Reasoning-intensive retrieval requires deep semantic inference beyond surface-level keyword matching, posing a challenge for current LLM-based rerankers limited by context constraints and order sensitivity.We propose BracketRank, a framework that treats document reranking as a reasoning-driven competitive tournament.Our approach introduces three key innovations: (1) adaptive grouping based on model context limits, (2) reasoning-enhanced prompts that mandate step-by-step relevance explanations, and (3) a bracket-style elimination structure with winner and loser tracks.This design ensures robust document advancement while enabling parallel processing across competition stages.Evaluation on the BRIGHT reasoning benchmark shows that BracketRank achieves 26.56 nDCG@10, significantly outperforming state-of-the-art baselines including RankGPT-4 (17.0) and Rank-R1-14B (20.5).On TREC datasets, BracketRank achieves 77.90 nDCG@5 on DL 19 and 75.85 nDCG@5 on DL 20, exceeding all baselines, establishing that explicit reasoning within competitive elimination is a powerful paradigm for complex, multi-step retrieval tasks. 1

Estimating question difficulty is a critical component in evaluating and improving large language models (LLMs) for question answering (QA).Existing approaches often rely on readability formulas, retrieval-based signals, or popularity statistics, which may not fully capture the reasoning challenges posed to modern LLMs.In this paper, we introduce Q-DAPS (Question Difficulty based on Answer Plausibility Scores) method, a novel approach that estimates question difficulty by computing the entropy of plausibility scores over candidate answers.We systematically evaluate Q-DAPS across four prominent QA datasets-TriviaQA, NQ, MuSiQue, and QASC-demonstrating that it consistently outperforms baselines.Moreover, Q-DAPS shows strong robustness across hyperparameter variations and question types.Extensive ablation studies further show that Q-DAPS remains robust across different plausibility estimation paradigms, model sizes, and realistic settings.Human evaluations further confirm strong alignment between Q-DAPS 's difficulty estimates and human judgments of question difficulty.Overall, Q-DAPS provides an interpretable, scalable, and bias-resilient approach to question difficulty estimation in modern QA systems.

Bhawna Piryani, Abdelrahman Abdallah, Jamshid Mozafari, Avishek Anand, Adam Jatowt. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2026.

While Large Language Models (LLMs) are widely used in open-domain Question Answering (QA), their ability to handle inferential questions—where answers must be derived rather than directly retrieved—remains still underexplored. This study investigates how the structure and quality of passages influence LLM performance on such questions. We focus on convergence, a measure of how effectively sentences (hints) eliminate incorrect answers, as a criterion for constructing passages. Using subsets of the TriviaHG dataset, we form passages by combining sentences with varying convergence levels and evaluate six LLMs of different sizes and architectures. Our results show that passages built from higher-convergence sentences lead to substantially better answer accuracy than those selected by cosine similarity, indicating that convergence captures meaningful relevance for inferential reasoning. Additionally, ordering sentences by descending convergence slightly improves performance, suggesting that LLMs tend to prioritize earlier, information-rich cues. These findings highlight convergence as a practical signal for guiding passage construction and analyzing inferential reasoning behavior in LLMs.

Large language models (LLMs) exhibit systematic preferences for well-known entities, a phenomenon often attributed to popularity bias. However, the extent to which these preferences reflect real-world popularity versus statistical exposure during pretraining remains unclear, largely due to the inaccessibility of most training corpora. We provide the first direct, large-scale analysis of popularity bias grounded in fully observable pretraining data. Leveraging the open OLMo models and their complete pretraining corpus, Dolma, we compute precise entity-level exposure statistics across 7.4 trillion tokens. We analyze 2,000 entities spanning five types (Person, Location, Organization, Art, Product) and compare pretraining exposure against Wikipedia pageviews and two elicited LLM popularity signals: direct scalar estimation and pairwise comparison. Our results show that pretraining exposure strongly correlates with Wikipedia popularity, validating exposure as a meaningful proxy for real-world salience during the training period. More importantly, we find that LLM popularity judgments align more closely with exposure than with Wikipedia, especially when elicited via pairwise comparisons. This alignment is strongest for larger models and persists in the long tail, where Wikipedia popularity becomes unreliable. Overall, our findings demonstrate that popularity priors in LLMs are primarily shaped by pretraining statistics rather than external popularity signals, offering concrete evidence that data exposure plays a central role in driving popularity bias.

