Evaluating the Limits of Large Language Models in Multilingual Legal Reasoning

• URL: http://arxiv.org/abs/2509.22472v1
• Date: Fri, 26 Sep 2025 15:19:12 GMT
• Title: Evaluating the Limits of Large Language Models in Multilingual Legal Reasoning
• Authors: Antreas Ioannou, Andreas Shiamishis, Nora Hollenstein, Nezihe Merve Gürel,
• Abstract summary: This work evaluates LLaMA and Gemini on multilingual legal and non-legal benchmarks.<n>We present an open-source, modular evaluation pipeline designed to support multilingual, task-diverse benchmarking.
• Score: 5.902003660308139
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: In an era dominated by Large Language Models (LLMs), understanding their capabilities and limitations, especially in high-stakes fields like law, is crucial. While LLMs such as Meta's LLaMA, OpenAI's ChatGPT, Google's Gemini, DeepSeek, and other emerging models are increasingly integrated into legal workflows, their performance in multilingual, jurisdictionally diverse, and adversarial contexts remains insufficiently explored. This work evaluates LLaMA and Gemini on multilingual legal and non-legal benchmarks, and assesses their adversarial robustness in legal tasks through character and word-level perturbations. We use an LLM-as-a-Judge approach for human-aligned evaluation. We moreover present an open-source, modular evaluation pipeline designed to support multilingual, task-diverse benchmarking of any combination of LLMs and datasets, with a particular focus on legal tasks, including classification, summarization, open questions, and general reasoning. Our findings confirm that legal tasks pose significant challenges for LLMs with accuracies often below 50% on legal reasoning benchmarks such as LEXam, compared to over 70% on general-purpose tasks like XNLI. In addition, while English generally yields more stable results, it does not always lead to higher accuracy. Prompt sensitivity and adversarial vulnerability is also shown to persist across languages. Finally, a correlation is found between the performance of a language and its syntactic similarity to English. We also observe that LLaMA is weaker than Gemini, with the latter showing an average advantage of about 24 percentage points across the same task. Despite improvements in newer LLMs, challenges remain in deploying them reliably for critical, multilingual legal applications.

Related papers

• Evaluating Large Language Model with Knowledge Oriented Language Specific Simple Question Answering [73.73820209993515]
  We introduce KoLasSimpleQA, the first benchmark evaluating the multilingual factual ability of Large Language Models (LLMs)<n>Inspired by existing research, we created the question set with features such as single knowledge point coverage, absolute objectivity, unique answers, and temporal stability.<n>Results show significant performance differences between the two domains.
  arXiv  Detail & Related papers  (2025-05-22T12:27:02Z)
• PolyMath: Evaluating Mathematical Reasoning in Multilingual Contexts [79.84059473102778]
  PolyMath is a multilingual mathematical reasoning benchmark covering 18 languages and 4 easy-to-hard difficulty levels.<n>Our benchmark ensures difficulty comprehensiveness, language diversity, and high-quality translation.
  arXiv  Detail & Related papers  (2025-04-25T15:39:04Z)
• MMLU-ProX: A Multilingual Benchmark for Advanced Large Language Model Evaluation [86.7047714187813]
  MMLU-ProX is a benchmark covering 29 languages, built on an English benchmark.<n>Each language version consists of 11,829 identical questions, enabling direct cross-linguistic comparisons.<n>To meet efficient evaluation needs, we provide a lite version containing 658 questions per language.
  arXiv  Detail & Related papers  (2025-03-13T15:59:20Z)
• Towards Robust Knowledge Representations in Multilingual LLMs for Equivalence and Inheritance based Consistent Reasoning [5.656040546546711]
  Reasoning and linguistic skills form the cornerstone of human intelligence, facilitating problem-solving and decision-making. Recent advances in Large Language Models (LLMs) have led to impressive linguistic capabilities and emergent reasoning behaviors, fueling widespread adoption across application domains. We focus on evaluating whether LLMs have the requisite representations to reason using two foundational relationships: "equivalence" and "inheritance"
  arXiv  Detail & Related papers  (2024-10-18T07:34:21Z)
• MlingConf: A Comprehensive Study of Multilingual Confidence Estimation on Large Language Models [23.384966485398184]
  This paper introduces a comprehensive investigation of Multilingual Confidence estimation (MlingConf) on Large Language Models (LLMs) The benchmark comprises four meticulously checked and human-evaluated high-quality multilingual datasets for LA tasks and one for the LS task tailored to specific social, cultural, and geographical contexts of a language. Experiments reveal that on LA tasks English exhibits notable linguistic dominance in confidence estimations than other languages, while on LS tasks, using question-related language to prompt LLMs demonstrates better linguistic dominance in multilingual confidence estimations.
  arXiv  Detail & Related papers  (2024-10-16T11:46:55Z)
• LLM for Everyone: Representing the Underrepresented in Large Language Models [21.07409393578553]
  This thesis aims to bridge the gap in NLP research and development by focusing on underrepresented languages. A comprehensive evaluation of large language models (LLMs) is conducted to assess their capabilities in these languages. The proposed solutions cover cross-lingual continual instruction tuning, retrieval-based cross-lingual in-context learning, and in-context query alignment.
  arXiv  Detail & Related papers  (2024-09-20T20:53:22Z)
• Is Translation All You Need? A Study on Solving Multilingual Tasks with Large Language Models [79.46179534911019]
  Large language models (LLMs) have demonstrated multilingual capabilities, yet they are mostly English-centric due to imbalanced training corpora.<n>We extend the evaluation to real-world user queries and non-English-centric LLMs, offering a broader examination of multilingual performance.
  arXiv  Detail & Related papers  (2024-03-15T12:47:39Z)
• FAC$^2$E: Better Understanding Large Language Model Capabilities by Dissociating Language and Cognition [56.76951887823882]
  Large language models (LLMs) are primarily evaluated by overall performance on various text understanding and generation tasks. We present FAC$2$E, a framework for Fine-grAined and Cognition-grounded LLMs' Capability Evaluation.
  arXiv  Detail & Related papers  (2024-02-29T21:05:37Z)
• MlingConf: A Comprehensive Study of Multilingual Confidence Estimation on Large Language Models [36.33453112932689]
  This paper introduces a comprehensive investigation of Multilingual Confidence estimation (MlingConf) on Large Language Models (LLMs)<n>The benchmark comprises four meticulously checked and human-evaluated high-quality multilingual datasets for LA tasks and one for the LS task tailored to specific social, cultural, and geographical contexts of a language.<n>Experiments reveal that on LA tasks English exhibits notable linguistic dominance in confidence estimations than other languages, while on LS tasks, using question-related language to prompt LLMs demonstrates better linguistic dominance in multilingual confidence estimations.
  arXiv  Detail & Related papers  (2024-02-21T08:20:06Z)
• CMMLU: Measuring massive multitask language understanding in Chinese [133.70911295934746]
  This paper introduces a comprehensive Chinese benchmark that covers various subjects, including natural science, social sciences, engineering, and humanities. CMMLU fills the gap in evaluating the knowledge and reasoning capabilities of large language models within the Chinese context.
  arXiv  Detail & Related papers  (2023-06-15T15:49:51Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.