paper-with-me

홈 › Papers

KRAG Framework for Enhancing LLMs in the Legal Domain

2024-10-10 · Nguyen Ha Thanh, Ken Satoh

This paper introduces Knowledge Representation Augmented Generation (KRAG), a novel framework designed to enhance the capabilities of Large Language Models (LLMs) within domain-specific applications. KRAG points to the strategic inclusion of critical knowledge entities and relationships that are typically absent in standard data sets and which LLMs do not inherently learn. In the context of legal applications, we present Soft PROLEG, an implementation model under KRAG, which uses inference graphs to aid LLMs in delivering structured legal reasoning, argumentation, and explanations tailored to user inquiries. The integration of KRAG, either as a standalone framework or in tandem with retrieval augmented generation (RAG), markedly improves the ability of language models to navigate and solve the intricate challenges posed by legal texts and terminologies. This paper details KRAG's methodology, its implementation through Soft PROLEG, and potential broader applications, underscoring its significant role in advancing natural language understanding and processing in specialized knowledge domains.

📄 PDF Abstract BibTeX arXiv:2410.07551

Code (0)

등록된 구현이 없습니다.

Tasks

Legal ReasoningNatural Language UnderstandingNavigateRAGRetrieval-augmented Generation

Similar Papers 제목 키워드 기반

RankRAG: Unifying Context Ranking with Retrieval-Augmented Generation in LLMs

2024-07-02 · Yue Yu, Wei Ping, Zihan Liu, Boxin Wang 외

Large language models (LLMs) typically utilize the top-k contexts from a retriever in retrieval-augmented generation (RAG). In this work, we propose a novel instruction fine-tuning framework RankRAG, which instruction-tu…

Answer GenerationQuestion AnsweringRAGRetrieval+1

Large Language Models Meet Legal Artificial Intelligence: A Survey

2025-09-12 · Zhitian Hou, Zihan Ye, Nanli Zeng, Tianyong Hao 외 arxiv

Large Language Models (LLMs) have significantly advanced the development of Legal Artificial Intelligence (Legal AI) in recent years, enhancing the efficiency and accuracy of legal tasks. To advance research and applicat…

Continual Pre-Training is (not) What You Need in Domain Adaption

2025-04-18 · Pin-Er Chen, Da-Chen Lian, Shu-Kai Hsieh, Sieh-Chuen Huang 외

The recent advances in Legal Large Language Models (LLMs) have transformed the landscape of legal research and practice by automating tasks, enhancing research precision, and supporting complex decision-making processes.…

Decision MakingDomain AdaptationLegal Reasoning

Knowledge Graph-Assisted LLM Post-Training for Enhanced Legal Reasoning

2026-01-20 · Dezhao Song, Guglielmo Bonifazi, Frank Schilder, Jonathan Richard Schwarz arxiv

LLM post-training has primarily relied on large text corpora and human feedback, without capturing the structure of domain knowledge. This has caused models to struggle dealing with complex reasoning tasks, especially fo…

Legal Reasoning

Enabling Discriminative Reasoning in LLMs for Legal Judgment Prediction

2024-07-02 · Chenlong Deng, Kelong Mao, Yuyao Zhang, Zhicheng Dou

Legal judgment prediction is essential for enhancing judicial efficiency. In this work, we identify that existing large language models (LLMs) underperform in this domain due to challenges in understanding case complexit…

Prediction