Multi-LexSum: Real-world Summaries of Civil Rights Lawsuits at Multiple Granularities

Zejiang Shen, Kyle Lo, Lauren Yu, Nathan Dahlberg et al.

All authors

Zejiang Shen, Kyle Lo, Lauren Yu, Nathan Dahlberg, Margo Schlanger, Doug Downey

NeurIPS 2022 Datasets and Benchmarks

What it adds

Pairs long collections of civil-rights litigation documents with expert-written summaries at three lengths. A small human evaluation examines whether generated summaries actually help trained legal writers.

Read with this limitation

The collection favours plaintiff wins and federal cases with online dockets. The human study involved two writers and forty new cases; its results concern the tested 2022 system and do not establish present-day model performance or general productivity gains.

Jurisdiction tags
United States
Language
English

Follow the source

Selected statements located in the linked primary sources. These results have not been independently reproduced here.

  1. Experts create and review summaries at long, short and one-sentence lengths.

    Section 3.2; task lengths in Section 3.1 on PDF page 4
  2. In the forty-case study, a revised BART-based writing system received an average usefulness rating of 0.43 on a 0–3 scale.

    Section 5, Human evaluation
Entry status, source edition & rights
Index entry
Source-linked summary, prepared with agent assistance. Independent scholarly review is pending.
Archive admission
This bibliographic entry does not confer admission to the versioned archive.
Edition inspected
10.52202/068431-0956
Reading coverage
NeurIPS proceedings PDF inspected for corpus construction, experimental setup, human study, limitations and CUAD reference (PDF pages 1–10 and 12). No dataset downloaded or model results reproduced. Printed corpus totals require reconciliation; see notes.
Rights
External source links only. No paper full text or underlying dataset is mirrored by the site; downstream reuse requires checking the source licence.
Entry updated
2026-10-15

Source-linked summary · independent assessment pending.

Research updates

A monthly digest of selected legal AI papers, datasets and benchmarks, plus published research checks.