LexEval: A Comprehensive Chinese Legal Benchmark for Evaluating Large Language Models

Large language models (LLMs) have made significant progress in natural language processing tasks and demonstrate considerable potential in the legal domain. However, legal applications demand high standards of accuracy, reliability, and fairness. Applying existing LLMs to legal systems without careful evaluation of their potential and limitations could pose significant risks in legal practice. To this end, we introduce a standardized comprehensive Chinese legal benchmark LexEval. This benchmark is notable in the following three aspects: (1) Ability Modeling: We propose a new taxonomy of legal cognitive abilities to organize different tasks. (2) Scale: To our knowledge, LexEval is currently the largest Chinese legal evaluation dataset, comprising 23 tasks and 14,150 questions. (3) Data: we utilize formatted existing datasets, exam datasets and newly annotated datasets by legal experts to comprehensively evaluate the various capabilities of LLMs. LexEval not only focuses on the ability of LLMs to apply fundamental legal knowledge but also dedicates efforts to examining the ethical issues involved in their application. We evaluated 38 open-source and commercial LLMs and obtained some interesting findings. The experiments and findings offer valuable insights into the challenges and potential solutions for developing Chinese legal systems and LLM evaluation pipelines. The LexEval dataset and leaderboard are publicly available at \url{https://github.com/CSHaitao/LexEval} and will be continuously updated.

LeKUBE: A Legal Knowledge Update BEnchmark

Recent advances in Large Language Models (LLMs) have significantly shaped the applications of AI in multiple fields, including the studies of legal intelligence. Trained on extensive legal texts, including statutes and legal documents, the legal LLMs can capture important legal knowledge/concepts effectively and provide important support for downstream legal applications such as legal consultancy. Yet, the dynamic nature of legal statutes and interpretations also poses new challenges to the use of LLMs in legal applications. Particularly, how to update the legal knowledge of LLMs effectively and efficiently has become an important research problem in practice. Existing benchmarks for evaluating knowledge update methods are mostly designed for the open domain and cannot address the specific challenges of the legal domain, such as the nuanced application of new legal knowledge, the complexity and lengthiness of legal regulations, and the intricate nature of legal reasoning. To address this gap, we introduce the Legal Knowledge Update BEnchmark, i.e. LeKUBE, which evaluates knowledge update methods for legal LLMs across five dimensions. Specifically, we categorize the needs of knowledge updates in the legal domain with the help of legal professionals, and then hire annotators from law schools to create synthetic updates to the Chinese Criminal and Civil Code as well as sets of questions of which the answers would change after the updates. Through a comprehensive evaluation of state-of-the-art knowledge update methods, we reveal a notable gap between existing knowledge update methods and the unique needs of the legal domain, emphasizing the need for further research and development of knowledge update mechanisms tailored for legal LLMs.

Improving Legal Case Retrieval with Brain Signals

The tasks of legal case retrieval have received growing attention from the IR community in the last decade. Relevance feedback techniques with implicit user feedback (e.g., clicks) have been demonstrated to be effective in traditional search tasks (e.g., Web search). In legal case retrieval, however, collecting relevance feedback faces a couple of challenges that are difficult to resolve under existing feedback paradigms. First, legal case retrieval is a complex task as users often need to understand the relationship between legal cases in detail to correctly judge their relevance. Traditional feedback signal such as clicks is too coarse to use as they do not reflect any fine-grained relevance information. Second, legal case documents are usually long, users often need even tens of minutes to read and understand them. Simple behavior signal such as clicks and eye-tracking fixations can hardly be useful when users almost click and examine every part of the document. In this paper, we explore the possibility of solving the feedback problem in legal case retrieval with brain signal. Recent advances in brain signal processing have shown that human emotional can be collected in fine grains through Brain-Machine Interfaces (BMI) without interrupting the users in their tasks. Therefore, we propose a framework for legal case retrieval that uses EEG signal to optimize retrieval results. We collected and create a legal case retrieval dataset with users EEG signal and propose several methods to extract effective EEG features for relevance feedback. Our proposed features achieve a 71% accuracy for feedback prediction with an SVM-RFE model, and our proposed ranking method that takes into account the diverse needs of users can significantly improve user satisfaction for legal case retrieval. Experiment results show that re-ranked result list make user more satisfied.

Evaluation Ethics of LLMs in Legal Domain

In recent years, the utilization of large language models for natural language dialogue has gained momentum, leading to their widespread adoption across various domains. However, their universal competence in addressing challenges specific to specialized fields such as law remains a subject of scrutiny. The incorporation of legal ethics into the model has been overlooked by researchers. We asserts that rigorous ethic evaluation is essential to ensure the effective integration of large language models in legal domains, emphasizing the need to assess domain-specific proficiency and domain-specific ethic. To address this, we propose a novelty evaluation methodology, utilizing authentic legal cases to evaluate the fundamental language abilities, specialized legal knowledge and legal robustness of large language models (LLMs). The findings from our comprehensive evaluation contribute significantly to the academic discourse surrounding the suitability and performance of large language models in legal domains.

