Pith. sign in

REVIEW 18 cited by

DISC-LawLLM: Fine-tuning Large Language Models for Intelligent Legal Services

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2309.11325 v2 pith:IQO44QHJ submitted 2023-09-20 cs.CL

Shengbin Yue , Wei Chen , Siyuan Wang , Bingxuan Li , Chenchen Shen , Shujun Liu , Yuxuan Zhou , Yao Xiao
show 3 more authors
Song Yun Xuanjing Huang Zhongyu Wei
This is my paper
classification cs.CL
keywords legaldisc-lawllmintelligentllmsmodelsdisc-law-evalfine-tuninglanguage
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

We propose DISC-LawLLM, an intelligent legal system utilizing large language models (LLMs) to provide a wide range of legal services. We adopt legal syllogism prompting strategies to construct supervised fine-tuning datasets in the Chinese Judicial domain and fine-tune LLMs with legal reasoning capability. We augment LLMs with a retrieval module to enhance models' ability to access and utilize external legal knowledge. A comprehensive legal benchmark, DISC-Law-Eval, is presented to evaluate intelligent legal systems from both objective and subjective dimensions. Quantitative and qualitative results on DISC-Law-Eval demonstrate the effectiveness of our system in serving various users across diverse legal scenarios. The detailed resources are available at https://github.com/FudanDISC/DISC-LawLLM.

Discussion (0). Sign in to comment.

Forward citations

Cited by 18 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. LegalWorld: A Life-Cycle Interactive Environment for Legal Agents

    cs.CL 2026-06 unverdicted novelty 7.0 of 10

    LegalWorld is a life-cycle interactive environment modeling Chinese civil litigation as five causally connected stages grounded in 75,309 judgments, paired with LongJud-Bench for cross-stage agent evaluation.

  2. TaxPraBen: A Scalable Benchmark for Structured Evaluation of LLMs in Chinese Real-World Tax Practice

    cs.CL 2026-04 unverdicted novelty 7.0 of 10

    TaxPraBen is a new benchmark with 14 datasets and a structured evaluation method for measuring LLM performance on Chinese real-world tax tasks and scenarios.

  3. VLegal-Bench: Cognitively Grounded Benchmark for Vietnamese Legal Reasoning of Large Language Models

    cs.CL 2025-12 conditional novelty 7.0 of 10

    VLegal-Bench supplies 10,450 expert-validated samples for evaluating LLMs on Vietnamese legal questions, retrieval, multi-step reasoning, and scenario solving.

  4. LexRel: Benchmarking Legal Relation Extraction for Chinese Civil Cases

    cs.CL 2025-12 unverdicted novelty 7.0 of 10

    LexRel introduces a hierarchical legal relation schema and expert benchmark for Chinese civil cases, exposing LLM limitations and downstream gains from explicit relation knowledge.

  5. NormWorlds-CF: Solver-Verified Counterfactual Normative Reasoning with Metamorphic-Relation GRPO

    cs.CL 2026-07 conditional novelty 6.5 of 10

    Solver-verified NormWorlds-CF and MR-GRPO show that answer-only training is an unsafe proxy and that class-conditioned metamorphic rewards improve balanced counterfactual change structure.

  6. NormWorlds-CF: Solver-Verified Counterfactual Normative Reasoning with Metamorphic-Relation GRPO

    cs.CL 2026-07 conditional novelty 6.0 of 10

    NormWorlds-CF provides solver-verified normative reasoning tasks without LLM judges; answer-only RL saturates verdicts but not falsification, and class-conditioned GRPO improves some structural change fields.

  7. Which Changes Matter? Towards Trustworthy Legal AI via Relevance-Sensitive Evaluation and Solver-Grounded Reasoning

    cs.AI 2026-05 unverdicted novelty 6.0 of 10

    The work introduces a should-change/should-not-change evaluation suite for legal LLMs and the LexGuard adversarial framework that uses SMT solvers to enforce legal consistency.

  8. RCBSF: A Multi-Agent Framework for Automated Contract Revision via Stackelberg Game

    cs.CL 2026-04 unverdicted novelty 6.0 of 10

    RCBSF models contract revision as a bilevel Stackelberg game between a Global Prescriptive Agent and constrained revision/verification agents, claiming convergence to superior equilibria and 84.21% risk resolution.

  9. LLM-AutoDP: Automatic Data Processing via LLM Agents for Model Fine-tuning

    cs.LG 2026-01 unverdicted novelty 6.0 of 10

    LLM agents iteratively generate and optimize data processing strategies for fine-tuning, delivering over 80% win rates versus unprocessed data and 65% versus LLM-based AutoML baselines while cutting search time by up to 10x.

  10. SVGen: Interpretable Vector Graphics Generation with Large Language Models

    cs.LG 2025-08 conditional novelty 6.0 of 10

    SVGen fine-tunes 3B to 7B LLMs with curriculum learning, chain-of-thought, and GRPO reinforcement to generate SVG icons from text, reporting better in-distribution quality than larger models.

  11. Memory Decoder at Scale: A Pretrained, Parametric Long-Term Memory

    cs.CL 2026-07 conditional novelty 5.0 of 10

    A pretrained parametric memory module, taught to copy nearest-neighbor retrieval for next-token prediction, lets small frozen LMs match or beat much larger LMs at the same total parameter budget.

  12. An Ontology-Guided Multi-Anchor Graph Retrieval Framework for Traffic Legal Liability Determination

    cs.CL 2026-06 unverdicted novelty 5.0 of 10

    OMAGR decomposes queries into ontology-aligned anchors for parallel multi-dimensional graph retrieval, outperforming baselines on Context Precision and Faithfulness in the new TrafficLaw-QA dataset of 200 questions.

  13. LegalDrill: Diagnosis-Driven Synthesis for Legal Reasoning in Small Language Models

    cs.CL 2026-04 unverdicted novelty 5.0 of 10

    LegalDrill uses diagnosis-driven synthesis and self-reflective verification to create high-quality training data that improves small language models' legal reasoning without expert annotations.

  14. PDF-WuKong: A Large Multimodal Model for Efficient Long PDF Reading with End-to-End Sparse Sampling

    cs.CV 2024-10 unverdicted novelty 5.0 of 10

    PDF-WuKong adds a sparse sampler to an MLLM for efficient long-PDF multimodal QA and reports an 8.6% F1 gain over proprietary models on a new 1.1M-pair academic-paper dataset.

  15. Retrieval-Augmented Generation for AI-Generated Content: A Survey

    cs.CV 2024-02 accept novelty 5.0 of 10

    A survey classifying RAG foundations for AIGC, summarizing enhancements, cross-modal applications, benchmarks, limitations, and future directions.

  16. LegalGraphRAG: Multi-Agent Graph Retrieval-Augmented Generation for Reliable Legal Reasoning

    cs.CL 2026-05 unverdicted novelty 4.0 of 10

    LegalGraphRAG adds hierarchical organization to legal knowledge graphs and a multi-agent verification loop to reach claimed state-of-the-art accuracy and trustworthiness on legal reasoning benchmarks.

  17. LLMs-as-Judges: A Comprehensive Survey on LLM-based Evaluation Methods

    cs.CL 2024-12 accept novelty 3.0 of 10

    A survey that organizes LLMs-as-judges research into functionality, methodology, applications, meta-evaluation, and limitations.

  18. A Survey on Knowledge Distillation of Large Language Models

    cs.CL 2024-02 accept novelty 3.0 of 10

    A comprehensive survey of knowledge distillation for LLMs structured around algorithms, skill enhancement, and vertical applications, highlighting data augmentation as a key enabler.

Pith tools