Related papers: Backtracing: Retrieving the Cause of the Query

Recent advances in retrieval-augmented generation (RAG) furnish large language models (LLMs) with iterative retrievals of relevant information to handle complex multi-hop questions. These methods typically alternate between LLM reasoning…

Augmenting Large Language Models (LLMs) with information retrieval capabilities (i.e., Retrieval-Augmented Generation (RAG)) has proven beneficial for knowledge-intensive tasks. However, understanding users' contextual search intent when…

Understanding how language models carry out long-horizon reasoning remains an open challenge. Existing interpretability methods often highlight tokens correlated with an answer, but rarely reveal where consequential reasoning turns occur,…

Information retrieval aims to find information that meets users' needs from the corpus. Different needs correspond to different IR tasks such as document retrieval, open-domain question answering, retrieval-based dialogue, etc., while they…

Explaining why a language model produces a particular output requires local, input-level explanations. Existing methods uncover global capability circuits (e.g., indirect object identification), but not why the model answers a specific…

Generative retrieval (GR) reformulates information retrieval (IR) by framing it as the generation of document identifiers (docids), thereby enabling end-to-end optimization and seamless integration with generative language models (LMs).…

The longitudinal evaluation of retrieval systems aims to capture how information needs and documents evolve over time. However, classical Cranfield-style retrieval evaluations only consist of a static set of queries and documents and…

Large language models require updates to remain up-to-date or adapt to new domains by fine-tuning them with new documents. One key is memorizing the latest information in a way that the memorized information is extractable with a query…

Information Retrieval (IR) systems are designed to deliver relevant content, but traditional systems may not optimize rankings for fairness, neutrality, or the balance of ideas. Consequently, IR can often introduce indexical biases, or…

Large Language Models have brought a radical change in the process of remote learning students, among other aspects of educative activities. Current retrieval of remote learning resources lacks depth in contextual meaning that provides…

Generative Retrieval (GR) is an emerging paradigm in information retrieval that leverages generative models to directly map queries to relevant document identifiers (DocIDs) without the need for traditional query processing or document…

Traditional code search engines often do not perform well with natural language queries since they mostly apply keyword matching. These engines thus require carefully designed queries containing information about programming APIs for code…

Document reranking is a key component in information retrieval (IR), aimed at refining initial retrieval results to improve ranking quality for downstream tasks. Recent studies--motivated by large reasoning models (LRMs)--have begun…

With the growing popularity of LLM agents and RAG, it has become increasingly important to retrieve documents that are essential for solving a task, even when their connection to the task is indirect or implicit. Addressing this problem…

The DRAGUN Track at TREC 2025 targets the growing need for effective support tools that help users evaluate the trustworthiness of online news. We describe the UR_Trecking system submitted for both Task 1 (critical question generation) and…

In the relatively short history of machine learning, the subtle balance between engineering and theoretical progress has been proved critical at various stages. The most recent wave of AI has brought to the IR community powerful techniques,…

Information retrieval systems are crucial for enabling effective access to large document collections. Recent approaches have leveraged Large Language Models (LLMs) to enhance retrieval performance through query augmentation, but often rely…

OpenIIR runs hundreds of LLM-driven personas as parameterised, reproducible IR research experiments. Researchers configure agents across four kinds of multi-agent study (deliberative panels, social platforms, curated recommender feeds, and…

Argument retrieval is the task of finding relevant arguments for a given query. While existing approaches rely solely on the semantic alignment of queries and arguments, this first shared task on perspective argument retrieval incorporates…

Delivering high-quality content is crucial for effective reading comprehension and successful learning. Ensuring educational materials are interpreted as intended by their authors is a persistent challenge, especially with the added…