LEMUR: A Corpus for Robust Fine-Tuning of Multilingual Law Embedding Models for Retrieval (2026.eacl-srw)
Copied to clipboard
| Challenge: | Existing large language models are not designed for semantic retrieval and PDF-based legislative sources introduce substantial noise due to imperfect text extraction. |
| Approach: | They propose a large-scale multilingual corpus of EU environmental legislation constructed from 24,953 official EUR-Lex PDF documents covering 25 languages. |
| Outcome: | The proposed model improves Top-k retrieval accuracy in monolingual and bilingual settings . it also improves accuracy in low- and high-resource languages . |
Similar Papers
LawInstruct: A Resource for Studying Language Model Adaptation to the Legal Domain (2025.findings-naacl)
Copied to clipboard
Joel Niklaus, Lucia Zheng, Arya D. McCarthy, Christopher Hahn, Brian M Rosen, Peter Henderson, Daniel E. Ho, Garrett Honke, Percy Liang, Christopher D Manning
| Challenge: | In general, instruction tuning is important for direct user interaction, but the legal domain is underrepresented in typical instruction datasets. |
| Approach: | They aggregate 58 annotated legal datasets and write instructions for each to create LawInstruct. |
| Outcome: | The proposed model improves on LegalBench across all model sizes, but no drop in MMLU. |
LexCLiPR: Cross-Lingual Paragraph Retrieval from Legal Judgments (2025.acl-long)
Copied to clipboard
| Challenge: | Existing work on IR focus on retrieving entire cases rather than precise, paragraph-level information. |
| Approach: | They propose a cross-lingual dataset for paragraph-level retrieval from ECtHR judgments . they evaluate retrieval models in a zero-shot setting and use multilingual case law guides . |
| Outcome: | The proposed model excels in cross-lingual retrieval, while siamese architectures are better suited for monolingual tasks. |
LEGAL-BERT: The Muppets straight out of Law School (2020.findings-emnlp)
Copied to clipboard
| Challenge: | Existing guidelines for pre-training and fine-tuning do not always generalize well in the legal domain. |
| Approach: | They propose to use BERT out of the box, adapt it by additional pre-training on domain-specific corpora, and pre-train it from scratch on domains. |
| Outcome: | The proposed strategies are: use the original BERT out of the box, adapt it by additional pre-training on domain-specific corpora, and pre-train it from scratch on domain specific corpors. |
Elevating Legal LLM Responses: Harnessing Trainable Logical Structures and Semantic Knowledge with Legal Reasoning (2025.naacl-long)
Copied to clipboard
| Challenge: | Existing approaches to large language models focus on semantic similarity, neglecting the intricate logical structures and reasoning essential for addressing complex legal issues. |
| Approach: | They propose a Logical-Semantic Integration Model (LSIM) that bridges semantic and logical coherence and a supervised framework that integrates semantic features with in-context learning. |
| Outcome: | The proposed framework significantly improves accuracy and reliability on a real-world legal QA dataset. |
Modeling Legal Reasoning: LM Annotation at the Edge of Human Agreement (2023.emnlp-main)
Copied to clipboard
| Challenge: | Existing research examines simple classification tasks, but ability of LMs to classify on complex tasks is less well understood. |
| Approach: | They analyze a Supreme Court opinion annotated by a team of domain experts . they find generative models perform poorly when given instructions equal to human annotators . |
| Outcome: | The proposed model performs poorly when given instructions equal to instructions given to human annotations . strongest results derive from fine-tuning models on the annotated dataset . |
LegalSearchLM: Rethinking Legal Case Retrieval as Legal Elements Generation (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing studies on legal case retrieval have limited results . limited representations and legally irrelevant matches are often used . |
| Approach: | They propose a large-scale Korean LCR benchmark and a retrieval model that performs legal element reasoning over the query case. |
| Outcome: | a new model outperforms baseline models on a Korean LCR benchmark . it performs state-of-the-art on 411 diverse crime types in queries over 1.2M candidate cases . previous studies have shown that the model can generalize to out-of domain cases if it is trained on in-domain data . |
EUR-Lex-Sum: A Multi- and Cross-lingual Dataset for Long-form Summarization in the Legal Domain (2022.emnlp-main)
Copied to clipboard
| Challenge: | Existing summarization datasets focus on overly exposed domains and are primarily monolingual with few multilingual datasets. |
| Approach: | They propose a new summarization dataset based on manually curated document summaries from the European Union law platform EUR-Lex. |
| Outcome: | The proposed dataset is based on document summaries of legal acts from the European Union law platform (EUR-Lex). |
CitaLaw: Enhancing LLM with Citations in Legal Domain (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing benchmarks have focused on enabling large language models (LLMs) to generate citationsupported outputs. |
| Approach: | They propose to use a citation-based framework to evaluate LLMs' ability to produce legally sound responses with appropriate citations. |
| Outcome: | The proposed framework enables LLMs to retrieve supporting citations from the reference corpus and align these citation with the corresponding sentences in their responses. |
How to Improve LLMs’ Performance on Specific Languages: A Perspective on LLM-Derived Language Similarity (2026.acl-long)
Copied to clipboard
| Challenge: | Large language models (LLMs) exhibit uneven performance across languages. |
| Approach: | They propose to use a framework to quantify the similarity within each language pair through both the lenses of language-specific performance patterns and cross-lingual transferability. |
| Outcome: | The proposed approach outperforms traditional linguistic typology and cross-lingual transferability measures on multilingual LLMs. |
Nine Ways to Break Copyright Law and Why Our LLM Won’t: A Fair Use Aligned Generation Framework (2025.findings-emnlp)
Copied to clipboard
Aakash Sen Sharma, Debdeep Sanyal, Priyansh Srivastava, Sundar Athreya H, Shirish Karande, Mohan Kankanhalli, Murari Mandal
| Challenge: | Large language models (LLMs) often risk copyright infringement by reproducing protected content verbatim or with insufficient transformative modifications. |
| Approach: | They propose a legally-grounded framework to align LLM outputs with fair-use doctrine . LAW-LM uses a dataset containing 18,000 expert-validated examples . |
| Outcome: | The proposed framework aligns outputs with fair-use doctrine and is validated by 18,000 experts. |