English
Related papers

Related papers: Mitigating False-Negative Contexts in Multi-docume…

200 papers

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…

Computation and Language · Computer Science 2022-11-11 Ella Neeman , Roee Aharoni , Or Honovich , Leshem Choshen , Idan Szpektor , Omri Abend

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…

Machine Learning · Computer Science 2025-06-17 Peter Carragher , Abhinand Jha , R Raghav , Kathleen M. Carley

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…

Computation and Language · Computer Science 2023-05-25 Avi Caciularu , Matthew E. Peters , Jacob Goldberger , Ido Dagan , Arman Cohan

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…

Computation and Language · Computer Science 2024-10-02 Jayetri Bardhan , Bushi Xiao , Daisy Zhe Wang

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…

Computation and Language · Computer Science 2024-06-18 Tianhua Zhang , Kun Li , Hongyin Luo , Xixin Wu , James Glass , Helen Meng

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…

Artificial Intelligence · Computer Science 2026-03-18 Trishita Dhara , Siddhesh Sheth

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…

Computation and Language · Computer Science 2026-02-26 Chenyu Lin , Yilin Wen , Du Su , Hexiang Tan , Fei Sun , Muhan Chen , Chenfu Bao , Zhonghou Lyu

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…

Computation and Language · Computer Science 2026-05-28 Yikai Zhu , Kunfeng Chen , Qihuang Zhong , Juhua Liu , Bo Du

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…

Information Retrieval · Computer Science 2025-09-17 Zihan Wang , Zihan Liang , Zhou Shao , Yufei Ma , Huangyu Dai , Ben Chen , Lingtao Mao , Chenyi Lei , Yuqing Ding , Han Li

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…

Computation and Language · Computer Science 2023-10-05 Yuxuan Sun , Kai Zhang , Yu Su

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…

Computation and Language · Computer Science 2025-09-26 Zeinab Sadat Taghavi , Ali Modarressi , Yunpu Ma , Hinrich Schütze

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…

Machine Learning · Computer Science 2026-04-22 Rapheal Huang , Weilong Guo

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…

Computation and Language · Computer Science 2026-02-23 Amine Kobeissi , Philippe Langlais

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,…

Computation and Language · Computer Science 2018-10-02 Jinhyuk Lee , Seongjun Yun , Hyunjae Kim , Miyoung Ko , Jaewoo Kang

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…

Computation and Language · Computer Science 2024-07-08 João Rodrigues , António Branco

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…

Computation and Language · Computer Science 2018-04-27 Shuohang Wang , Mo Yu , Jing Jiang , Wei Zhang , Xiaoxiao Guo , Shiyu Chang , Zhiguo Wang , Tim Klinger , Gerald Tesauro , Murray Campbell

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…

Computation and Language · Computer Science 2024-04-24 Kuicai Dong , Derrick Goh Xin Deik , Yi Quan Lee , Hao Zhang , Xiangyang Li , Cong Zhang , Yong Liu

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…

Computation and Language · Computer Science 2026-05-15 Zeyu Huang , Adhiguna Kuncoro , Qixuan Feng , Jiajun Shen , Lucio Dery , Arthur Szlam , Marc'Aurelio Ranzato

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…

Computation and Language · Computer Science 2024-02-14 Sohan Patnaik , Heril Changwal , Milan Aggarwal , Sumit Bhatia , Yaman Kumar , Balaji Krishnamurthy
‹ Prev 1 4 5 6 7 8 10 Next ›