paper-with-me

홈 › Papers

Retrieving Contextual Information for Long-Form Question Answering using Weak Supervision

2024-10-11 · Philipp Christmann, Svitlana Vakulenko, Ionut Teodor Sorodoc, Bill Byrne, Adrià De Gispert

Long-form question answering (LFQA) aims at generating in-depth answers to end-user questions, providing relevant information beyond the direct answer. However, existing retrievers are typically optimized towards information that directly targets the question, missing out on such contextual information. Furthermore, there is a lack of training data for relevant context. To this end, we propose and compare different weak supervision techniques to optimize retrieval for contextual information. Experiments demonstrate improvements on the end-to-end QA performance on ASQA, a dataset for long-form question answering. Importantly, as more contextual information is retrieved, we improve the relevant page recall for LFQA by 14.7% and the groundedness of generated long-form answers by 12.5%. Finally, we show that long-form answers often anticipate likely follow-up questions, via experiments on a conversational QA dataset.

📄 PDF Abstract BibTeX arXiv:2410.08623

Code (0)

등록된 구현이 없습니다.

Tasks

FormLong Form Question AnsweringQuestion AnsweringRetrieval

Similar Papers 제목 키워드 기반

VL-MemKnG: Hybrid Memory with a Spatio-Temporal Knowledge Graph for Question Answering over Long Egocentric Navigation Trajectories

2026-06-15 · Svetlana Lukina, Mohamad Al Mdfaa, Gloria Haro, Sergey Zagoruyko 외 arxiv

Answering navigation-relevant questions over long egocentric videos requires retrieving and organizing evidence distributed across distant temporal moments while maintaining spatial and contextual consistency. Although l…

Video Question AnsweringKnowledge Graphs

OmniQuery: Contextually Augmenting Captured Multimodal Memory to Enable Personal Question Answering

2024-09-12 · Jiahao Nick Li, Zhuohao Jerry Zhang, Jiaju Ma

People often capture memories through photos, screenshots, and videos. While existing AI-based tools enable querying this data using natural language, they only support retrieving individual pieces of information like ce…

Language ModelingLanguage ModellingLarge Language ModelQuestion Answering+1

When Retriever-Reader Meets Scenario-Based Multiple-Choice Questions

2021-08-31 · Findings (EMNLP) 2021 11 · Zixian Huang, Ao Wu, Yulin Shen, Gong Cheng 외

Scenario-based question answering (SQA) requires retrieving and reading paragraphs from a large corpus to answer a question which is contextualized by a long scenario description. Since a scenario contains both keyphrase…

Multiple-choiceQuestion AnsweringRetrieval

DCG-SQL: Enhancing In-Context Learning for Text-to-SQL with Deep Contextual Schema Link Graph

2025-05-26 · Jihyung Lee, Jin-Seop Lee, Jaehoon Lee, YunSeok Choi 외

Text-to-SQL, which translates a natural language question into an SQL query, has advanced with in-context learning of Large Language Models (LLMs). However, existing methods show little improvement in performance compare…

In-Context LearningText to SQLText-To-SQL

Improving Contextual Faithfulness of Large Language Models via Retrieval Heads-Induced Optimization

2025-01-23 · Lei Huang, Xiaocheng Feng, Weitao Ma, Yuchun Fan 외

Ensuring contextual faithfulness in retrieval-augmented large language models (LLMs) is crucial for building trustworthy information-seeking systems, particularly in long-form question-answering (LFQA) scenarios. In this…

Long Form Question AnsweringQuestion AnsweringRetrieval