Long-Context Long-Form Question Answering for Legal Domain

2026-02-06

AI Summary

This work addresses the significant challenges posed by long-form question answering in the legal domain, where documents exhibit complex structures, specialized terminology, and answers often span multiple pages requiring comprehensive articulation. To tackle these issues, we propose an end-to-end legal QA framework that integrates document layout parsing, domain-specific term decomposition, cross-page information retrieval, and long-form text generation, effectively modeling the relationships between main text and footnotes while synthesizing dispersed evidence. To evaluate answer completeness, we introduce a recall-based coverage metric. Extensive experiments on an expert-constructed legal QA dataset demonstrate that our approach substantially improves both the accuracy and comprehensiveness of generated long-form answers.

Technology Category

• Natural Language Processing: Question Answering
• Machine Learning: Large Multimodal Models (LMMs)
• Application Domains: Humanities & Computational Social Science

Application Category

• Search and Retrieval-Augmented AI: Web question answering
• Web Mining and Content Analysis: Community question answering
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

Abstract

Legal documents have complex document layouts involving multiple nested sections, lengthy footnotes and further use specialized linguistic devices like intricate syntax and domain-specific vocabulary to ensure precision and authority. These inherent characteristics of legal documents make question answering challenging, and particularly so when the answer to the question spans several pages (i.e. requires long-context) and is required to be comprehensive (i.e. a long-form answer). In this paper, we address the challenges of long-context question answering in context of long-form answers given the idiosyncrasies of legal documents. We propose a question answering system that can (a) deconstruct domain-specific vocabulary for better retrieval from source documents, (b) parse complex document layouts while isolating sections and footnotes and linking them appropriately, (c) generate comprehensive answers using precise domain-specific vocabulary. We also introduce a coverage metric that classifies the performance into recall-based coverage categories allowing human users to evaluate the recall with ease. We curate a QA dataset by leveraging the expertise of professionals from fields such as law and corporate tax. Through comprehensive experiments and ablation studies, we demonstrate the usability and merit of the proposed system.

Problem

• long-context
• long-form question answering
• legal documents
• complex document layout
• domain-specific vocabulary

Innovation

• long-context QA
• legal document understanding
• domain-specific vocabulary
• document layout parsing
• coverage metric