← Natural Language Understanding

Papers with Code · CC BY-SA 4.0

LexGLUE

아카이브 평가 8건 · 마지막 적재/변경 2026-10-30

원본 데이터셋 링크 1

평가 기록

과거 수집 기록이며 최신 순위가 아닙니다. 데이터셋 버전·split·실험 조건과 지표 방향이 검증되지 않은 결과는 직접 비교할 수 없습니다. 날짜는 논문 날짜이며 최신 평가일을 뜻하지 않습니다.

표가 화면보다 넓으면 좌우로 스크롤하여 논문과 구현 링크를 확인하세요.

원본 기록 순서 · 순위 미부여
모델	원본 지표·값	논문	구현
BERT	ECtHR Task A 71.4 / 64.0 ECtHR Task B 87.6 / 77.8 SCOTUS 70.5 / 60.9 EUR-LEX 71.6 / 55.6 LEDGAR 87.7 / 82.2 UNFAIR-ToS 87.5 / 81.0 CaseHOLD 70.7	LexGLUE: A Benchmark Dataset for Legal Language Understanding in English 2021-10-03	코드 1
Legal-BERT	ECtHR Task A 71.2 / 64.6 ECtHR Task B 88.0 / 77.2 SCOTUS 76.2 / 65.8 EUR-LEX 72.2 / 56.2 LEDGAR 88.1 / 82.7 UNFAIR-ToS 88.6 / 82.3 CaseHOLD 75.1	LexGLUE: A Benchmark Dataset for Legal Language Understanding in English 2021-10-03	코드 1
CaseLaw-BERT	ECtHR Task A 71.2 / 64.2 ECtHR Task B 88.0 / 77.5 SCOTUS 76.4 / 66.2 EUR-LEX 71.0 / 55.9 LEDGAR 88.0 / 82.3 UNFAIR-ToS 88.3 / 81.0 CaseHOLD 75.6	LexGLUE: A Benchmark Dataset for Legal Language Understanding in English 2021-10-03	코드 1
BigBird	ECtHR Task A 70.5 / 63.8 ECtHR Task B 88.1 / 76.6 SCOTUS 71.7 / 61.4 EUR-LEX 71.8 / 56.6 LEDGAR 87.7 / 82.1 UNFAIR-ToS 87.7 / 80.2 CaseHOLD 70.4	LexGLUE: A Benchmark Dataset for Legal Language Understanding in English 2021-10-03	코드 1
Longformer	ECtHR Task A 69.6 / 62.4 ECtHR Task B 88.0 / 77.8 SCOTUS 72.2 / 62.5 EUR-LEX 71.9 / 56.7 LEDGAR 87.7 / 82.3 UNFAIR-ToS 87.7 / 80.1 CaseHOLD 72.0	LexGLUE: A Benchmark Dataset for Legal Language Understanding in English 2021-10-03	코드 1
RoBERTa	ECtHR Task A 69.5 / 60.7 ECtHR Task B 87.2 / 77.3 SCOTUS 70.8 / 61.2 EUR-LEX 71.8 / 57.5 LEDGAR 87.9 / 82.1 UNFAIR-ToS 87.7 / 81.5 CaseHOLD 71.7	LexGLUE: A Benchmark Dataset for Legal Language Understanding in English 2021-10-03	코드 1
DeBERTa	ECtHR Task A 69.1 / 61.2 ECtHR Task B 87.4 / 77.3 SCOTUS 70.0 / 60.0 EUR-LEX 72.3 / 57.2 LEDGAR 87.9 / 82.0 UNFAIR-ToS 87.2 / 78.8 CaseHOLD 72.1	LexGLUE: A Benchmark Dataset for Legal Language Understanding in English 2021-10-03	코드 1
Optimised SVM Baseline	ECtHR Task A 66.3 / 55.0 ECtHR Task B 76.0 / 65.4 SCOTUS 74.4 / 64.5 EUR-LEX 65.7 / 49.0 LEDGAR 88.0 / 82.6	The Unreasonable Effectiveness of the Baseline: Discussing SVMs in Legal Text Classification 2021-09-15	연결 없음