[论文解读] Caveat Lector: Large Language Models in Legal Practice

Eliza Mik|arXiv (Cornell University)|Mar 14, 2024

Artificial Intelligence in Law被引用 6

一句话总结

本论文警告说，尽管大型语言模型（LLMs）能够生成流畅的法律文本，但它们并不理解含义，可能会产生幻觉，并且在没有意识到其局限性的情况下，不应被用于高风险的法律任务。

ABSTRACT

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 would not trust perfect legalese? Relying 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 meaning, 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 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. At present, lawyers should beware of relying on text generated by LLMs.

研究动机与目标

• 促使对法律工作流程中 LLM 能力与局限性进行审慎评估。
• 用证据揭示其缺陷，抵消对 LLM 在法律领域有用性的乐观预测。
• 主张在法律实践中实现对 LLM 的知情整合，以避免低效率和风险。

提出的方法

• 综合技术与法律学术文献中关于 LLM 局限性的发现。
• 在法律情境中就语言建模与理解/验证之间的不匹配进行概念性论证。
• 强调在事实基础或高风险法律任务中依赖 LLM 的风险。

实验结果

研究问题

• RQ1 哪些 LLM 的局限性会影响其在法律实践中的使用？
• RQ2 LLMs 缺乏真正理解如何影响其处理法律文本与推理的能力？
• RQ3 在高风险法律领域中幻觉与输出不正确的风险有多大？
• RQ4 为将 LLMs 集成到法律工作流程以避免低效率和风险需要哪些指引？

主要发现

• LLMs 不理解文本，无法获取知识或进行复杂推理。
• 他们对法律的知识仅限于记忆的词串，且常常不正确或不完整。
• LLMs 基于词分布运作，而非经验证的事实，导致幻觉。
• 在法律服务中依赖 LLM 生成的文本存在风险，因为风险高且可能传播错误信息。
• 在不了解局限性的情况下，将 LLM 集成到法律工作流程中可能造成低效率或风险。
• 律师应对当前使用 LLM 生成的文本保持谨慎。