Accepted Papers

Modern representation learning increasingly relies on unsupervised and self-supervised methods trained on large-scale unlabeled data. While these approaches achieve impressive generalization across tasks and domains, evaluating embedding quality without labels remains an open challenge. In this work...

Dense retrieval is a promising approach for acquiring relevant context or world knowledge in open-domain natural language processing tasks and is now widely used in information retrieval applications. However, recent reports claim a broad preference for text generated by large language models (LLMs)...

"Uncertainty quantification has gained increasing importance in natural language processing (NLP), offering a conceptual and methodological framework to address critical issues such as hallucinations in the answers of LLMs, detection of low-quality responses, out-of-distribution detection, and reduc...

Assessing the validity of user simulators when used for the evaluation of information retrieval systems remains an open question, constraining their effective use and the reliability of simulation-based results. To address this issue, we conduct a comprehensive literature review with a particular fo...

Neural models have transformed Information Retrieval (IR) by enabling semantic search, representing queries and documents as dense embeddings in latent spaces. However, recent works indicate the contribution of single dimensions in these representations to ranking quality is uneven: some dimensions ...

The rapid advancement of Large Language Models (LLMs) has transformed conversational systems into practical tools used by millions. However, the nature and necessity of information retrieval in real-world conversations remain largely unexplored, as research has focused predominantly on traditional, ...

Despite the dramatic advances in Large Language Models (LLMs), traditional summarization benchmarks are critically saturated, failing to differentiate state-of-the-art models or reflect real-world user needs. Existing evaluation datasets suffer from fundamental constraints in instructional diversity...

Resources for simulation-based evaluation of conversational recommender systems (CRSs) are scarce. The UserSimCRS toolkit was introduced to address this gap. In this work, we present UserSimCRS v2, a significant upgrade aligning the toolkit with state-of-the-art research. Key extensions include an e...

Segmentation is a crucial prerequisite for effective and efficient information retrieval on websites, as it enables the structured interpretation of heterogeneous content. Recently, a novel dataset has been released that provides two complementary segmentation schemes: a broad functional segmentatio...

We present a workshop proposal on \textit{Conversational AI and Search for Complex Information Needs}. Recent advances in conversational systems have expanded research beyond generative dialogue and factoid question-answering tasks, towards addressing complex information needs and improving user exp...

Machine Translation (MT) plays a pivotal role in cross-lingual information access, public policy communication, and equitable knowledge dissemination. However, critical meaning errors, such as factual distortions, intent reversals, or biased translations, can undermine the reliability, fairness, and...

"This tutorial introduces mechanistic interpretability, a growing research area within the broader interpretability community that seeks to reverse-engineer model components to understand how neural models perform tasks. While this area has rapidly advanced in NLP, yielding insights into the inner w...

Retrieval-Augmented Generation systems depend on retrieving semantically relevant document chunks to support accurate, grounded outputs from large language models. In structured and repetitive corpora such as regulatory filings, chunk similarity alone often fails to distinguish between documents wit...

Generative search engines are reshaping information access by replacing traditional ranked lists with synthesized answers and references. In parallel, with the growth of Web3 platforms, incentive-driven creator ecosystems have become an essential part of how projects build visibility and community b...

Large Language Models (LLMs) enhanced with Retrieval-Augmented Generation (RAG) have achieved substantial improvements in accuracy by grounding their responses in external documents that are relevant to the user's query. However, relatively little work has investigated the impact of RAG in terms of ...

This paper introduces XProvence, a multilingual zero-cost context pruning model for Retrieval-Augmented Generation (RAG), supporting 100+ languages. Motivated by the growing use of RAG systems across diverse languages, we explore several strategies to generalize the Provence framework--which first i...