Submit

Large Language Models & Generative AI in Legal

LLMs power a new generation of legal AI tools — Harvey, CoCounsel, Lexis+ AI — that draft documents, answer research questions, and analyze legal issues conversationally.

Last updated
Maintained by
Peter KorpakLead Editor
Methodology
How evidence is checked

How is Large Language Models & Generative AI used in legal?

In legal, Large Language Models & Generative AI is represented by 209 published case-study records and 6 linked vendors in this directory. 209 records retain cited source URLs. The largest concentration is Law Firms, with Contract Review & Analysis the most common use case. Outcomes are attributed to each record's source when available rather than independently verified.

Published records
209
Records with cited source links
209
Linked vendors
6
Top industry
Law Firms
Top use case
Contract Review & Analysis

Limitation: A missing source link does not mean the deployment did not happen.

209
Case Studies
6
Vendors
Law Firms
Top Industry
Contract Review & Analysis
Top Use Case

Industries Distribution

Law Firms
105
Corporate Legal & In-House
61
Legal Technology & Services
16
Litigation & Disputes
14
Regulatory & Compliance
8
Intellectual Property
5

What is AI Large Language Models & Generative AI in Legal?

Large language models have catalyzed the most significant transformation in legal technology since the advent of online legal research. Within two years of GPT-4's release, virtually every major legal technology provider launched LLM-powered features, and several well-funded startups — Harvey AI foremost among them — built entirely new platforms around generative AI for legal work. The appeal is intuitive: LLMs can read and write legal text with a fluency that makes them natural tools for a profession that runs on language.

The legal-specific LLM ecosystem has matured rapidly. Harvey AI, founded by former O'Melveny & Myers attorney Winston Weinberg and backed by Google Ventures and Sequoia, has become the leading legal generative AI platform with partnerships across dozens of Am Law 100 firms. Thomson Reuters integrated LLMs across its product suite: CoCounsel for legal research, Practical Law AI for drafting assistance, and Westlaw AI for case analysis. LexisNexis launched Lexis+ AI with similar capabilities. Spellbook (from Rally) focuses on contract drafting, and EvenUp uses LLMs to generate demand letters for personal injury cases. Each platform addresses the fundamental challenge of legal LLMs: grounding outputs in verified legal authorities to prevent hallucination.

The implementation approaches vary significantly across the market. RAG (retrieval-augmented generation) is the dominant architecture, connecting LLMs to curated legal databases so that generated text is anchored in real cases, statutes, and regulations. Fine-tuning on legal corpora improves understanding of legal concepts and reasoning patterns. Constitutional AI and guardrail systems prevent outputs that could create ethical or malpractice risks. The most sophisticated implementations combine all three approaches, creating systems that generate fluent, accurate legal content while maintaining appropriate uncertainty when the law is unclear or evolving.

Reported uses and outcomes for Large Language Models & Generative AI

  • Draft legal documents — briefs, memos, contracts, correspondence — in minutes with quality approaching experienced attorney output
  • Answer complex legal research questions conversationally with cited authorities, eliminating hours of manual case law searching
  • Summarize lengthy documents, depositions, and regulatory filings into actionable digests tailored to specific legal questions
  • Analyze contract language for risks and inconsistencies using contextual understanding that goes beyond keyword matching
  • Enable self-service legal tools that let business users handle routine legal questions without engaging the legal department

Large Language Models & Generative AI: Common Questions

Legal AI platforms use multiple strategies to minimize hallucination. RAG (retrieval-augmented generation) grounds LLM outputs in verified legal databases — when CoCounsel cites a case, it retrieves the actual case from Westlaw rather than generating text from memory. Citation verification systems check every legal reference against authoritative databases before presenting results. Confidence scoring flags outputs where the model is uncertain. And some platforms restrict generative capabilities to domains where they have verified training data, declining to answer questions outside their knowledge boundaries. These approaches don't eliminate hallucination entirely but reduce it to manageable levels with attorney oversight.

Which companies have deployed Large Language Models & Generative AI? (209)

