9:00 – 10:00
Keynote (plenary)
10:30 – 12:30
Room A Full Papers
Full Papers 1: Core Retrieval Models, Representations & Evaluation
  • Sample-Free Almost-Exact Estimation of Plackett-Luce Propensities for Off-Policy Ranking
    Norman Knyazev and Harrie Oosterhuis
  • Validating Search Query Simulations: A Taxonomy of Measures
    Andreas Konstantin Kruff, Nolwenn Bernard and Philipp Schaer
  • Reducing Human Effort to Validate LLM Relevance Judgements via Stratified Sampling
    Simone Merlo, Stefano Marchesin, Guglielmo Faggioli and Nicola Ferro
  • Revealing MonoT5's Learning Mechanisms via Prompt-Token Adaptation
    Marco Braga, Sean MacAvaney, Craig Macdonald and Gabriella Pasi
  • When Reducing Representations Improves Performance
    Andrea Pasin, Guglielmo Faggioli, Nicola Ferro, Raffaele Perego and Nicola Tonellotto
  • An Empirical Study of Model Casing in Learned Sparse Retrieval
    Emmanouil Georgios Lionis, Jia-Huei Ju, Angelos Nalmpantis, Casper Thuis, Sean MacAvaney and Andrew Yates
  • Improving Instruction-Aware Retrieval with Query-Preserving Regularization
    Hyewon Kim and Hyun-Je Song
Room B Full Papers
Full Papers 2: Applied Generation, Evaluation & Analysis with LLMs
  • Contradictions in Context: Challenges for Retrieval-Augmented Generation in Healthcare
    Saeedeh Javadi, Sara Mirabi, Manan Gangar and Bahadorreza Ofoghi
  • Small Models, Big Picture! A Language Model Augmentation for Enhanced Reader-Aware Summarization
    Raghvendra Kumar, A S Poornash and Sriparna Saha
  • From Comments to Conclusions: Adaptive Reader-Aware Summary Generation in Low-Resource Languages via Agent Debate
    Raghvendra Kumar, Mohammed Salman S A, Jaya Verma and Sriparna Saha
  • Prompt Compression in the Wild: Measuring Latency, Rate Adherence, and Quality for Faster LLM Inference
    Cornelius Kummer, Lena Jurkschat, Michael Färber and Sahar Vahdati
  • Towards Quantitative Summarization Evaluation: An Integrated Atomic-Based Evaluation Framework and Dataset for Text Summarization
    Yan Lei, Suncong Zheng, Roberts Wang, Liang Pang, Lei He, Shuang Chen, Wang Yu, Huawei Shen, Xueqi Cheng and Yuanzhuo Wang
  • ExpertMix: Aspect and Severity Detection in Conversational Complaints
    Sarmistha Das, Apoorva Singh, Rishu Kumar Singh, Navneet Shreya and Sriparna Saha
  • MemTool: Optimizing Short-Term Memory Management for Dynamic Tool Retrieval and Invocation in LLM Agent Multi-Turn Conversations
    Elias Lumer
Room C IR4Good
IR4Good 1: IR-for-Good Paper Session I
  • From Engagement to Empowerment: A Capability-Theoretic Rethinking of Recommender Systems
    Vittoria Vineis and Gabriele Tolomei
  • Bias in Book Recommendation: A Case Study on the Danish Public Libraries
    Savvina Daniil, Søren Højlund Mollerup and Laura Hollink
  • How Do LLMs Cite? A Mechanistic Interpretation of Attribution in RAG
    Ian van Dort and Maria Heuss
  • All That Matters: Revisiting Children's Concept of Relevance in Primary School Context
    Diletta Micol Tobia, Hrishita Chakrabarti, Maria Soledad Pera and Monica Landoni
  • When Attention Becomes Exposure in Generative Search
    Shayan Alipour, Mehdi Kargar and Morteza Zihayat
