Legal IR

IR: Information Retrieval

Legal information retrieval studies how to find the right legal authority or passage for questions, research, and tasks such as precedent and patent search. Systems range from lexical methods such as BM25 to dense embeddings, hybrid retrieval and reranking, and approaches that use document structure, citations, or graphs; retrieval-augmented generation uses these results to ground answers. Legal language, long documents, and differences across jurisdictions make query matching difficult, while legal hierarchy, changing authority, and citation provenance can matter as much as semantic similarity. Benchmarks now cover varied languages, tasks, and levels of passage detail, but results often fail to transfer across datasets, and reliable systems still need to balance recall, ranking quality, temporal correctness, and human verification.

Latest papers

53 papers8 papers in the last four weeks, up 33% on the four weeks before. 0.0% of all new papers.

Novel or Not? PatEx-Gym: Agentic Prior-Art Search for Novelty Assessment in Patent Examination
Oct 24, 2026Qiyao Wang, Xinyi Chen, Hongbo Wang +5Novelty Search AI Agent Benchmarks
Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences · University of Chinese Academy of Sciences · Dalian University of Technology +1
StrucChunk: Structure-Aware Retrieval for Legal Document RAG
Oct 19, 2026Surya Deep Singh, Ashutosh Tripathi, Gaurav Deep SinghLegal IR Document Chunking
Independent Researcher.
Beyond Recall Saturation: Scaling Hard-Negative Reranker Training for Industrial Legal Retrieval
Oct 17, 2026Yunhan Li, Mingjie Xie, Zeyang Shi +2LLM Reranking Legal IR
SIAT-DELI AI and Law Joint Lab, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences Shenzhen, China · City University of Macau Macau, China · City University of Macauy Shenzhen, China
Comparing GenAI to Machine Learning and Manual Review for eDiscovery
Oct 12, 2026Gordon V. Cormack, Maura R. GrossmanGenerative AI Evaluation Legal IR
University of Waterloo, ON, Canada
Verifiable Retrieval for Legal Reasoning through Structure-driven Knowledge Graph
Oct 9, 2026Ibrahim Siddig, Sviatoslav Tugeev, Munir GeorgesLegal IR Graph Retrieval-Augmented Generation
Technische Hochschule Ingolstadt, Esplanade 10, 85049 Ingolstadt, Germany
From Rules to Neural Graphs: Scalable Structured Prediction for Patent Prior Art Search
Oct 1, 2026Nikolai Zenovkin, Sebastian BjörkqvistLegal IR Graph-Based Retrieval
IPRally Technologies Oy, Helsinki, Finland
LawCompass: Navigating from Legal QA to Multi-Agent Deep Research with Grounded Evidence
Oct 1, 2026Xiaoxia Cheng, Linnan Wang, Jiahao Ma +5Multi-Agent LLM Systems Legal IR
Anhui University · Tsinghua University
ViLegalExpert: A Large-Scale Benchmark for Vietnamese Legal Retrieval and Question Answering from Real-World Consultations
Sep 30, 2026Dat Tien Nguyen, Nghia Hieu Nguyen, Anh Thi-Hoang Nguyen +3Legal QA Legal NLP
University of Information Technology · Vietnam National University, Ho Chi Minh city, Viet Nam
Mining Legal Arguments in U.S. Corporate Case Law
Sep 21, 2026Luis Brena, William Jurayj, Gregory Deyesu +3Argument Mining Legal IR
Johns Hopkins University · University of Maryland School of Law
UK-PRBENCH: A Paragraph-Level Precedent Retrieval Benchmark for United Kingdom Case Law
Sep 21, 2026Damith Premasiri, Tharindu RanasingheLegal IR Information Retrieval
Lancaster University, UK
PRISM-RAG: Multimodal Hypergraph Retrieval-Augmented Generation for Tobacco Product and Legislative Policy Reasoning
Sep 20, 2026Manuel Serna-Aguilera, Raegan Anderes, Page Dobbs +1Multimodal RAG Legal IR
Fay W. Boozman College of Public Health, University of Arkansas for Medical Sciences, Little Rock, Arkansas, 72205
ChemCLIR-Bench: Benchmarking Cross-Lingual Information Retrieval in Multilingual Chemical Patents
Sep 19, 2026Mahdi Astaraki, Mohammad Khodadad, Reza Namazi +4Multilingual IR Information Retrieval
Faculty of Engineering, McMaster University, Canada · BASF Canada Inc., Canada
Reading a Legal Question Word by Word: Embedding Trajectories of 2,144 Vietnamese Legal Headlines
Sep 8, 2026Tran Minh QuanText Embeddings Word Embeddings
Annotated Surrogate Retrieval for Polish Statutory Law
Aug 31, 2026Orkun Yiğit CengizLegal IR LLM Reranking
Independent Researcher
BLANC: Discovering Patent White Space via Changes in Normalized Pointwise Mutual Information Between Multi-View Clusters
Aug 27, 2026Shuichi Miyazawa, Kensuke FujiiLegal IR
Digital & Innovation Management Division, AGC Inc., Tokyo, Japan · Intellectual Property Division, AGC Inc., Tokyo, Japan
GreenLeaf Law Embed Tiny: A Compact Embedding Model for Legal Domain Retrieval
Aug 23, 2026Surya SakaText Embedding Models Legal IR
JudicialMind
