Caveat Lector: Large Language Models in Legal Practice
https://papers.ssrn.com/sol3/papers.cfm?abstract_id=4757452
The current fascination with large language models, or “LLMs,” derives from the fact that many users lack the expertise to evaluate the quality of the generated text. LLMs may therefore appear more capable than they actually are. The dangerous combination of fluency and superficial plausibility leads to the temptation to trust the generated text and creates the risk of overreliance. Who wouldn’t trust perfect legalese?
Drawing from recent findings in both technical and legal scholarship, this Article counterbalances the overly optimistic predictions as to the role of LLMs in legal practice. Integrating LLMs into legal workstreams without a better comprehension of their limitations, will create inefficiencies if not outright risks. Notwithstanding their unprecedented ability to generate text, LLMs do not understand text. Without the ability to understand the meaning of words, LLMs will remain unable to use language, to acquire knowledge and to perform complex reasoning tasks.
Trained to model language on the basis of stochastic word predictions, LLMs cannot distinguish fact from fiction. Their “knowledge” of the law is limited to word strings memorized in their parameters. It is also often incomplete and largely incorrect. LLMs operate at the level of word distributions, not at the level of verified facts. The resulting propensity to hallucinate, to produce statements that are incorrect but appear helpful and relevant, is alarming in high-risk areas like legal services. For the time being, lawyers should beware of relying on text generated by LLMs.
SaulLM-7B: A pioneering Large Language Model for Law
In this paper, we introduce SaulLM-7B, a large language model (LLM) tailored for the legal domain. With 7 billion parameters, SaulLM-7B is the first LLM designed explicitly for legal text comprehension and generation. Leveraging the Mistral 7B architecture as its foundation, SaulLM-7B is trained on an English legal corpus of over 30 billion tokens. SaulLM-7B exhibits state-of-the-art proficiency in understanding and processing legal documents. Additionally, we present a novel instructional fine-tuning method that leverages legal datasets to further enhance SaulLM-7B’s performance in legal tasks. SaulLM-7B is released under the MIT License.
LeXFiles and LegalLAMA: Facilitating English Multinational Legal Language Model Development
In this work, we conduct a detailed analysis on the performance of legal-oriented pre-trained language models (PLMs). We examine the interplay between their original objective, acquired knowledge, and legal language understanding capacities which we define as the upstream, probing, and downstream performance, respectively. We consider not only the models’ size but also the pre-training corpora used as important dimensions in our study. To this end, we release a multinational English legal corpus (LeXFiles) and a legal knowledge probing benchmark (LegalLAMA) to facilitate training and detailed analysis of legal-oriented PLMs. We release two new legal PLMs trained on LeXFiles and evaluate them alongside others on LegalLAMA and LexGLUE. We find that probing performance strongly correlates with upstream performance in related legal topics. On the other hand, downstream performance is mainly driven by the model’s size and prior legal knowledge which can be estimated by upstream and probing performance. Based on these findings, we can conclude that both dimensions are important for those seeking the development of domain-specific PLMs.
MultiLegalSBD: A Multilingual Legal Sentence Boundary Detection Dataset
ABSTRACT Sentence Boundary Detection (SBD) is one of the foundational building blocks of Natural Language Processing (NLP), with incorrectly split sentences heavily influencing the output quality of downstream tasks. It is a challenging task for algorithms, especially in the legal domain, considering the complex and different sentence structures used. In this work, we curated a diverse multilingual legal dataset consisting of over 130’000 annotated sentences in 6 languages. Our experimental results indicate that the performance of existing SBD models is subpar on multilingual legal data. We trained and tested monolingual and multilingual models based on CRF, BiLSTM-CRF, and transformers, demonstrating state-of-the art performance. We also show that our multilingual models outperform all baselines in the zero-shot setting on a Portuguese test set. To encourage further research and development by the community, we have made our dataset, models, and code publicly available.
Exploring the State of the Art in Legal QA Systems
Answering questions related to the legal domain is a complex task, primarily due to the intricate nature and diverse range of legal document systems. Providing an accurate answer to a legal query typically necessitates specialized knowledge in the relevant domain, which makes this task all the more challenging, even for human experts. Question answering (QA) systems are designed to generate answers to questions asked in human languages. QA uses natural language processing to understand questions and search through information to find relevant answers. QA has various practical applications, including customer service, education, research, and cross-lingual communication. However, QA faces challenges such as improving natural language understanding and handling complex and ambiguous questions. Answering questions related to the legal domain is a complex task, primarily due to the intricate nature and diverse range of legal document systems. Providing an accurate answer to a legal query typically necessitates specialized knowledge in the relevant domain, which makes this task all the more challenging, even for human experts. At this time, there is a lack of surveys that discuss legal question answering. To address this problem, we provide a comprehensive survey that reviews 14 benchmark datasets for question-answering in the legal field as well as presents a comprehensive review of the state-of-the-art Legal Question Answering deep learning models. We cover the different architectures and techniques used in these studies and the performance and limitations of these models. Moreover, we have established a public GitHub repository where we regularly upload the most recent articles, open data, and source code.
FairLex : A Multilingual Benchmark for Evaluating Fairness in Legal Text Processing
We present a benchmark suite of four datasets for evaluating the fairness of pre-trained language models and the techniques used to fine-tune them for downstream tasks. Our benchmarks cover four jurisdictions (European Council, USA, Switzerland, and China), five languages (English, German, French, Italian and Chinese) and fairness across five attributes (gender, age, region, language, and legal area). In our experiments, we evaluate pretrained language models using several grouprobust fine-tuning techniques and show that performance group disparities are vibrant in many cases, while none of these techniques guarantee fairness, nor consistently mitigate group disparities. Furthermore, we provide a quantitative and qualitative analysis of our results, highlighting open challenges in the development of robustness methods in legal NLP.
Can GPT-3 Perform Statutory Reasoning?
Statutory reasoning is the task of reasoning with facts and statutes, which are rules written in natural language by a legislature. It is a basic legal skill. In this paper we explore the capabilities of the most capable GPT-3 model, text-davinci-003, on an established statutory-reasoning dataset called SARA. We consider a variety of approaches, including dynamic few-shot prompting, chain-ofthought prompting, and zero-shot prompting. While we achieve results with GPT-3 that are better than the previous best published results, we also identify several types of clear errors it makes. We investigate why these errors happen. We discover that GPT-3 has imperfect prior knowledge of the actual U.S. statutes on which SARA is based. More importantly, we create simple synthetic statutes, which GPT-3 is guaranteed not to have seen during training. We find GPT-3 performs poorly at answering straightforward questions about these simple synthetic statutes.
RISC : Generating Realistic Synthetic Bilingual Insurance Contract
This paper presents RISC, an open-source Python package data generator1 . RISC generates look-alike automobile insurance contracts based on the Quebec regulatory insurance form in French and English. Insurance contracts are 90 to 100 pages long and use complex legal and insurance-specific vocabulary for a layperson. Hence, they are a much more complex class of documents than those in traditional NLP corpora. Therefore, we introduce RISCBAC, a Realistic Insurance Synthetic Bilingual Automobile Contract dataset based on the mandatory Quebec car insurance contract. The dataset comprises 10,000 French and English unannotated insurance contracts. RISCBAC enables NLP research for unsupervised automatic summarisation, question answering, text simplification, machine translation and more. Moreover, it can be further automatically annotated as a dataset for supervised tasks such as NER.