ContractScrub: A benchmark for final review of legal contracts

Source

• Source name: arXiv
• Source kind: paper
• Authors / organization: Yejin Bang, Kirsty Fielding, Brandan Oliver, Brian Birke, Nabeel Seedat, Andrew M. Bean
• Venue: arXiv: cs.AI
• Published: 2026-08-20
• Collected: 2026-08-21
• URL: http://arxiv.org/abs/2608.20204v1
• PDF: https://arxiv.org/pdf/2608.20204v1
• DOI: UNKNOWN
• Registry group: academic_apis_and_preprints
• Evidence role: canonical_academic_index
• Language: en
• Country / region: UNKNOWN

Plain-Language Brief

The paper introduces ContractScrub, a new benchmark for evaluating the performance of Language Models (LLMs) in reviewing legal contracts for errors. The study finds that while LLMs perform well on general benchmarks, they struggle with contract scrubbing, highlighting the need for domain-specific evaluations.

What the Document Says

• Legal work is considered a domain heavily relying on text processing and suitable for automation.
• Contract scrubbing is the final review of transactional agreements for errors and inconsistencies.
• The paper introduces ContractScrub, a benchmark for evaluating contract scrubbing capabilities.
• ContractScrub consists of contracts hand-crafted by experienced lawyers over diverse error categories.
• Frontier models (LLMs) have been found to perform poorly on contract scrubbing, despite strong performance on general benchmarks.
• One model reached a macro average recall of 0.75 in contract scrubbing.

Key Concepts Mentioned

• legal work
• contract scrubbing
• Language Models (LLMs)
• benchmark
• error categories
• macro average recall

Claims Made by the Document

• Legal work is suitable for automation.
• Contract scrubbing is a task that aligns with the capabilities of frontier LLMs.
• No formal evaluations of LLMs performing contract scrubbing have been conducted.

Evidence Used

• Heavy reliance on text processing
• Routine and painstaking work requiring detailed attention
• Hand-crafted contracts by experienced lawyers

Methods / Approach

UNKNOWN

Limitations Stated by the Authors

UNKNOWN

Limitations Noted by the Agent

Agent interpretation — not from the source.

UNKNOWN

Open Questions

UNKNOWN

Notes for Future Q&A

May include interpretation. Labeled where it does.

UNKNOWN

Raw Abstract / Excerpt

Legal work, with its heavy reliance on processing large amounts of text, is often considered one of the domains most exposed to the use of LLMs. Contract ``scrubbing,'' the final review of transactional agreements for errors and inconsistencies, is a particularly suitable task for automation, because it is routine, painstaking work requiring detailed attention to long documents. Scrubbing also seems to align naturally with the general capabilities expected of frontier LLMs around long-context reasoning, consistency checking, and named entity recognition (NER). Despite the economic value and potential for automation, no formal evaluations of LLMs performing contract scrubbing have been conducted. We introduce ContractScrub, the first benchmark designed to evaluate contract scrubbing capabilities, comprising contracts hand-crafted by experienced lawyers over diverse error categories such as misuse of defined terms, incorrect references, and inconsistent language. Frontier models perform surprisingly poorly with only one model reaching 0.75 macro average recall despite strong performance on seemingly related general benchmarks, demonstrating the practical limits of current models and the importance of narrowly targeted, domain-specific benchmarks for measuring real-world impact.