Related papers: Mitigating False-Negative Contexts in Multi-docume…
Question answering models commonly have access to two sources of "knowledge" during inference time: (1) parametric knowledge - the factual knowledge encoded in the model weights, and (2) contextual knowledge - external knowledge (e.g., a…
Large Language Models (LLMs) demonstrate remarkable capabilities in question answering (QA), but metrics for assessing their reliance on memorization versus retrieval remain underdeveloped. Moreover, while finetuned models are…
The integration of multi-document pre-training objectives into language models has resulted in remarkable improvements in multi-document downstream tasks. In this work, we propose extending this idea by pre-training a generic multi-document…
Retrieval-Augmented Generation (RAG) systems face challenges with complex, multihop questions, and agentic frameworks such as Search-R1 (Jin et al., 2025), which operates iteratively, have been proposed to address these complexities.…
Question answering (QA) over tables and text has gained much popularity over the years. Multi-hop table-text QA requires multiple hops between the table and text, making it a challenging QA task. Although several works have attempted to…
Query rewriting is a crucial technique for passage retrieval in open-domain conversational question answering (CQA). It decontexualizes conversational queries into self-contained questions suitable for off-the-shelf retrievers. Existing…
Large language models are increasingly deployed in settings where relevant information is embedded within long and noisy contexts. Despite this, robustness to growing context length remains poorly understood across different question…
Retrieval-augmented generation (RAG) improves performance on knowledge-intensive tasks but can be derailed by wrong, irrelevant, or conflicting retrieved text, causing models to rely on inaccurate evidence and cascade errors. We propose…
Retrieval-augmented generation (RAG) has emerged as a promising paradigm for enhancing large language models (LLMs) on multi-hop question answering (QA), which requires reasoning over evidence from multiple documents. Current multi-hop RAG…
Retrieval-Augmented Generation (RAG) has emerged as a promising approach to address key limitations of Large Language Models (LLMs), such as hallucination, outdated knowledge, and lacking reference. However, current RAG frameworks often…
Multimodal information extraction (MIE) aims to extract structured information from unstructured multimedia content. Due to the diversity of tasks and settings, most current MIE models are task-specific and data-intensive, which limits…
Retrieval systems are central to many NLP pipelines, but often rely on surface-level cues such as keyword overlap and lexical semantic similarity. To evaluate retrieval beyond these shallow signals, recent benchmarks introduce…
Large Language Models (LLMs) excel at reasoning, traditionally requiring high-quality large-scale data and extensive training. Recent works reveal a very appealing Less-Is-More phenomenon where very small, carefully curated high-quality…
Retrieval-augmented generation is increasingly used for financial question answering over long regulatory filings, yet reliability depends on retrieving the exact context needed to justify answers in high stakes settings. We study a…
Recently, open-domain question answering (QA) has been combined with machine comprehension models to find answers in a large knowledge source. As open-domain QA requires retrieving relevant documents from text corpora to answer questions,…
Retrieval-augmented generation resorts to content retrieved from external sources in order to leverage the performance of large language models in downstream tasks. The excessive volume of retrieved content, the possible dispersion of its…
A popular recent approach to answering open-domain questions is to first search for question-related passages and then apply reading comprehension models to extract answers. Existing methods usually extract answers from single passages…
Long document question answering (DocQA) aims to answer questions from long documents over 10k words. They usually contain content structures such as sections, sub-sections, and paragraph demarcations. However, the indexing methods of long…
Most existing large language models (LLMs) are expensive to adapt after deployment, especially when a task requires newly produced information or niche domain knowledge. Recent work has shown that, by manipulating and optimizing their…
Table understanding capability of Large Language Models (LLMs) has been extensively studied through the task of question-answering (QA) over tables. Typically, only a small part of the whole table is relevant to derive the answer for a…