Gender Biased Legal Case Retrieval System on Users' Decision Process

In the last decade, legal case search has become an important part of a legal practitioner's work. During legal case search, search engines retrieval a number of relevant cases from huge amounts of data and serve them to users. However, it is uncertain whether these cases are gender-biased and whether such bias has impact on user perceptions. We designed a new user experiment framework to simulate the judges' reading of relevant cases. 72 participants with backgrounds in legal affairs invited to conduct the experiment. Participants were asked to simulate the role of the judge in conducting a legal case search on 3 assigned cases and determine the sentences of the defendants in these cases. Gender of the defendants in both the task and relevant cases was edited to statistically measure the effect of gender bias in the legal case search results on participants' perceptions. The results showed that gender bias in the legal case search results did not have a significant effect on judges' perceptions.

Caseformer: Pre-training for Legal Case Retrieval

Legal case retrieval aims to help legal workers find relevant cases related to their cases at hand, which is important for the guarantee of fairness and justice in legal judgments. While recent advances in neural retrieval methods have significantly improved the performance of open-domain retrieval tasks (e.g., Web search), their advantages have not been observed in legal case retrieval due to their thirst for annotated data. As annotating large-scale training data in legal domains is prohibitive due to the need for domain expertise, traditional search techniques based on lexical matching such as TF-IDF, BM25, and Query Likelihood are still prevalent in legal case retrieval systems. While previous studies have designed several pre-training methods for IR models in open-domain tasks, these methods are usually suboptimal in legal case retrieval because they cannot understand and capture the key knowledge and data structures in the legal corpus. To this end, we propose a novel pre-training framework named Caseformer that enables the pre-trained models to learn legal knowledge and domain-specific relevance information in legal case retrieval without any human-labeled data. Through three unsupervised learning tasks, Caseformer is able to capture the special language, document structure, and relevance patterns of legal case documents, making it a strong backbone for downstream legal case retrieval tasks. Experimental results show that our model has achieved state-of-the-art performance in both zero-shot and full-data fine-tuning settings. Also, experiments on both Chinese and English legal datasets demonstrate that the effectiveness of Caseformer is language-independent in legal case retrieval.

LeCaRDv2: A Large-Scale Chinese Legal Case Retrieval Dataset

As an important component of intelligent legal systems, legal case retrieval plays a critical role in ensuring judicial justice and fairness. However, the development of legal case retrieval technologies in the Chinese legal system is restricted by three problems in existing datasets: limited data size, narrow definitions of legal relevance, and naive candidate pooling strategies used in data sampling. To alleviate these issues, we introduce LeCaRDv2, a large-scale Legal Case Retrieval Dataset (version 2). It consists of 800 queries and 55,192 candidates extracted from 4.3 million criminal case documents. To the best of our knowledge, LeCaRDv2 is one of the largest Chinese legal case retrieval datasets, providing extensive coverage of criminal charges. Additionally, we enrich the existing relevance criteria by considering three key aspects: characterization, penalty, procedure. This comprehensive criteria enriches the dataset and may provides a more holistic perspective. Furthermore, we propose a two-level candidate set pooling strategy that effectively identify potential candidates for each query case. It's important to note that all cases in the dataset have been annotated by multiple legal experts specializing in criminal law. Their expertise ensures the accuracy and reliability of the annotations. We evaluate several state-of-the-art retrieval models at LeCaRDv2, demonstrating that there is still significant room for improvement in legal case retrieval. The details of LeCaRDv2 can be found at the anonymous website https://github.com/anonymous1113243/LeCaRDv2.

Investigating the Influence of Legal Case Retrieval Systems on Users' Decision Process

Given a specific query case, legal case retrieval systems aim to retrieve a set of case documents relevant to the case at hand. Previous studies on user behavior analysis have shown that information retrieval (IR) systems can significantly influence users' decisions by presenting results in varying orders and formats. However, whether such influence exists in legal case retrieval remains largely unknown. This study presents the first investigation into the influence of legal case retrieval systems on the decision-making process of legal users. We conducted an online user study involving more than ninety participants, and our findings suggest that the result distribution of legal case retrieval systems indeed affect users' judgements on the sentences in cases. Notably, when users are presented with biased results that involve harsher sentences, they tend to impose harsher sentences on the current case as well. This research highlights the importance of optimizing the unbiasedness of legal case retrieval systems.

An Intent Taxonomy of Legal Case Retrieval

Legal case retrieval is a special Information Retrieval~(IR) task focusing on legal case documents. Depending on the downstream tasks of the retrieved case documents, users' information needs in legal case retrieval could be significantly different from those in Web search and traditional ad-hoc retrieval tasks. While there are several studies that retrieve legal cases based on text similarity, the underlying search intents of legal retrieval users, as shown in this paper, are more complicated than that yet mostly unexplored. To this end, we present a novel hierarchical intent taxonomy of legal case retrieval. It consists of five intent types categorized by three criteria, i.e., search for Particular Case(s), Characterization, Penalty, Procedure, and Interest. The taxonomy was constructed transparently and evaluated extensively through interviews, editorial user studies, and query log analysis. Through a laboratory user study, we reveal significant differences in user behavior and satisfaction under different search intents in legal case retrieval. Furthermore, we apply the proposed taxonomy to various downstream legal retrieval tasks, e.g., result ranking and satisfaction prediction, and demonstrate its effectiveness. Our work provides important insights into the understanding of user intents in legal case retrieval and potentially leads to better retrieval techniques in the legal domain, such as intent-aware ranking strategies and evaluation methodologies.

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

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.