Pith. sign in

REVIEW 21 cited by

SaulLM-7B: A pioneering Large Language Model for Law

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 2403.03883 v2 pith:YUGKWHFY submitted 2024-03-06 cs.CL

classification cs.CL
keywords saullm-7blegalbillionlanguagelargemodeladditionallyarchitecture
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

In this paper, we introduce SaulLM-7B, a large language model (LLM) tailored for the legal domain. With 7 billion parameters, SaulLM-7B is the first LLM designed explicitly for legal text comprehension and generation. Leveraging the Mistral 7B architecture as its foundation, SaulLM-7B is trained on an English legal corpus of over 30 billion tokens. SaulLM-7B exhibits state-of-the-art proficiency in understanding and processing legal documents. Additionally, we present a novel instructional fine-tuning method that leverages legal datasets to further enhance SaulLM-7B's performance in legal tasks. SaulLM-7B is released under the MIT License.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 21 Pith papers

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

  1. Patent-CR: A Dataset for Patent Claim Revision

    cs.CL 2024-12 conditional novelty 7.0 of 10

    Patent-CR provides the first English patent claim revision dataset, and benchmark results show current LLMs, including GPT-4, cannot yet revise claims to examination standard.

  2. 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.

  3. OpsLLM: Construction of Large Language Model for Software Operations with Multi-stage Learning

    cs.LG 2026-04 unverdicted novelty 6.0 of 10

    OpsLLM's pipeline (HITL data curation, SFT, GRPO RL with a domain process reward model) improves LLM accuracy on software-operations QA and RCA, especially on in-distribution root-cause-analysis tasks.

  4. Scale or Reason? A Compute-Equivalent Analysis of Reasoning Distillation

    cs.CL 2025-09 conditional novelty 6.0 of 10

    At matched training or inference FLOPs, plain instruction tuning is usually as good as or better than reasoning distillation, and reasoning only wins on open-ended tasks at 7B scale and up.

  5. Learning Dynamics in Continual Pre-Training for Large Language Models

    cs.CL 2025-05 conditional novelty 6.0 of 10

    A continual pre-training scaling law decomposes the loss curve into a pre-training baseline plus a distribution-shift term, enabling per-step and cross-schedule loss prediction.

  6. Automatic Legal Writing Evaluation of LLMs

    cs.CL 2025-04 conditional novelty 6.0 of 10

    oab-bench provides 105 graded Brazilian Bar Exam writing questions and an LLM-judge pipeline; Claude 3.5 Sonnet scores highest under the o1 judge, but judge-human agreement is validated on only three approved exams.

  7. How Does the Spatial Distribution of Pre-training Data Affect Geospatial Foundation Models?

    cs.LG 2025-01 conditional novelty 6.0 of 10

    Balanced, globally representative pre-training data generally outperforms region-specific sampling for two geospatial foundation models in few-shot downstream tasks, and the advantage shrinks as finetuning data grows.

  8. Domain Adaptation of Foundation LLMs for e-Commerce

    cs.CL 2025-01 conditional novelty 6.0 of 10

    Continued pretraining Llama 3.1 on 1 trillion e-commerce tokens produces e-Llama 8B/70B models that improve in-house e-commerce benchmarks by roughly 25-30% while retaining most general-domain accuracy.

  9. Evaluating LLM-based Approaches to Legal Citation Prediction: Domain-specific Pre-training, Fine-tuning, or RAG? A Benchmark and an Australian Law Case Study

    cs.CL 2024-12 conditional novelty 6.0 of 10

    The paper releases the AusLaw Citation Benchmark and shows that instruction-tuned 7B-8B LLMs plus retrieval re-ranking outperform general and law-specific pretrained LLMs for legal citation prediction, reaching about ...

  10. Rhetorical-Role-Aware Retrieval-Augmented Generation for Legal Question Answering over Indian Supreme Court Judgments

    cs.IR 2026-08 reject novelty 5.0 of 10

    A rhetorical-role-aware RAG system for Indian Supreme Court judgments is described, but its effectiveness claim is unsupported by baselines, ablations, or human evaluation.

  11. LLMs for LLMs: A Structured Prompting Methodology for Long Legal Documents

    cs.AI 2025-09 reject novelty 5.0 of 10

    On CUAD legal contracts, a prompt-engineered QWEN-2 pipeline with chunking and two answer-selection heuristics reportedly outperforms the fine-tuned DeBERTa-large baseline by about 9%, reaching claimed state-of-the-ar...

  12. TRIDENT: Benchmarking LLM Safety in Finance, Medicine, and Law

    cs.CL 2025-07 conditional novelty 5.0 of 10

    Trident-Bench provides 2,652 professionally validated harmful prompts across finance, law, and medicine, and shows that domain-specialized LLMs often comply with unethical requests more than generalist models.

  13. SOFT: Selective Data Obfuscation for Protecting LLM Fine-tuning against Membership Inference Attacks

    cs.CR 2025-06 conditional novelty 5.0 of 10

    SOFT paraphrases low-loss fine-tuning samples before training, reducing MIA AUC from about 0.82 to about 0.54 across six datasets at roughly 7% perplexity cost.

  14. Feeding LLM Annotations to BERT Classifiers at Your Own Risk

    cs.CL 2025-04 conditional novelty 5.0 of 10

    Fine-tuning BERT-class models on LLM-generated labels consistently produces less accurate, more unstable classifiers that plateau early, and common fixes only partially help.

  15. On the Suitability of pre-trained foundational LLMs for Analysis in German Legal Education

    cs.CL 2024-12 conditional novelty 5.0 of 10

    Pre-trained open LLMs underperform bag-of-words baselines on German Gutachtenstil identification and legal essay grading, but retrieval-based example selection narrows the gap on simpler tasks.

  16. Middo: Model-Informed Dynamic Data Optimization for Enhanced LLM Fine-Tuning via Closed-Loop Learning

    cs.CL 2025-08 conditional novelty 4.0 of 10

    An iterative data-optimization pipeline that simplifies, extends, and rewrites SFT examples based on the model's own loss, embedding sparsity, and self-scores reports up to 7.15 absolute points of average benchmark im...

  17. Llama-3.1-FoundationAI-SecurityLLM-8B-Instruct Technical Report

    cs.CR 2025-08 conditional novelty 4.0 of 10

    Foundation-Sec-8B-Instruct, an instruction-tuned 8B cybersecurity LLM, is released and claimed to beat Llama 3.1-8B-Instruct on CTIBench-RCM and CTIBench-MCQA while remaining competitive on general instruction-following.

  18. LLM4WM: Adapting LLM for Wireless Multi-Tasking

    eess.SP 2025-01 conditional novelty 4.0 of 10

    LLM4WM uses MoE-LoRA fine-tuning of a pre-trained LLM to jointly perform six wireless channel tasks, outperforming single-task baselines on simulated data.

  19. ALKAFI-LLAMA3: Fine-Tuning LLMs for Precise Legal Understanding in Palestine

    cs.CL 2024-12 conditional novelty 4.0 of 10

    A fine-tuned 1B-parameter Llama model answers questions about Palestinian law using a synthetic dataset of 243,841 QA pairs, but with only anecdotal evaluation.

  20. LAW: Legal Agentic Workflows for Custody and Fund Services Contracts

    cs.AI 2024-12 reject novelty 4.0 of 10

    An agentic workflow using reusable legal tools beats a raw GPT-3.5 baseline on contract retrieval, but the evaluation is compromised because the ground truth was generated with the same tools.

  21. Domaino1s: Guiding LLM Reasoning for Explainable Answers in High-Stakes Domains

    cs.CL 2025-01

Pith tools