  • Counterfactual Understanding via Retrieval-Aware Multimodal Modeling for Time-to-Event Survival Prediction
    Ha-Anh Hoang Nguyen, Tri-Duc Phan Le, Duc-Hoang Pham, Huy-Son Nguyen, Cam-Van Thi Nguyen, Duc-Trong Le and Hoang-Quynh Le
  • Joint Modeling of Candidate and Recruiter Preferences for Fair Two-Sided Job Matching
    Clara Rus, Masoud Mansoury, Andrew Yates and Maarten de Rijke
14:30 – 15:30
Room A Full Papers
Full Papers 3: Specialized Retrieval Domains & Architectures
  • Filtering Few-Level Segment Regions for Efficient Subsequence Search in 3D Human Motions
    Andrej Černek and Jan Sedmidubsky
  • Starbucks: Improved Training for 2D Matryoshka Embeddings
    Shengyao Zhuang, Shuai Wang, Fabio Zheng, Bevan Koopman and Guido Zuccon
  • Website Segmentation Beyond Structure: A Benchmark on Functional and Digital Maturity Classes
    Jonathan Gerber, Jasmin Saxer, Andreas Weiler and Michael Grossniklaus
Room B Reproducibility
Reproducibility 1: Recommender Systems
  • Are Multimodal Embeddings Truly Beneficial for Recommendation? A Deep Dive into Whole vs. Individual Modalities
    Yu Ye, Junchen Fu, Yu Song, Kaiwen Zheng and Joemon Jose
  • RecRankerEval: A Reproducible Framework for Deploying and Evaluating LLM-Based Top-k Recommenders
    Zeyuan Meng, Zixuan Yi and Iadh Ounis
  • Efficient Optimization of Hierarchical Identifiers for Generative Recommendation
    Federica Valeau, Odysseas Boufalis, Polytimi Gkotsi, Joshua Rosenthal and David Vos
  • A Reproducible and Fair Evaluation of Partition-Aware Collaborative Filtering
    Domenico de Gioia, Claudio Pomo, Ludovico Boratto and Tommaso Di Noia
  • A Systematic Reproducibility Study of BSARec for Sequential Recommendation
    Jan Hutter, Hua Chang Bakker, Stan Fris, Angela Madelon Bernardy and Yuanna Liu
Room C IR4Good
IR4Good 2: IR-for-Good Paper Session II
  • Measuring Political Stance and Consistency in Large Language Models
    Mucahid Kutlu, Saban Kardas, Salah Feras Alali and Mohammad Nashat Maasfeh
  • Judiciously Reducing Sub-Group Comparisons for Learning Intersectional Fair Representations
    Clara Rus, Andrew Yates and Maarten de Rijke
  • Modeling Behavioral Patterns in News Recommendations Using Fuzzy Neural Networks
    Kevin Innerebner, Stephan Bartl, Markus Reiter-Haas and Elisabeth Lex
  • Does Reasoning Make Search More Fair? Comparing Fairness in Reasoning and Non-Reasoning Rerankers
    Saron Samuel, Benjamin Van Durme and Eugene Yang
16:00 – 17:00
Room A Findings
Findings Lightning Talks
Room B Reproducibility
Reproducibility 2: Retrieval
  • Fast, Compact, Dynamic Indexing for Learned Sparse Retrieval Systems
    Billy Rule and Joel Mackenzie
  • Down with the Hierarchy: The 'H' in HNSW Stands for "Hubs"
    Blaise Munyampirwa, Vihan Lakshman and Benjamin Coleman
  • Multivector Reranking in the Era of Strong First-Stage Retrievers
    Silvio Martinico, Franco Maria Nardini, Cosimo Rulli and Rossano Venturini
  • Temporal Fact Conflicts in LLMs: Reproducibility Insights from Unifying DYNAMICQA and MULAN
    Ritajit Dey, Iadh Ounis, Graham McDonald and Yashar Moshfeghi
Room C IR4Good
IR4Good Invited Talks and Panel

Tuesday