K
Intellectual PropertyLegal Research & Case LawLarge Language Models & Generative AI
Reported result:
~500 times/month Smart AI Prior Art Search Monthly Executions
Deployment timeframe:
Not reported by source
Technology:
Large Language Models & Generative AI
Vendor:
Not available in record
Cited source: research.konicaminolta.comSource published Source link checked Automated evidence gate passed
C
Corporate Legal & In-HouseContract Lifecycle ManagementLarge Language Models & Generative AI
Reported result:
$30,000 Annual eSignature Cost Savings
Deployment timeframe:
Not reported by source
Technology:
Large Language Models & Generative AI
Vendor:
Not available in record
Cited source: www.intelagree.comSource link checked Automated evidence gate passed
A
Corporate Legal & In-HouseLegal Document DraftingLarge Language Models & Generative AI
Reported result:
Weeks to days Commercial Lease Negotiation Time
Deployment timeframe:
Not reported by source
Technology:
Large Language Models & Generative AI
Vendor:
Not available in record
Cited source: spellbook.comSource published Source link checked Automated evidence gate passed
L
Law FirmsE-Discovery & Document ReviewLarge Language Models & Generative AI
Reported result:
under 7 minutes Summary & Timeline Generation
Deployment timeframe:
Not reported by source
Technology:
Large Language Models & Generative AI
Vendor:
Not available in record
Cited source: legal.thomsonreuters.comSource published Source link checked Automated evidence gate passed
M
Litigation & DisputesLegal Document DraftingLarge Language Models & Generative AI
Reported result:
From 6 hours to a few minutes Hearing minutes drafting time
Deployment timeframe:
Not reported by source
Technology:
Large Language Models & Generative AI
Vendor:
Not available in record
Cited source: news.microsoft.comSource link checked Automated evidence gate passed
B
Corporate Legal & In-HouseContract Review & AnalysisLarge Language Models & Generative AI
Reported result:
Over 95% reduction Bespoke Trading Agreement Review Time
Deployment timeframe:
Not reported by source
Technology:
Large Language Models & Generative AI
Vendor:
Not available in record
Cited source: www.harvey.aiSource link checked Automated evidence gate passed
T
Legal Technology & ServicesLegal Document DraftingLarge Language Models & Generative AI
Reported result:
95%+ of LLM-suggested edits showed improved quality Translation Edit Quality
Deployment timeframe:
Not reported by source
Technology:
Large Language Models & Generative AI
Vendor:
Not available in record
Cited source: aws.amazon.comSource published Source link checked Automated evidence gate passed
D
Law FirmsLegal Document DraftingLarge Language Models & Generative AI
Reported result:
36 hours/week Weekly Time Savings (up to, early internal experiments)
Deployment timeframe:
Not reported by source
Technology:
Large Language Models & Generative AI
Vendor:
Not available in record
Cited source: www.microsoft.comSource published Source link checked Automated evidence gate passed
L
Regulatory & ComplianceLegal Research & Case LawLarge Language Models & Generative AI
Reported result:
Up to 91% reduction (1 hour → as few as 5 minutes) Case Data Compilation Time
Deployment timeframe:
Not reported by source
Technology:
Large Language Models & Generative AI
Vendor:
Not available in record
Cited source: www.ibm.comSource published Source link checked Automated evidence gate passed
F
Corporate Legal & In-HouseContract Lifecycle ManagementLarge Language Models & Generative AI
Reported result:
From ~1 week (multiple lawyers) to minutes Contract Risk Review Time
Deployment timeframe:
Not reported by source
Technology:
Large Language Models & Generative AI
Vendor:
Not available in record
Cited source: corporatecounselnow.comSource published Source link checked Automated evidence gate passed
Q
Law FirmsE-Discovery & Document ReviewLarge Language Models & Generative AI
Reported result:
98% (vendor-reported) Document Review Recall
Deployment timeframe:
Not reported by source
Technology:
Large Language Models & Generative AI
Vendor:
Not available in record
Cited source: legalrealist.aiSource published Source link checked Automated evidence gate passed
C
Law FirmsLegal Document DraftingLarge Language Models & Generative AI
Reported result:
95% (initial rollout phase) Lawyer Adoption Rate
Deployment timeframe:
Not reported by source
Technology:
Large Language Models & Generative AI
Vendor:
Not available in record
Cited source: theapplied.coSource published Source link checked Automated evidence gate passed
P
Litigation & DisputesLegal Research & Case LawLarge Language Models & Generative AI
Reported result:
$38.50 saved per $1 invested Return on Investment
Deployment timeframe:
Not reported by source
Technology:
Large Language Models & Generative AI
Vendor:
Not available in record
Cited source: the-decoder.comSource published Source link checked Automated evidence gate passed
S
Law FirmsContract Review & AnalysisLarge Language Models & Generative AI
Reported result:
62% reduction (standard NDAs & supplier agreements) Contract Review Cycle Time
