Circumstances enhanced Criminal Court View Generation

Yue, Linan; Liu, Qi; Wu, Han; An, Yanqing; Wang, Li; Yuan, Senchao; Wu, Dayong

doi:10.1145/3404835.3462984

Cited by 7 publications

(2 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Li and Zhang (2021) combine two separate optimizers to generate rationales for charges given facts and articles. Yue et al (2021b) also generate finegained rationales for charges and terms of penalty, respectively. Although these works can improve the interpretability of judgment results, they do not demonstrate the logical relationship explicitly in the analysis process.…”

Section: Court View Generationmentioning

confidence: 99%

See 1 more Smart Citation

Syllogistic Reasoning for Legal Judgment Analysis

Deng,

Pei,

Kong

et al. 2023

Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing

View full text Add to dashboard Cite

Legal judgment assistants are developing fast due to impressive progress of large language models (LLMs). However, people can hardly trust the results generated by a model without reliable analysis of legal judgement. For legal practitioners, it is common practice to utilize syllogistic reasoning to select and evaluate the arguments of the parties as part of the legal decision-making process. But the development of syllogistic reasoning for legal judgment analysis is hindered by the lack of resources:(1) there is no large-scale syllogistic reasoning dataset for legal judgment analysis, and (2) there is no set of established benchmarks for legal judgment analysis. In this paper, we construct and manually correct a syllogistic reasoning dataset for legal judgment analysis. The dataset contains 11,239 criminal cases which cover 4 criminal elements, 80 charges and 124 articles. We also select a set of large language models as benchmarks, and conduct a in-depth analysis of the capacity of their legal judgment analysis.

show abstract

Section: Court View Generationmentioning

confidence: 99%

“…Another group of researchers explores court view generation (CVG) (Ye et al, 2018;Yue et al, 2021b;Wu et al, 2020) to enable the interpretability of the results of legal judgment. The core idea is to generate phrases or sentences in the description of a fact as rationales for supporting legal judgment results.…”

Section: Introductionmentioning

confidence: 99%