AppellateGen: A Benchmark for Appellate Legal Judgment Generation

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Yang, Hongkun, Wang, Lionel Z., Fan, Wei, Hu, Yiran, Wang, Lixu, Liu, Chenyu, Zeng, Yu, Fu, Shenghong, Gong, Lei, Zhang, Zhengxin, Li, Haoyang, Zheng, Jiexin, Xu, Xin
Format: Preprint
Publié: 2026
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866914428533866496
author Yang, Hongkun
Wang, Lionel Z.
Fan, Wei
Hu, Yiran
Wang, Lixu
Liu, Chenyu
Zeng, Yu
Fu, Shenghong
Gong, Lei
Zhang, Zhengxin
Li, Haoyang
Zheng, Jiexin
Xu, Xin
author_facet Yang, Hongkun
Wang, Lionel Z.
Fan, Wei
Hu, Yiran
Wang, Lixu
Liu, Chenyu
Zeng, Yu
Fu, Shenghong
Gong, Lei
Zhang, Zhengxin
Li, Haoyang
Zheng, Jiexin
Xu, Xin
contents Legal judgment generation is a critical task in legal intelligence. However, existing research in legal judgment generation has predominantly focused on first-instance trials, relying on static fact-to-verdict mappings while neglecting the dialectical nature of appellate (second-instance) review. To address this, we introduce AppellateGen, a benchmark for second-instance legal judgment generation comprising 7,351 case pairs. The task requires models to draft legally binding judgments by reasoning over the initial verdict and evidentiary updates, thereby modeling the causal dependency between trial stages. We further propose a judicial Standard Operating Procedure (SOP)-based Legal Multi-Agent System (SLMAS) to simulate judicial workflows, which decomposes the generation process into discrete stages of issue identification, retrieval, and drafting. Experimental results indicate that while SLMAS improves logical consistency, the complexity of appellate reasoning remains a substantial challenge for current LLMs. The dataset and code are publicly available at: https://anonymous.4open.science/r/AppellateGen-5763.
format Preprint
id arxiv_https___arxiv_org_abs_2601_01331
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle AppellateGen: A Benchmark for Appellate Legal Judgment Generation
Yang, Hongkun
Wang, Lionel Z.
Fan, Wei
Hu, Yiran
Wang, Lixu
Liu, Chenyu
Zeng, Yu
Fu, Shenghong
Gong, Lei
Zhang, Zhengxin
Li, Haoyang
Zheng, Jiexin
Xu, Xin
Computers and Society
Computation and Language
Machine Learning
Legal judgment generation is a critical task in legal intelligence. However, existing research in legal judgment generation has predominantly focused on first-instance trials, relying on static fact-to-verdict mappings while neglecting the dialectical nature of appellate (second-instance) review. To address this, we introduce AppellateGen, a benchmark for second-instance legal judgment generation comprising 7,351 case pairs. The task requires models to draft legally binding judgments by reasoning over the initial verdict and evidentiary updates, thereby modeling the causal dependency between trial stages. We further propose a judicial Standard Operating Procedure (SOP)-based Legal Multi-Agent System (SLMAS) to simulate judicial workflows, which decomposes the generation process into discrete stages of issue identification, retrieval, and drafting. Experimental results indicate that while SLMAS improves logical consistency, the complexity of appellate reasoning remains a substantial challenge for current LLMs. The dataset and code are publicly available at: https://anonymous.4open.science/r/AppellateGen-5763.
title AppellateGen: A Benchmark for Appellate Legal Judgment Generation
topic Computers and Society
Computation and Language
Machine Learning
url https://arxiv.org/abs/2601.01331