Pith. sign in

REVIEW 9 cited by

Lawyer LLaMA Technical Report

Not yet reviewed by Pith; the record is open.

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 2305.15062 v2 pith:UBTLI5X2 submitted 2023-05-24 cs.CL cs.AI

Lawyer LLaMA Technical Report

classification cs.CL cs.AI
keywords modelknowledgellamadatadomaindomain-specificdomainsduring
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

Large Language Models (LLMs), like LLaMA, have exhibited remarkable performance across various tasks. Nevertheless, when deployed to specific domains such as law or medicine, the models still confront the challenge of a deficiency in domain-specific knowledge and an inadequate capability to leverage that knowledge to resolve domain-related problems. In this paper, we propose a new framework to adapt LLMs to specific domains and build Lawyer LLaMA, a legal domain LLM, based on this framework. Specifically, we inject domain knowledge during the continual training stage and teach the model to learn professional skills using properly designed supervised fine-tuning tasks. Moreover, to alleviate the hallucination problem during the model's generation, we add a retrieval module and extract relevant legal articles before the model answers any queries. When learning domain-specific skills, we find that experts' experience is much more useful than experiences distilled from ChatGPT, where hundreds of expert-written data outperform tens of thousands of ChatGPT-generated ones. We will release our model and data.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 9 Pith papers

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

  1. Implicit Humanization in Everyday LLM Moral Judgments

    cs.CY 2026-03 unverdicted novelty 7.0

    LLM responses to moral judgment queries reinforce implicit humanization, potentially exacerbating overreliance and misplaced trust.

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

    cs.CL 2025-12 conditional novelty 7.0

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

  3. LLM Evolution as an Industry-Scale Ecosystem: A Lifecycle Perspective on Continual Learning

    cs.LG 2026-06 unverdicted novelty 5.0

    The paper reformulates industrial continual learning for LLMs as a closed-loop ecosystem problem, identifies three core challenges, and organizes solutions around five lifecycle design principles.

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

    cs.CL 2026-06 unverdicted novelty 5.0

    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.

  5. Accurate Legal Reasoning at Scale: Neuro-Symbolic Offloading and Structural Auditability for Robust Legal Adjudication

    cs.CL 2026-05 unverdicted novelty 5.0

    A neuro-symbolic system converts legal clauses into deterministic typed graphs for consistent, auditable adjudication that cuts compute costs by over 90% versus direct large reasoning model use.

  6. MAR: Efficient Large Language Models via Module-aware Architecture Refinement

    cs.AI 2026-01 unverdicted novelty 5.0

    MAR integrates SSMs and sparsification with new ATMN neurons and SBDS distillation to produce efficient LLMs that match dense-model performance at substantially lower inference energy.

  7. LicenseGPT: A Fine-tuned Foundation Model for Publicly Available Dataset License Compliance

    cs.SE 2024-12 unverdicted novelty 5.0

    LicenseGPT fine-tuned on 500 expert-annotated licenses raises prediction agreement to 64.30% and cuts per-license analysis time by 94.44% from 108s to 6s in lawyer user studies.

  8. Preserving Knowledge in Large Language Model with Model-Agnostic Self-Decompression

    cs.CL 2024-06 unverdicted novelty 5.0

    Introduces Tree Generation (TG-SFT) to generate synthetic instruction-tuning data from LLMs, reducing catastrophic forgetting when fine-tuning MLLMs on domain-specific or multimodal data.

  9. A Survey on Knowledge Distillation of Large Language Models

    cs.CL 2024-02 accept novelty 3.0

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