REVIEW 15 cited by
LawGPT: A Chinese Legal Knowledge-Enhanced Large Language Model
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
Signed reviews
read the original abstract
Large language models (LLMs), including both proprietary and open-source models, have showcased remarkable capabilities in addressing a wide range of downstream tasks. Nonetheless, when it comes to practical Chinese legal tasks, these models fail to meet the actual requirements. Proprietary models do not ensure data privacy for sensitive legal cases, while open-source models demonstrate unsatisfactory performance due to their lack of legal knowledge. To address this problem, we introduce LawGPT, the first open-source model specifically designed for Chinese legal applications. LawGPT comprises two key components: legal-oriented pre-training and legal supervised fine-tuning. Specifically, we employ large-scale Chinese legal documents for legal-oriented pre-training to incorporate legal domain knowledge. To further improve the model's performance on downstream legal tasks, we create a knowledge-driven instruction dataset for legal supervised fine-tuning. Our experimental results demonstrate that LawGPT outperforms the open-source LLaMA 7B model. Our code and resources are publicly available at https://github.com/pengxiao-song/LaWGPT and have received 5.7K stars on GitHub.
Forward citations
Cited by 15 Pith papers
-
AppealCase: A Dataset and Benchmark for Civil Case Appeal Scenarios
AppealCase is a new paired first- and second-instance Chinese civil judgment benchmark with five appellate LegalAI tasks on which current models score below 50% F1 for reversal prediction from the first-instance perspective.
-
CitaLaw: Enhancing LLM with Citations in Legal Domain
CitaLaw is a Chinese legal benchmark that tests citation-grounded answers for laypeople and legal practitioners, with a syllogism-based evaluation that shows substantial agreement with human judges.
-
A Data Synthesis Method Driven by Large Language Models for Proactive Mining of Implicit User Intentions in Tourism
A two-agent LLM data synthesis method that adds probabilistic inquiry control, memory stacks, and emotion/option reasoning produces training data that lets a 7B model proactively mine implicit user intents in Chinese ...
-
OntoTune: Ontology-Driven Self-training for Aligning Large Language Models
A self-training method that uses an existing medical ontology to select and learn from the model's own inconsistent answers improves medical QA and taxonomy tasks while preserving general ability.
-
Learning to Solve Domain-Specific Calculation Problems with Knowledge-Intensive Programs Generator
A pipeline that generates executable programs from domain knowledge documents and uses them with extracted variables to solve domain-specific calculation problems, improving accuracy over baselines in legal and medical QA.
-
ChiMed 2.0: Advancing Chinese Medical Dataset in Facilitating Large Language Modeling
ChiMed 2.0 is a 204.4M-character Chinese medical dataset spanning pretraining, SFT, and preference data that yields small gains on CMMLU and CEval medical subsets.
-
ASP2LJ : An Adversarial Self-Play Laywer Augmented Legal Judgment Framework
ASP2LJ combines synthetic case generation with adversarial self-play for lawyer agents, improving legal judgment prediction on a Chinese benchmark and on a new rare-case dataset.
-
RTBAgent: A LLM-based Agent System for Real-Time Bidding
RTBAgent wraps an LLM around an expert bidding strategy, letting the model adjust a bid multiplier by up to ±50% using memories and daily reflection, and reports marginal click gains on iPinYou.
-
Adapting Network Information into Semantics for Generalizable and Plug-and-Play Multi-Scenario Network Diagnosis
NetSemantic uses LLM-generated semantic and symbolic descriptions plus a knowledge graph to perform zero-shot network fault diagnosis, reporting 89.5% fault classification accuracy on a digital twin dataset.
-
When Large Language Models Meet Law: Dual-Lens Taxonomy, Technical Advances, and Ethical Governance
A literature review that classifies LLM-for-law research using a dual-lens taxonomy of Toulmin argumentation components and legal practitioner roles.
-
ICH-Qwen: A Large Language Model Towards Chinese Intangible Cultural Heritage
They fine-tuned Qwen2.5-7B on Chinese intangible cultural heritage texts to build ICH-Qwen, and report n-gram metric wins over general LLMs on 100-sample ICH QA tasks.
-
METEOR: Evolutionary Journey of Large Language Models from Guidance to Self-Growth
METEOR combines weak-to-strong distillation, iterative GPT-4 feedback, and contrastive self-training to adapt 7B-8B LLMs to a domain, with gains measured only by GPT-4 as judge.
-
Large Language Models Meet Legal Artificial Intelligence: A Survey
A structured review of legal LLMs, LLM-based frameworks, benchmarks, and datasets, with a taxonomy and future directions.
-
Legal Evalutions and Challenges of Large Language Models
In a small human-scored evaluation of 10 LLMs on 26 legal cases, o1-preview received the highest overall human score (3.96/5), while ROUGE and BLEU scores did not track human preference.
-
Robust Semi-Supervised Learning in Open Environments
A review covering robust semi-supervised learning under label, feature, and distribution inconsistency between labeled and unlabeled data.
Discussion (0). Continue with ORCID to comment.