We introduce InternLM-Law, a large language model (LLM) tailored for addressing diverse legal tasks related to Chinese laws. These tasks range from responding to standard legal questions (e.g., legal exercises in textbooks) to analyzing complex real-world legal situations. Our work contributes to Chinese Legal NLP research by (1) conducting one of the most extensive evaluations of state-of-the-art general-purpose and legal-specific LLMs to date that involves an automatic evaluation on the 20 legal NLP tasks in LawBench, a human evaluation on a challenging version of the Legal Consultation task, and an automatic evaluation of a model’s ability to handle very long legal texts; (2) presenting a methodology for training a Chinese legal LLM that offers superior performance to all of its counterparts in our extensive evaluation; and (3) facilitating future research in this area by making all of our code and model publicly available at https://github.com/InternLM/InternLM-Law.

We present LawBench, the first evaluation benchmark composed of 20 tasks aimed to assess the ability of Large Language Models (LLMs) to perform Chinese legal-related tasks. LawBench is meticulously crafted to enable precise assessment of LLMs’ legal capabilities from three cognitive levels that correspond to the widely accepted Bloom’s cognitive taxonomy. Using LawBench, we present a comprehensive evaluation of 21 popular LLMs and the first comparative analysis of the empirical results in order to reveal their relative strengths and weaknesses. All data, model predictions and evaluation code are accessible from https://github.com/open-compass/LawBench.

Legal Judgment Prediction (LJP) refers to the task of automatically predicting judgment results (e.g., charges, law articles and term of penalty) given the fact description of cases. While SOTA models have achieved high accuracy and F1 scores on public datasets, existing datasets fail to evaluate specific aspects of these models (e.g., legal fairness, which significantly impact their applications in real scenarios). Inspired by functional testing in software engineering, we introduce LJPCHECK, a suite of functional tests for LJP models, to comprehend LJP models’ behaviors and offer diagnostic insights. We illustrate the utility of LJPCHECK on five SOTA LJP models. Extensive experiments reveal vulnerabilities in these models, prompting an in-depth discussion into the underlying reasons of their shortcomings.

Legal Judgment Prediction (LJP) has attracted significant attention in recent years. However, previous studies have primarily focused on cases involving only a single defendant, skipping multi-defendant cases due to complexity and difficulty. To advance research, we introduce CMDL, a large-scale real-world Chinese Multi-Defendant LJP dataset, which consists of over 393,945 cases with nearly 1.2 million defendants in total. For performance evaluation, we propose case-level evaluation metrics dedicated for the multi-defendant scenario. Experimental results on CMDL show existing SOTA approaches demonstrate weakness when applied to cases involving multiple defendants. We highlight several challenges that require attention and resolution.

User targeting is an essential task in the modern advertising industry: given a package of ads for a particular category of products (e.g., green tea), identify the online users to whom the ad package should be targeted. A (ad package specific) user targeting model is typically trained using historical clickthrough data: positive instances correspond to users who have clicked on an ad in the package before, whereas negative instances correspond to users who have not clicked on any ads in the package that were displayed to them. Collecting a sufficient amount of positive training data for training an accurate user targeting model, however, is by no means trivial. This paper focuses on the development of a method for automatic augmentation of the set of positive training instances. Experimental results on two datasets, including a real-world company dataset, demonstrate the effectiveness of our proposed method.

While hyperbole is one of the most prevalent rhetorical devices, it is arguably one of the least studied devices in the figurative language processing community. We contribute to the study of hyperbole by (1) creating a corpus focusing on sentence-level hyperbole detection, (2) performing a statistical and manual analysis of our corpus, and (3) addressing the automatic hyperbole detection task.