9:00 – 10:00
Keynote – IR4Good (plenary)
10:30 – 12:30
Room A Full Papers
Full Papers 4: LLMs as Rankers, Rerankers & Judges
  • Training-Induced Bias Toward LLM-Generated Content in Dense Retrieval
    William Xion and Wolfgang Nejdl
  • OrLog: Resolving Complex Queries with LLMs and Probabilistic Reasoning
    Mohanna Hoveyda, Jelle Piepenbrock, Arjen de Vries, Maarten de Rijke and Faegheh Hasibi
  • LLM-based Listwise Reranking Under the Effect of Positional Bias
    Jingfen Qiao, Jin Huang, Xinyu Ma, Shuaiqiang Wang, Dawei Yin, Evangelos Kanoulas and Andrew Yates
  • RerAnchor: Anchoring Important Context in Multi-Modal Document Reranking
    Tz-Huan Hsu, Sian-Yao Huang, Kuanlun Liao, Che-Yu Lin and Cheng-Lin Yang
  • How Role-Play Shapes Relevance Judgment in Zero-Shot LLM Rankers
    Yumeng Wang, Jirui Qi, Catherine Chen, Panagiotis Eustratiadis and Suzan Verberne
  • Influential Training Data Retrieval for Explaining Verbalized Confidence of LLMs
    Yuxi Xia, Loris Schoenegger and Benjamin Roth
  • LANCER: LLM Reranking for Nugget Coverage
    Jia-Huei Ju, François G. Landry, Eugene Yang, Suzan Verberne and Andrew Yates
Room B Full Papers
Full Papers 5: RAG: Retrieval Utility, Scaling & Infrastructure
  • Who Benefits from RAG? The Role of Exposure, Utility and Attribution Bias
    Mahdi Dehghan and Graham McDonald
  • Utilizing Metadata for Better Retrieval-Augmented Generation
    Raquib Bin Yousuf, Shengzhe Xu, Mandar Sharma, Andrew Neeser, Chris Latimer and Naren Ramakrishnan
  • Predicting Retrieval Utility and Answer Quality in Retrieval-Augmented Generation
    Fangzheng Tian, Debasis Ganguly and Craig Macdonald
  • Open Web Indexes for Remote Querying
    Gijs Hendriksen, Djoerd Hiemstra and Arjen P. de Vries
  • LURE-RAG: Lightweight Utility-Driven Reranking for Efficient RAG
    Manish Chandra, Debasis Ganguly and Iadh Ounis
  • Insider Knowledge: How Much Can RAG Systems Gain from Evaluation Secrets
    Laura Dietz, Bryan Li, Eugene Yang, Dawn Lawrie, William Walden and James Mayfield
  • Less LLM, More Documents: Searching for Improved RAG
    Jingjie Ning, Yibo Kong, Yunfan Long and Jamie Callan
Room C IR4Good
IR4Good 3: IR-for-Good Paper Session III
  • AgriIR: A Scalable Framework for Domain-Specific Knowledge Retrieval
    Shuvam Banerji Seal, Aheli Poddar, Alok Mishra and Dwaipayan Roy
  • Extending Logic Tensor Networks to Implicit Feedback for Representation-Aware Music Recommendation
    Hannah Eckert, Oleg Lesota and Markus Schedl
  • Cultural Analytics for Good: Building Inclusive Evaluation Frameworks for Historical IR
    Suchana Datta, Dwaipayan Roy, Derek Greene, Gerardine Meaney, Karen Wade and Philipp Mayr
  • One LLM to Train Them All: A Multi-Task Learning Framework for Fact-Checking
    Malin Astrid Larsson, Harald Fosen Grunnaleite and Vinay Setty
  • How Information Retrieval Systems Construct and Amplify Immigration Narratives
    Zarif Masud, Abhijit Paul, Syed Ishtiaque Ahmed and Ebrahim Bagheri
  • Towards Reliable Machine Translation: Scaling LLMs for Critical Error Detection and Safety
    Muskaan Chopra, Lorenz Sparrenberg and Rafet Sifa
