Accepted Papers

In the online digital ecosystem, we are surrounded by distinct forms of information pollution, posing significant threats to both individuals and society as a whole. Just think of the recent riots in England and Wales which were triggered by deliberate misinformation. Other instances of false news, ...

Transformer-based cross-encoders, such as MonoT5, achieve state-of-the-art performance in several retrieval tasks. In particular, MonoT5 is based on a sequence-to-sequence architecture and trained on MS MARCO for passage re-ranking, where it predicts the relevance of a passage given an input query. ...

Off-policy evaluation (OPE) and optimization for learning to rank (LTR) leverage document placement probabilities to correct for the effects of various statistical biases, e.g., position bias. However, computing these propensities poses a challenge, as for most ranking models this requires iterating...

Validating user simulation is a difficult task due to the lack of established measures and benchmarks, which makes it challenging to assess whether a simulator accurately reflects real user behavior. As part of the Sim4IA Micro-Shared Task at the Sim4IA Workshop, SIGIR 2025, we present Sim4IA-Bench,...

Formula retrieval is an important topic in Mathematical Information Retrieval. We propose SSEmb, a novel embedding framework capable of capturing both structural and semantic features of formulas. Structurally, we employ Graph Contrastive Learning to encode formulas represented as Shared-substructur...

The increasing complexity of information access systems necessitates innovative evaluation methods beyond real-world user data, which is often biased, incomplete, or difficult to obtain due to privacy concerns. Simulation and synthetic data methods provide controlled and reproducible environments fo...

Large Language Models (LLMs) often struggle with temporal fact conflicts due to outdated or evolving information in their training data. Two recent studies with accompanying dataset report opposite conclusions on whether external context can effectively resolve such conflicts. DYNAMICQA evaluates ho...

The main objective of the CheckThat! lab is to advance the development of innovative technologies combating disinformation and manipulation efforts in online communication across a multitude of languages and platforms. Focusing on core tasks of the verification pipeline in earlier years, namely chec...

The IRAI workshop explores how information retrieval (IR) can promote accountability and integrity in public discourse and corporate commitments. It focuses on verifying forecasts, promises, and predictions using IR and NLP, bridging research and practice to foster transparency, responsible AI, and ...

We present ReFormeR, a pattern-guided approach for query reformulation. Instead of prompting a language model to generate reformulations of a query directly, ReFormeR first elicits short reformulation patterns from pairs of initial queries and empirically stronger reformulations, consolidates them i...

Using large language models (LLMs) to annotate relevance is an increasingly important problem in the information retrieval community. While some studies demonstrate that LLMs can achieve high user agreement with ground truth (human) judgments, other studies have argued for the opposite conclusion. T...

Music Cover Retrieval, also known as Version Identification, aims to recognize distinct renditions of the same underlying musical work, a task central to catalog management, copyright enforcement, and music retrieval. State-of-the-art approaches have largely focused on harmonic and melodic features,...

In conversational search, user simulation is an important method for evaluation and it offers three key benefits: (i) considering conversational interactions, (ii) avoiding user privacy issues, and (iii) reducing evaluation costs compared to online evaluation. However, most prior work has focused on...

2D Matryoshka training enables a single embedding model to produce sub-network representations across varying layers and embedding dimensions, offering flexibility under different computational and task constraints. However, its performance remains below that of individually trained models of compar...

Information retrieval evaluation often suffers from fragmented practices---varying dataset subsets, aggregation methods, and pipeline configurations---that undermine reproducibility and comparability, especially for foundation embedding models requiring robust out-of-domain performance. We introduce...

With the increasing use of AI, deepfakes are becoming an increasingly prevalent threat in today's world. At the same time, the performance of most detectors drops significantly when faced with unseen data, whereas generation models are improving, resulting in fewer artefacts. We examined deepfakes p...

We propose the second workshop on Scholarly Information Access (SCOLIA) to take place at ECIR 2026 as a half-day workshop. The workshop is building upon SCOLIA@ECIR 2025 and following up on the long series of the Bibliometric-enhanced Information Retrieval (BIR) workshops at ECIR. SCOLIA addresses r...

Conventional vision-based document retrievers operate at page-level granularity, compelling subsequent reranking models to process documents containing substantial irrelevant information. We introduce RerAnchor, a post-retrieval, OCR-free reranking module designed to address this limitation. At the ...

Retrieval models are key components of Retrieval-Augmented Generation (RAG) systems, which generate search queries, process the documents returned, and generate a response. RAG systems are often dynamic and may involve multiple rounds of retrieval. While many state-of-the-art retrieval methods are a...

The use of natural language (NL) user profiles in recommender systems offers greater transparency and user control compared to traditional representations. However, there is scarcity of large-scale, publicly available test collections for evaluating NL profile-based recommendation. To address this g...

Integrating heterogeneous modalities for effective information access remains a central challenge in Information Retrieval (IR), particularly in reader-aware summarization, where user perspectives must be incorporated alongside textual and multimedia content. In this work, we present a novel augment...

With the rapid proliferation of online sports journalism, extracting meaningful pre-game and post-game insights from articles is essential for enhancing user engagement and comprehension. In this paper, we address the task of automatically extracting such insights from articles published before and ...

Retrieval-augmented generation (RAG) systems promise factually grounded answers, yet evaluating their quality remains difficult. Automated metrics and LLM-as-judge approaches offer scalability but risk circularity, benchmark leakage, and loss of diversity. Human assessors, meanwhile, often struggle ...

For eight years, Text2Story has gathered researchers on narrative understanding, detecting, representing, and reasoning over stories in text. Recent progress and discussions have been driven by Transformers and Large Language Models (LLMs), which are increasingly central to the field and have reshap...

We propose the third International Workshop on Open Web Search (WOWS) at ECIR~2026 with two calls for contributions: The first call targets scientific contributions on collaborative search engine building, including crawling, deployment, evaluation, and use of the web as a resource by researchers an...