MétaCan
Menu
Back to cohort
Record W7117147504 · doi:10.1057/s41599-025-05924-3

Large Language Models in Legal Systems: A Survey

2025· article· en· W7117147504 on OpenAlexaff
Fatemeh Dehghani, Roya Dehghani, Yazdan Naderzadeh Ardebili, Shahryar Rahnamayan

Bibliographic record

VenueHumanities and Social Sciences Communications · 2025
Typearticle
Languageen
FieldSocial Sciences
TopicArtificial Intelligence in Law
Canadian institutionsUniversity of TorontoBrock UniversityOntario Tech University
Fundersnot available
KeywordsPerspective (graphical)Key (lock)Reliability (semiconductor)Domain (mathematical analysis)Compliance (psychology)

Abstract

fetched live from OpenAlex

Abstract This paper provides a comprehensive survey of the role of large language models (LLMs) in legal systems. It examines their applications across key areas such as legal document drafting, case analysis, research, compliance monitoring, and education. In addition to mapping these use cases, the survey reviews datasets and benchmarks that enable the training and fine-tuning of LLMs for legal tasks. The analysis highlights both the opportunities and challenges of adopting LLMs in practice, including issues of bias, interpretability, accuracy, and ethical risk. Particular attention is given to the limitations of current models and the risks of overstating their reliability in high-stakes legal contexts. By synthesizing recent advancements, this paper provides a balanced perspective on the current state of LLMs in the legal domain and outlines future directions for research and practice aimed at improving their effectiveness, accountability, and responsible deployment.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

How this classification was reachedexpand

Full frame machine prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.

metaresearch head score (Codex)0.015
metaresearch head score (Gemma)0.063
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Not applicable · Consensus signal: none
GenreCandidate signal: Review · Consensus signal: Review
Teacher disagreement score0.015
Threshold uncertainty score0.081

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0150.063
Meta-epidemiology (narrow)0.0010.001
Meta-epidemiology (broad)0.0010.001
Bibliometrics0.0080.010
Science and technology studies0.0010.002
Scholarly communication0.0060.013
Open science0.0020.003
Research integrity0.0020.003
Insufficient payload (model declined to judge)0.0050.001

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.277
GPT teacher head0.431
Teacher spread0.154 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designNot applicable
Domainnot available
GenreReview

How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".

Quick stats

Citations6
Published2025
Admission routes1
Has abstractyes

Explore more

Same venueHumanities and Social Sciences CommunicationsSame topicArtificial Intelligence in LawFrench-language works237,207