Assessing the Performance Gap Between Lexical and Semantic Models for Information Retrieval With Formulaic Legal Language

• URL: http://arxiv.org/abs/2506.12895v1
• Date: Sun, 15 Jun 2025 15:53:38 GMT
• Title: Assessing the Performance Gap Between Lexical and Semantic Models for Information Retrieval With Formulaic Legal Language
• Authors: Larissa Mori, Carlos Sousa de Oliveira, Yuehwern Yih, Mario Ventresca,
• Abstract summary: This study investigates the task of retrieving legal passages or paragraphs from decisions of the Court of Justice of the European Union (CJEU)<n>Our experiments show that BM25 is a strong baseline, surpassing off-the-shelf dense models in 4 out of 7 performance metrics.<n>Fine-tuning a dense model on domain-specific data led to improved performance, surpassing BM25 in most metrics.
• Score: 1.3499500088995462
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Legal passage retrieval is an important task that assists legal practitioners in the time-intensive process of finding relevant precedents to support legal arguments. This study investigates the task of retrieving legal passages or paragraphs from decisions of the Court of Justice of the European Union (CJEU), whose language is highly structured and formulaic, leading to repetitive patterns. Understanding when lexical or semantic models are more effective at handling the repetitive nature of legal language is key to developing retrieval systems that are more accurate, efficient, and transparent for specific legal domains. To this end, we explore when this routinized legal language is better suited for retrieval using methods that rely on lexical and statistical features, such as BM25, or dense retrieval models trained to capture semantic and contextual information. A qualitative and quantitative analysis with three complementary metrics shows that both lexical and dense models perform well in scenarios with more repetitive usage of language, whereas BM25 performs better than the dense models in more nuanced scenarios where repetition and verbatim~quotes are less prevalent and in longer queries. Our experiments also show that BM25 is a strong baseline, surpassing off-the-shelf dense models in 4 out of 7 performance metrics. However, fine-tuning a dense model on domain-specific data led to improved performance, surpassing BM25 in most metrics, and we analyze the effect of the amount of data used in fine-tuning on the model's performance and temporal robustness. The code, dataset and appendix related to this work are available on: https://github.com/larimo/lexsem-legal-ir.

Related papers

• Optimizing Multi-Stage Language Models for Effective Text Retrieval [0.0]
  We introduce a novel two-phase text retrieval pipeline optimized for Japanese legal datasets.<n>Our method leverages advanced language models to achieve state-of-the-art performance.<n>To further enhance robustness and adaptability, we incorporate an ensemble model that integrates multiple retrieval strategies.
  arXiv  Detail & Related papers  (2024-12-26T16:05:19Z)
• Exploiting LLMs' Reasoning Capability to Infer Implicit Concepts in Legal Information Retrieval [6.952344923975001]
  This work focuses on utilizing the logical reasoning capabilities of large language models (LLMs) to identify relevant legal terms. The proposed retrieval system integrates additional information from the term--based expansion and query reformulation to improve the retrieval accuracy. Experiments on COLIEE 2022 and COLIEE 2023 datasets show that extra knowledge from LLMs helps to improve the retrieval result of both lexical and semantic ranking models.
  arXiv  Detail & Related papers  (2024-10-16T01:34:14Z)
• LawLLM: Law Large Language Model for the US Legal System [43.13850456765944]
  We introduce the Law Large Language Model (LawLLM), a multi-task model specifically designed for the US legal domain. LawLLM excels at Similar Case Retrieval (SCR), Precedent Case Recommendation (PCR), and Legal Judgment Prediction (LJP) We propose customized data preprocessing techniques for each task that transform raw legal data into a trainable format.
  arXiv  Detail & Related papers  (2024-07-27T21:51:30Z)
• Large Language Models for Judicial Entity Extraction: A Comparative Study [0.0]
  This research investigates the application of Large Language Models in identifying domain-specific entities within case law documents. The study evaluates the performance of state-of-the-art Large Language Model architectures, including Large Language Model Meta AI 3, Mistral, and Gemma.
  arXiv  Detail & Related papers  (2024-07-08T09:49:03Z)
• The Power of Question Translation Training in Multilingual Reasoning: Broadened Scope and Deepened Insights [108.40766216456413]
  We propose a question alignment framework to bridge the gap between large language models' English and non-English performance. Experiment results show it can boost multilingual performance across diverse reasoning scenarios, model families, and sizes. We analyze representation space, generated response and data scales, and reveal how question translation training strengthens language alignment within LLMs.
  arXiv  Detail & Related papers  (2024-05-02T14:49:50Z)
• DELTA: Pre-train a Discriminative Encoder for Legal Case Retrieval via Structural Word Alignment [55.91429725404988]
  We introduce DELTA, a discriminative model designed for legal case retrieval. We leverage shallow decoders to create information bottlenecks, aiming to enhance the representation ability. Our approach can outperform existing state-of-the-art methods in legal case retrieval.
  arXiv  Detail & Related papers  (2024-03-27T10:40:14Z)
• Leveraging Large Language Models for Relevance Judgments in Legal Case Retrieval [16.29803062332164]
  We propose a few-shot approach where large language models assist in generating expert-aligned relevance judgments.<n>The proposed approach decomposes the judgment process into several stages, mimicking the workflow of human annotators.<n>It also ensures interpretable data labeling, providing transparency and clarity in the relevance assessment process.
  arXiv  Detail & Related papers  (2024-03-27T09:46:56Z)
• Making Retrieval-Augmented Language Models Robust to Irrelevant Context [55.564789967211844]
  An important desideratum of RALMs, is that retrieved information helps model performance when it is relevant. Recent work has shown that retrieval augmentation can sometimes have a negative effect on performance.
  arXiv  Detail & Related papers  (2023-10-02T18:52:35Z)
• Beyond Contrastive Learning: A Variational Generative Model for Multilingual Retrieval [109.62363167257664]
  We propose a generative model for learning multilingual text embeddings. Our model operates on parallel data in $N$ languages. We evaluate this method on a suite of tasks including semantic similarity, bitext mining, and cross-lingual question retrieval.
  arXiv  Detail & Related papers  (2022-12-21T02:41:40Z)
• Attentive Deep Neural Networks for Legal Document Retrieval [2.4350217735794337]
  We study the use of attentive neural network-based text representation for statute law document retrieval. We develop two hierarchical architectures with sparse attention to represent long sentences and articles, and we name them Attentive CNN and Paraformer. Experimental results show that Attentive neural methods substantially outperform non-neural methods in terms of retrieval performance across datasets and languages.
  arXiv  Detail & Related papers  (2022-12-13T01:37:27Z)
• When Does Translation Require Context? A Data-driven, Multilingual Exploration [71.43817945875433]
  proper handling of discourse significantly contributes to the quality of machine translation (MT) Recent works in context-aware MT attempt to target a small set of discourse phenomena during evaluation. We develop the Multilingual Discourse-Aware benchmark, a series of taggers that identify and evaluate model performance on discourse phenomena.
  arXiv  Detail & Related papers  (2021-09-15T17:29:30Z)
• Efficient Nearest Neighbor Language Models [114.40866461741795]
  Non-parametric neural language models (NLMs) learn predictive distributions of text utilizing an external datastore. We show how to achieve up to a 6x speed-up in inference speed while retaining comparable performance.
  arXiv  Detail & Related papers  (2021-09-09T12:32:28Z)

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.