Pith. sign in

REVIEW 3 cited by

Legal Prompting: Teaching a Language Model to Think Like a Lawyer

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 2212.01326 v2 pith:ZVNQWX3R submitted 2022-12-02 cs.CL cs.AI

classification cs.CLcs.AI
keywords accuracyapproachesbestlegalpromptingfew-shotfine-tuningimprove
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Large language models that are capable of zero or few-shot prompting approaches have given rise to the new research area of prompt engineering. Recent advances showed that for example Chain-of-Thought (CoT) prompts can improve arithmetic or common sense tasks significantly. We explore how such approaches fare with legal reasoning tasks and take the COLIEE entailment task based on the Japanese Bar exam for testing zero-shot/few-shot and fine-tuning approaches. Our findings show that while CoT prompting and fine-tuning with explanations approaches show improvements, the best results are produced by prompts that are derived from specific legal reasoning techniques such as IRAC (Issue, Rule, Application, Conclusion). Based on our experiments we improve the 2021 best result from 0.7037 accuracy to 0.8148 accuracy and beat the 2022 best system of 0.6789 accuracy with an accuracy of 0.7431.

Discussion (0). Sign in to comment.

Forward citations

Cited by 3 Pith papers

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

  1. From Judgments to Issues: Structured Extraction of Legal Reasoning with Citation-Hallucination Control

    cs.CL 2026-07 conditional novelty 6.0 of 10

    A cost-efficient DeepSeek-V3 pipeline extracts IRAC-grounded issue-level XML from ~330k Italian tax judgments and cuts citation hallucinations from 11.7% to 0.9% via Linkoln matching, validated by two tax-law PhDs on ...

  2. 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...

  3. Prompt Engineering Guidelines for Using Large Language Models in Requirements Engineering

    cs.SE 2025-07 conditional novelty 4.0 of 10

    A literature review and three expert interviews yield a proposed mapping of prompt engineering guideline themes onto five requirements engineering activities, with no empirical validation of the mapping.

Pith tools