  • Integrating AI and IR Paradigms for Sustainable and Trustworthy Accurate Access to Large Scale Biomedical Information
    Federico Borazio, Danilo Croce, Roberto Basili and Francesco Labbate
  • Debiasing CLIP with Neural Interventions
    Amelia Gómez Grabowska, Jordi Gonzalez and Lluis Gomez
14:30 – 16:00
Room A Full Papers
Full Papers 6: Multimodal Retrieval & Embeddings
  • Event-Aware Video Corpus Moment Retrieval
    Danyang Hou, Liang Pang, Yanyan Lan, Huawei Shen and Xueqi Cheng
  • Scalable Music Cover Retrieval Using Lyrics-Aligned Audio Embeddings
    Joanne Affolter, Benjamin Martin, Elena V. Epure, Gabriel Meseguer-Brocal and Frédéric Kaplan
  • Image Complexity-Aware Adaptive Retrieval for Efficient Vision-Language Models
    Mikel Williams-Lekuona and Georgina Cosma
  • Cross-Sensory Brain Passage Retrieval: Scaling Beyond Visual to Audio
    Niall McGuire and Yashar Moshfeghi
  • Learning Audio–Visual Embeddings with Inferred Latent Interaction Graphs
    Donghuo Zeng, Hao Niu, Yanan Wang and Masato Taya
Room B Full Papers
Full Papers 7: Trustworthy and Responsible Retrieval-Augmented Systems
  • Learned Hallucination Detection in Black-Box LLMs Using Token-Level Entropy Production Rate
    Charles Moslonka, Hicham Randrianarivo, Arthur Garnier and Emmanuel Malherbe
  • FACTUM: Mechanistic Detection of Citation Hallucination in Long-Form RAG
    Maxime Dassen, Rebecca Kotula, Kenton Murray, Andrew Yates, Dawn Lawrie, Efsun Kayi, James Mayfield and Kevin Duh
  • SUMMIR: A Hallucination-Aware Framework for Ranking Sports Insights from LLMs
    Nitish Kumar, Sannu Kumar, S Akash, Manish Gupta, Ankith Karat and Sriparna Saha
  • Bribery-Resistant Ranking Systems: A Multipartite User-Agnostic Framework for AI Act Compliance
    Martim Baltazar, Ludovico Boratto, Mirko Marras and Guilherme Ramos
  • RAC: Retrieval-Augmented Clarification for Faithful Conversational Search
    Ahmed Rayane Kebir, Vincent Guigue, Lynda Said Lhadj and Laure Soulier
Room C Resource
Resource 1: Interactive and Conversational Search
  • WildClaims: Conversational Information Access in the Wild(Chat)
    Hideaki Joko, Shakiba Amirshahi, Charles L. A. Clarke and Faegheh Hasibi
  • LISP – A Rich Interaction Dataset and Loggable Interactive Search Platform
    Jana Isabelle Friese, Andreas Konstantin Kruff, Philipp Schaer, Norbert Fuhr and Nicola Ferro
  • UserSimCRS v2: Simulation-Based Evaluation for Conversational Recommender Systems
    Nolwenn Bernard and Krisztian Balog
  • Sim4IA-Bench: A User Simulation Benchmark Suite for Next Query and Utterance Prediction
    Andreas Konstantin Kruff, Christin Katharina Kreutz, Timo Breuer, Philipp Schaer and Krisztian Balog
  • Beyond the Click: A Framework for Inferring Cognitive Traces in Search
    Saber Zerhoudi and Michael Granitzer
Evening Banquet

Wednesday

9:00 – 10:00
Keynote – KvR (plenary)
10:30 – 12:30
Room A IRRJ
IRRJ Papers
Room B CLEF
CLEF Tracks Presentations
Room C Resource
Resource 2: Domain- and Language-Specific Datasets
  • FaE: A Resource of Logs, Profiles, and Rankings for Academic Expert Finding
    Marjan Azimi, Alistair Moffat and Justin Zobel
  • SciNUP: Natural Language User Interest Profiles for Scientific Literature Recommendation
