THUIR@COLIEE 2023: More Parameters and Legal Knowledge for Legal Case Entailment

TL;DR

This paper presents a legal case entailment approach combining large pre-trained models, legal knowledge, and learning-to-rank techniques, achieving third place in COLIEE 2023 with insights on the importance of parameters and domain knowledge.

Contribution

The study explores the impact of increased model parameters and legal knowledge integration on legal entailment, highlighting limitations of learning-to-rank methods in this context.

Findings

More parameters and legal knowledge improve entailment performance

Learning-to-rank methods are not very robust for this task

Achieved third place in COLIEE 2023

Abstract

This paper describes the approach of the THUIR team at the COLIEE 2023 Legal Case Entailment task. This task requires the participant to identify a specific paragraph from a given supporting case that entails the decision for the query case. We try traditional lexical matching methods and pre-trained language models with different sizes. Furthermore, learning-to-rank methods are employed to further improve performance. However, learning-to-rank is not very robust on this task. which suggests that answer passages cannot simply be determined with information retrieval techniques. Experimental results show that more parameters and legal knowledge contribute to the legal case entailment task. Finally, we get the third place in COLIEE 2023. The implementation of our method can be found at https://github.com/CSHaitao/THUIR-COLIEE2023.