Information continuously evolves over time. Because of this dynamic nature, time becomes a fundamental dimension that shapes how we extract, retrieve, interpret, and reason about knowledge. As information systems are constantly updated, models must determine not only what is relevant, but also when that information is valid. This tutorial provides a structured and in-depth overview of the complete temporal information access pipeline: Temporal Information Extraction (TIE), Temporal Information Retrieval (TIR), and Temporal Question Answering (TQA). We examine the progression of temporal methods from early rule-based extraction and probabilistic retrieval to contemporary transformer-based and large language model (LLM) architectures. Participants gain a solid understanding of the core principles underlying the identification and normalization of time expressions, time-aware document ranking, and temporal reasoning in retrieval-augmented generation (RAG). The tutorial concludes with a discussion of open challenges and future research directions aimed at building AI systems that are temporally aware, robust, and adaptive. By connecting classical extraction and IR foundations with modern LLM-based reasoning, this tutorial presents a cohesive and up-to-date perspective on temporal information systems.

Temporal information is crucial for information retrieval, yet most dense retrieval systems focus exclusively on semantic similarity while neglecting temporal alignment between queries and documents. We propose TempRetriever, a lightweight framework that explicitly incorporates temporal information into dense passage retrieval through learned fusion techniques. Unlike existing approaches requiring extensive architectural modifications or specialized pre-training, TempRetriever enhances standard dense retrievers by combining semantic embeddings with temporal representations using four fusion strategies: Feature Stacking, Vector Summation, Relative Embeddings, and Element-Wise Interaction. Our approach introduces a learned temporal encoder and time-based negative sampling strategy to address temporal misalignment during training. We evaluate TempRetriever on three temporal question answering datasets (ArchivalQA, ChroniclingAmericaQA, NobelPrize) spanning altogether years from 1800 to 2022. TempRetriever achieves substantial improvements over standard DPR: 6.86% on ArchivalQA (Recall@1) and 4.40% on ChroniclingAmericaQA (Recall@1). Our method also outperforms state-of-the-art temporal retrieval systems, obtaining 9.62% improvement over BiTimeBERT and 5.16% over TS-Retriever. Notably, TempRetriever's fusion techniques can enhance existing temporal methods, improving BiTimeBERT by 5.12% and TS-Retriever by 6.17%, demonstrating modularity and practical value. Zero-shot evaluation confirms strong generalization across domains, and integration with retrieval-augmented generation shows consistent end-to-end improvements.

Evaluating the quality of retrieval-augmented generation (RAG) and document reranking systems remains challenging due to the lack of scalable, user-centric, and multi-perspective evaluation tools. We introduce RankArena, a unified platform for comparing and analysing the performance of retrieval pipelines, rerankers, and RAG systems using structured human and LLM-based feedback as well as for collecting such feedback. RankArena supports multiple evaluation modes: direct reranking visualisation, blind pairwise comparisons with human or LLM voting, supervised manual document annotation, and end-to-end RAG answer quality assessment. It captures fine-grained relevance feedback through both pairwise preferences and full-list annotations, along with auxiliary metadata such as movement metrics, annotation time, and quality ratings. The platform also integrates LLM-as-a-judge evaluation, enabling comparison between model-generated rankings and human ground truth annotations. All interactions are stored as structured evaluation datasets that can be used to train rerankers, reward models, judgment agents, or retrieval strategy selectors. Our platform is publicly available at https://rankarena.ngrok.io/, and the Demo video is provided. https://youtu.be/jIYAP4PaSSI.