    Mariam Arustashvili and Krisztian Balog
  • FoodNexus: Massive Food Knowledge for Recommender Systems
    Ludovico Boratto, Gianni Fenu, Mirko Marras, Giacomo Medda and Giovanni Zedda
  • pt-image-ir-dataset: An Image Retrieval Dataset in European Portuguese
    Rodrigo Duarte, António Branco, Hugo Proença and Ricardo Campos
  • CitiLink-Minutes: A Multilayer Annotated Dataset of Municipal Meeting Minutes
    Ricardo Campos, Ana Pacheco, Ana Fernandes, Inês Cantante, Rute Rebouças, Luís Filipe Cunha, José Isidro, José Pedro Evans, Miguel Marques, Rodrigo Batista, Evelin Amorim, Alípio Jorge, Nuno Guimarães, Sérgio Nunes, António Leal and Purificação Silvano
  • ClaimPT: A Portuguese Dataset of Annotated Claims in News Articles
    Ricardo Campos, Raquel Sequeira, Sara Nerea, Inês Cantante, Diogo Folques, Luís Filipe Cunha, João Canavilhas, António Branco, Alípio Jorge, Sérgio Nunes, Nuno Guimarães and Purificação Silvano
  • BioGraphletQA: Knowledge-Anchored Generation of Complex Question Answering Datasets
    Richard A. A. Jonker, Bárbara Maria Ribeiro de Abreu Martins and Sérgio Matos
14:30 – 16:00
Room A Full Papers
Full Papers 8: Recommendation Systems & LLMs
  • From What to Why: Thought-Space Recommendation with Small Language Models
    Prosenjit Biswas, Pervez Shaik, Abhinav Thorat, Ravi Kolla and Niranjan Pedanekar
  • Post-Training Denoising of User Profiles with LLMs in Collaborative Filtering Recommendation
    Ervin Dervishaj, Maria Maistro, Tuukka Ruotsalo and Christina Lioma
  • PromptHG: Prompt-Enhanced Heterogeneous Graph for Personalized News Recommendation
    Dang Kieu, Delvin Ce Zhang, Minh-Duc Nguyen, Qiang Wu, Min Xu and Dung D. Le
  • Interplay: Training Independent Simulators for Reference-Free Conversational Recommendation
    Jerome Ramos, Feng Xia, Xi Wang, Shubham Chatterjee, Xiao Fu, Hossein A. Rahmani and Aldo Lipani
  • Improving Conversational Recommendation with Contextual Adaptation of External Recommenders and LLM-Based Reranking
    Chuang Li, Yang Deng, Weida Liang, Hengchang Hu, See-Kiong Ng, Min-Yen Kan and Haizhou Li
Room B
- No session -
Room C Resource
Resource 3: Evaluation Tooling for Retrieval and RecSys
  • CoRECT: A Framework for Evaluating Embedding Compression Techniques at Scale
    Laura Caspari, Michael Dinzinger, Kanishka Ghosh Dastidar, Christofer Fellicious, Jelena Mitrović and Michael Granitzer
  • GREAT: Group Recommender Evaluation and Analysis Tool
    Ariel Smith, David Contreras, Maria Salamo and Ludovico Boratto
  • Evaluating the Efficiency and Effectiveness of Learned Sparse Retrieval with the lsr_benchmark
    Maik Fröbe, Ferdinand Schlatt, Cosimo Rulli, Tim Hagen, Jan Heinrich Merker, Gijs Hendriksen, Carlos Lassance, Franco Maria Nardini, Rossano Venturini and Martin Potthast
  • An Open SERP Mining Infrastructure for the Archive Query Log
    Jan Heinrich Merker, Simon Ruth, Harrisen Scells and Martin Potthast
  • RoutIR: Fast Serving of Retrieval Pipelines for Retrieval-Augmented Generation
    Eugene Yang, Andrew Yates, Dawn Lawrie, James Mayfield and Trevor Adriaanse
16:00 – 16:30
Closing Session (plenary)
74 hits