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
Signed reviews
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.
Forward citations
Cited by 21 Pith papers
-
Patent-CR: A Dataset for Patent Claim Revision
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.
-
NormWorlds-CF: Solver-Verified Counterfactual Normative Reasoning with Metamorphic-Relation GRPO
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.
-
OpsLLM: Construction of Large Language Model for Software Operations with Multi-stage Learning
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.
-
Scale or Reason? A Compute-Equivalent Analysis of Reasoning Distillation
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.
-
Learning Dynamics in Continual Pre-Training for Large Language Models
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.
-
Automatic Legal Writing Evaluation of LLMs
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.
-
How Does the Spatial Distribution of Pre-training Data Affect Geospatial Foundation Models?
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.
-
Domain Adaptation of Foundation LLMs for e-Commerce
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.
-
Evaluating LLM-based Approaches to Legal Citation Prediction: Domain-specific Pre-training, Fine-tuning, or RAG? A Benchmark and an Australian Law Case Study
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 ...
-
Rhetorical-Role-Aware Retrieval-Augmented Generation for Legal Question Answering over Indian Supreme Court Judgments
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.
-
LLMs for LLMs: A Structured Prompting Methodology for Long Legal Documents
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...
-
TRIDENT: Benchmarking LLM Safety in Finance, Medicine, and Law
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.
-
SOFT: Selective Data Obfuscation for Protecting LLM Fine-tuning against Membership Inference Attacks
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.
-
Feeding LLM Annotations to BERT Classifiers at Your Own Risk
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.
-
On the Suitability of pre-trained foundational LLMs for Analysis in German Legal Education
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.
-
Middo: Model-Informed Dynamic Data Optimization for Enhanced LLM Fine-Tuning via Closed-Loop Learning
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...
-
Llama-3.1-FoundationAI-SecurityLLM-8B-Instruct Technical Report
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.
-
LLM4WM: Adapting LLM for Wireless Multi-Tasking
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.
-
ALKAFI-LLAMA3: Fine-Tuning LLMs for Precise Legal Understanding in Palestine
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.
-
LAW: Legal Agentic Workflows for Custody and Fund Services Contracts
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.
- Domaino1s: Guiding LLM Reasoning for Explainable Answers in High-Stakes Domains
Discussion (0). Continue with ORCID to comment.