Optical Character Recognition (OCR) plays a crucial role in digitizing historical and multilingual documents, yet OCR errors - imperfect extraction of text, including character insertion, deletion, and substitution can significantly impact downstream tasks like question-answering (QA). In this work, we conduct a comprehensive analysis of how OCR-induced noise affects the performance of Multilingual QA Systems. To support this analysis, we introduce a multilingual QA dataset MultiOCR-QA, comprising 50K question-answer pairs across three languages, English, French, and German. The dataset is curated from OCR-ed historical documents, which include different levels and types of OCR noise. We then evaluate how different state-of-the-art Large Language Models (LLMs) perform under different error conditions, focusing on three major OCR error types. Our findings show that QA systems are highly prone to OCR-induced errors and perform poorly on noisy OCR text. By comparing model performance on clean versus noisy texts, we provide insights into the limitations of current approaches and emphasize the need for more noise-resilient QA systems in historical digitization contexts.

This paper presents DynRank, a novel framework for enhancing passage retrieval in open-domain question-answering systems through dynamic zero-shot question classification. Traditional approaches rely on static prompts and pre-defined templates, which may limit model adaptability across different questions and contexts. In contrast, DynRank introduces a dynamic prompting mechanism, leveraging a pre-trained question classification model that categorizes questions into fine-grained types. Based on these classifications, contextually relevant prompts are generated, enabling more effective passage retrieval. We integrate DynRank into existing retrieval frameworks and conduct extensive experiments on multiple QA benchmark datasets.

Large Language Models (LLMs) are revolutionizing information retrieval, with chatbots becoming an important source for answering user queries. As by their design, LLMs prioritize generating correct answers, the value of highly plausible yet incorrect answers (candidate answers) tends to be overlooked. However, such answers can still prove useful, for example, they can play a crucial role in tasks like Multiple-Choice Question Answering (MCQA) and QA Robustness Assessment (QARA). Existing QA datasets primarily focus on correct answers without explicit consideration of the plausibility of other candidate answers, limiting opportunity for more nuanced evaluations of models. To address this gap, we introduce PlausibleQA, a large-scale dataset comprising 10,000 questions and 100,000 candidate answers, each annotated with plausibility scores and justifications for their selection. Additionally, the dataset includes 900,000 justifications for pairwise comparisons between candidate answers, further refining plausibility assessments. We evaluate PlausibleQA through human assessments and empirical experiments, demonstrating its utility in MCQA and QARA analysis. Our findings show that plausibility-aware approaches are effective for MCQA distractor generation and QARA. We release PlausibleQA as a resource for advancing QA research and enhancing LLM performance in distinguishing plausible distractors from correct answers.

Question answering (QA) and Machine Reading Comprehension (MRC) tasks have significantly advanced in recent years due to the rapid development of deep learning techniques and, more recently, large language models. At the same time, many benchmark datasets have become available for QA and MRC tasks. However, most existing large-scale benchmark datasets have been created predominantly using synchronous document collections like Wikipedia or the Web. Archival document collections, such as historical newspapers, contain valuable information from the past that is still not widely used to train large language models. To further contribute to advancing QA and MRC tasks and to overcome the limitation of previous datasets, we introduce ChroniclingAmericaQA, a large-scale temporal QA dataset with 487K question-answer pairs created based on the historical newspaper collection Chronicling America. Our dataset is constructed from a subset of the Chronicling America newspaper collection spanning 120 years. One of the significant challenges for utilizing digitized historical newspaper collections is the low quality of OCR text. Therefore, to enable realistic testing of QA models, our dataset can be used in three different ways: answering questions from raw and noisy content, answering questions from cleaner, corrected version of the content, as well as answering questions from scanned images of newspaper pages. This and the fact that ChroniclingAmericaQA spans the longest time period among available QA datasets make it quite a unique and useful resource.