Scholarlink

<p>Legal Multi-Choice Question Answering (LMCQA) presents unique challenges due to the complexity and subtlety of legal reasoning. This paper presents DeAtt-LMCQA, a novel model that integrates the DeBERTa language model with attention mechanisms to mitigate classification bias and enhance performance in legal multiple-choice tasks. The system first uses BM25 to retrieve relevant legal articles for each question-option pair, grounding answer evaluation in authoritative legal content. It then encodes these triples via DeBERTa and employs a two-stage attention mechanism for semantic fusion and matching across articles, questions, and answer options. A binary classification strategy is adopted to assess each option independently, improving interpretability and robustness. Extensive experiments on the Judicial Examination Challenge - Question Answering (JEC-QA) dataset from China’s judicial examination demonstrate that DeAtt-LMCQA outperforms multiple strong baselines and achieves third place in the Challenge of AI in Law (CAIL) 2022 competition. Furthermore, it shows competitive advantages over several contemporary large language models in both accuracy and interpretability, highlighting its practical value in domain-specific legal question answering. Our code and model checkpoint are available at <a href="https://github.com/gbchen99/chatGPT_result/tree/main/source_code">https://github.com/gbchen99/chatGPT_result/tree/main/source_code</a>.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

DeAtt-LMCQA: a DeBERTa and attention based model of legal multi-choice question answering

  • 期刊论文

  • 发表日期：

    2026年4月9日

查看全文
  • Guibin Chen,
  • Xudong Luo,
  • Yanling Li,
  • Binxia Yang,
  • Junlin Zhu

摘要

Legal Multi-Choice Question Answering (LMCQA) presents unique challenges due to the complexity and subtlety of legal reasoning. This paper presents DeAtt-LMCQA, a novel model that integrates the DeBERTa language model with attention mechanisms to mitigate classification bias and enhance performance in legal multiple-choice tasks. The system first uses BM25 to retrieve relevant legal articles for each question-option pair, grounding answer evaluation in authoritative legal content. It then encodes these triples via DeBERTa and employs a two-stage attention mechanism for semantic fusion and matching across articles, questions, and answer options. A binary classification strategy is adopted to assess each option independently, improving interpretability and robustness. Extensive experiments on the Judicial Examination Challenge - Question Answering (JEC-QA) dataset from China’s judicial examination demonstrate that DeAtt-LMCQA outperforms multiple strong baselines and achieves third place in the Challenge of AI in Law (CAIL) 2022 competition. Furthermore, it shows competitive advantages over several contemporary large language models in both accuracy and interpretability, highlighting its practical value in domain-specific legal question answering. Our code and model checkpoint are available at https://github.com/gbchen99/chatGPT_result/tree/main/source_code.