Pith. sign in

REVIEW 10 cited by

LawBench: Benchmarking Legal Knowledge of Large Language Models

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 2309.16289 v1 pith:GXFUHCF5 submitted 2023-09-28 cs.CL cs.AIcs.LG

classification cs.CLcs.AIcs.LG
keywords legalllmsknowledgelawbenchtaskswhethercapabilitiesdomain
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Large language models (LLMs) have demonstrated strong capabilities in various aspects. However, when applying them to the highly specialized, safe-critical legal domain, it is unclear how much legal knowledge they possess and whether they can reliably perform legal-related tasks. To address this gap, we propose a comprehensive evaluation benchmark LawBench. LawBench has been meticulously crafted to have precise assessment of the LLMs' legal capabilities from three cognitive levels: (1) Legal knowledge memorization: whether LLMs can memorize needed legal concepts, articles and facts; (2) Legal knowledge understanding: whether LLMs can comprehend entities, events and relationships within legal text; (3) Legal knowledge applying: whether LLMs can properly utilize their legal knowledge and make necessary reasoning steps to solve realistic legal tasks. LawBench contains 20 diverse tasks covering 5 task types: single-label classification (SLC), multi-label classification (MLC), regression, extraction and generation. We perform extensive evaluations of 51 LLMs on LawBench, including 20 multilingual LLMs, 22 Chinese-oriented LLMs and 9 legal specific LLMs. The results show that GPT-4 remains the best-performing LLM in the legal domain, surpassing the others by a significant margin. While fine-tuning LLMs on legal specific text brings certain improvements, we are still a long way from obtaining usable and reliable LLMs in legal tasks. All data, model predictions and evaluation code are released in https://github.com/open-compass/LawBench/. We hope this benchmark provides in-depth understanding of the LLMs' domain-specified capabilities and speed up the development of LLMs in the legal domain.

Discussion (0). Sign in to comment.

Forward citations

Cited by 10 Pith papers

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

  1. Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements

    cs.CL 2026-05 unverdicted novelty 7.0 of 10

    Presents Ishigaki-IDS-Bench, the first benchmark for LLM-based IDS generation from BIM requirements, with baseline results showing max 65.6% Facet F1 and 33.1% content pass rate across 10 models.

  2. AI for Statutory Simplification: A Comprehensive State Legal Corpus and Labor Benchmark

    cs.IR 2025-08 conditional novelty 7.0 of 10

    State-of-the-art LLMs with retrieval answer simplified boolean questions about state unemployment insurance law with at best 0.69 F1, well short of reliable end-to-end code simplification.

  3. Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements

    cs.CL 2026-05 unverdicted novelty 6.0 of 10

    Ishigaki-IDS-Bench supplies 166 verified bilingual examples plus audits to measure LLMs on producing standard-compliant IDS XML from BIM requirements, with best models at 65.6% macro F1 but only 27.7% passing content audits.

  4. MinT: Managed Infrastructure for Training and Serving Millions of LLMs

    cs.LG 2026-05 unverdicted novelty 6.0 of 10

    MinT enables efficient management of million-scale LoRA-adapted LLM policies over shared 1T-parameter base models by moving only small adapters through training and serving pipelines.

  5. Benchmarking LLM-Assisted Blue Teaming via Standardized Threat Hunting

    cs.CR 2025-09 conditional novelty 6.0 of 10

    Standardized modular threat-hunting workflows (CyberTeam) improve LLM performance on blue team tasks compared to open-ended ICL, CoT, and ToT prompting across 30 tasks and 452k samples.

  6. Towards Evaluation for Real-World LLM Unlearning

    cs.AI 2025-08 conditional novelty 6.0 of 10

    DCUE evaluates LLM unlearning by comparing core-token confidence score distributions of the unlearned model and the original model, corrected by a validation set, using the Kolmogorov-Smirnov test.

  7. LLMs Prompted for Legal Context Object More: Overrefusal from Small On-Premises LLMs in Criminal Legal Context

    cs.AI 2026-06 unverdicted novelty 5.0 of 10

    Authority-style prefixes increase refusal rates 2-20x in small on-prem LLMs on criminal legal prompts while a jailbreak prefix shows mixed effects.

  8. MinT: Managed Infrastructure for Training and Serving Millions of LLMs

    cs.LG 2026-05 unverdicted novelty 5.0 of 10

    MinT is a system for managing million-scale LoRA adapter catalogs on shared 1T-parameter base models, with reported efficiency gains in adapter movement, multi-policy training, and catalog addressability.

  9. TrustLLM: Trustworthiness in Large Language Models

    cs.CL 2024-01 unverdicted novelty 5.0 of 10

    TrustLLM defines eight trustworthiness principles, creates a six-dimension benchmark, and evaluates 16 LLMs showing proprietary models generally lead but some open-source ones are close while over-calibration can hurt...

  10. Sora: A Review on Background, Technology, Limitations, and Opportunities of Large Vision Models

    cs.CV 2024-02 unverdicted novelty 2.0 of 10

    The paper reviews the background, technology, applications, limitations, and future directions of OpenAI's Sora text-to-video generative model based on public information.

Pith tools