Deployment timeframe:
Not reported by source
Technology:
Large Language Models & Generative AI
Vendor:
Not available in record
Cited source: windowsnews.aiSource published Source link checked Automated evidence gate passed
I
Legal Technology & ServicesLegal Research & Case LawLarge Language Models & Generative AI
Reported result:
Reduced from days to minutes Judgment Summarization Time
Deployment timeframe:
Not reported by source
Technology:
Large Language Models & Generative AI
Vendor:
Not available in record
Cited source: aws.amazon.comSource link checked Automated evidence gate passed
d
Corporate Legal & In-HouseContract Review & AnalysisLarge Language Models & Generative AI
Reported result:
-67% (1.5h to 30 min) Contract Review Time (100-page contracts)
Deployment timeframe:
Not reported by source
Technology:
Large Language Models & Generative AI
Vendor:
Not available in record
Cited source: www.legartis.aiSource link checked Automated evidence gate passed
D
Law FirmsLegal Research & Case LawLarge Language Models & Generative AI
Reported result:
80% reduction (1-2 weeks to 1-2 days) Arbitrator Research Time
Deployment timeframe:
Not reported by source
Technology:
Large Language Models & Generative AI
Vendor:
Not available in record
Cited source: dailyjus.comSource published Source link checked Automated evidence gate passed
O
Corporate Legal & In-HouseContract Lifecycle ManagementLarge Language Models & Generative AI
Reported result:
Thousands of hours per year Manual Approval Hours Eliminated
Deployment timeframe:
Not reported by source
Technology:
Large Language Models & Generative AI
Vendor:
Not available in record
Cited source: newsroom.osfhealthcare.orgSource link checked Automated evidence gate passed
B
Corporate Legal & In-HouseLegal Operations & Matter ManagementLarge Language Models & Generative AI
Reported result:
Days of research now accomplished significantly faster Research Time Reduction
Deployment timeframe:
Not reported by source
Technology:
Large Language Models & Generative AI
Vendor:
Not available in record
Cited source: legal.thomsonreuters.comSource link checked Automated evidence gate passed
F
Regulatory & ComplianceCompliance MonitoringLarge Language Models & Generative AI
Reported result:
More than 90% Irrelevant Content Filtered
Deployment timeframe:
Not reported by source
Technology:
Large Language Models & Generative AI
Vendor:
Not available in record
Cited source: www.hoganlovells.comSource link checked Automated evidence gate passed
L
Law FirmsLegal Document DraftingLarge Language Models & Generative AI
Reported result:
1 week (vs. 8 months traditional) — 32x compression Time to Produce CNBV Authorization File
Deployment timeframe:
Not reported by source
Technology:
Large Language Models & Generative AI
Vendor:
Not available in record
Cited source: www.legalparadox.comSource link checked Automated evidence gate passed
M
Litigation & DisputesE-Discovery & Document ReviewLarge Language Models & Generative AI
Reported result:
90% Video Analysis Time Reduction
Deployment timeframe:
Not reported by source
Technology:
Large Language Models & Generative AI
Vendor:
Not available in record
Cited source: www.techandjustice.bsg.ox.ac.ukSource link checked Automated evidence gate passed
B
Corporate Legal & In-HouseLegal Operations & Matter ManagementLarge Language Models & Generative AI
Reported result:
54 countries with multilingual compliance coverage Countries managed in-house
Deployment timeframe:
Not reported by source
Technology:
Large Language Models & Generative AI
Vendor:
Not available in record
Cited source: legal.thomsonreuters.comSource link checked Automated evidence gate passed
L
Law FirmsLegal Research & Case LawLarge Language Models & Generative AI
Reported result:
2x increase (per-call time cut from 30 to 15 minutes) Urgent Hotline Calls Handled
Deployment timeframe:
Not reported by source
Technology:
Large Language Models & Generative AI
Vendor:
Not available in record
Cited source: legal.thomsonreuters.comSource link checked Automated evidence gate passed
C
Law FirmsLegal Operations & Matter ManagementLarge Language Models & Generative AI
Reported result:
From ~15 minutes of lawyer time to instant (staff-handled) Routine Question Response Time
Deployment timeframe:
Not reported by source
Technology:
Large Language Models & Generative AI
Vendor:
Not available in record
Cited source: www.netdocuments.comSource link checked Automated evidence gate passed
A
Litigation & DisputesE-Discovery & Document ReviewLarge Language Models & Generative AI
Reported result:
50–67% reduction (one-quarter of the personnel) Document Review Time Reduction
Deployment timeframe:
Not reported by source
Technology:
Large Language Models & Generative AI
Vendor:
Not available in record
Cited source: www.everlaw.comSource link checked Automated evidence gate passed

Which vendors are linked to documented Large Language Models & Generative AI deployments? (6)

Favicon of LuminanceLuminance7Favicon of Harvey AIHarvey AI13Favicon of EverlawEverlaw3Favicon of RelativityRelativity6Favicon of IroncladIronclad3Favicon of Robin AIRobin AI1