GreekBarRetrieval: A Benchmark for Greek Statutory Retrieval
Aug 19, 2026Ernest Beta, Odysseas S. Chlapanis, Dimitrios Galanis +1Legal IR Query Reformulation
Department of Informatics, Athens University of Economics and Business, Greece · Archimedes, Athena Research Center, Greece · Institute for Language and Speech Processing, Athena Research Center, Greece
ABAI at COLIEE 2026 Task 1: Multi-Stage Retrieval with GraphRAG-Enhanced Meta-Learning, and a Post-Hoc Study of the Cross-Validation-to-Test Gap
Aug 12, 2026Minhan Cho, Soyoung Park, Daejin Choi +1Legal IR IR Evaluation
AlphaBridge Seongnam-si, Gyeonggi-do, Republic of Korea · Sungkyunkwan University Seoul, Republic of Korea · National Assembly Research Service Seoul, Republic of Korea +1
Evaluating RAG for French immigration law: a benchmark and baseline study
Jul 27, 2026Annia Abtout, Julien Delaunay, Monika Ewa RakoczyLLM Grounding Legal IR
Talan, Paris, France
Fenced Citation-Context Retrieval for Case Law: Temporal Leakage and Degree Control Across Two Jurisdictions
Jul 19, 2026Yao Liu, Tien-Ping Tan, Zhilan LiuData Leakage Legal IR
The Engineering and Technology College, Chengdu University of Technology, Leshan, China · School of Computer Sciences, Universiti Sains Malaysia, Penang, Malaysia · Department of Art and Design, The Engineering and Technology College, Chengdu University of Technology, Leshan, China
NOWJ@COLIEE 2026: Adaptive Pipelines for Legal Retrieval and Reasoning
Jul 18, 2026Thuong-Hieu Ngo, Hoang-Trung Nguyen, Huu-Dong Nguyen +5Legal NLP Legal IR
VNU University of Engineering and Technology Hanoi, Vietnam · Center for Juris-Informatics, ROIS-DS College of Engineering & Computer Science, VinUniversity Hanoi, Vietnam
Cross-Architecture LLM Ensembles, Feature-Based Reranking and Retrieval-Augmented Prompting for Legal Information Processing
Jul 13, 2026Amal Saad Alshehri, Nelly Bencomo, Amir Atapour-AbarghoueiLegal NLP Legal IR
Durham University · Department of Computer Science · Durham, United Kingdom +2
Generative Chinese Statute Retrieval
Jul 13, 2026Yiteng Tu, Zitao Su, Weihang Su +5Legal IR Generative Retrieval
Tsinghua University Quancheng Laboratory Beijing, China
PRecG: Legal Precedent Retrieval with Graph Neural Networks and Rhetorical Role Segmentation
Jul 10, 2026Devanshu Verma, Vasudha Bhatnagar, Vikas Kumar +1Graph Neural Networks Legal IR
aUniversity of Delhi, Delhi, India · bIBM Research, Bengaluru, India
Inject or Navigate? Token-Efficient Retrieval for LLM Analysis of Transactional Legal Documents
Jul 7, 2026Mahmoud Hany, Mourad ElSheraey, Mahmoud Said +1LLM Inference Efficiency Legal IR
Syntheia Pty Ltd
Train, Retrieve, or Both? A Four-Arm Head-to-Head for Correct Statutory Citation on the Ontario Residential Tenancies Act
Jun 18, 2026Ali Asaria, Tony Salomone, Deep GandhiSupervised Fine-Tuning Retrieval-Augmented Generation
Transformer Lab
Human-on-the-Loop Orchestration for AI-Assisted Legal Discovery
Jun 18, 2026Anushree Sinha, Srivaths Ranganathan, Abhishek Dharmaratnakar +1Legal IR LLM Agent Orchestration
Google LLC Mountain View, CA, USA
Freeing the Law with LOCUS: A Local Ordinance Corpus for the United States
Jun 17, 2026Denis Peskoff, Joe Barrow, Christopher Vu +1Legal IR Legal Document Analysis
1UC Berkeley · School of Information · 3Independent
When Rules Learn: A Self-Evolving Agent for Legal Case Retrieval
Jun 15, 2026Mingxu Tao, Jiawei Hu, Xian Zhou +5Legal NLP Legal IR
Center of Information Research, AMS · 2Discipline and Technology Research Center for Large Model Intelligence Applications · 3Hebei University of Engineering
LAUKIN: A Multi-jurisdictional Common Law Contract Dataset
Jun 11, 2026Amrita Singh, Aditya Joshi, Jiaojiao Jiang +2Legal NLP Pairwise Comparison
Computer Science and Engineering, UNSW, Sydney, Australia · Law and Justice, UNSW, Sydney, Australia

Oct 24, 2026J/K move · Enter open · S save

Novel or Not? PatEx-Gym: Agentic Prior-Art Search for Novelty Assessment in Patent Examination

Qiyao Wang, Xinyi Chen, Hongbo Wang, Jiayuan Lu+4

Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences · University of Chinese Academy of Sciences · Dalian University of Technology+1

Novelty Search AI Agent Benchmarks Legal IR Legal Document Analysis

Open paper AskPDF arXiv

Patent examination is a challenging real-world task that requires agents to discover sparse prior art, iteratively refine queries, inspect technical evidence, and produce novelty assessments documented in Office Actions (OAs) across heterogeneous scientific and technical domains. However, existing benchmarks largely focus on static and limited candidate sets, leaving the full search--reasoning--assessment process underexplored. We present PatEx-Gym, the first framework for developing and evaluating agents for patent examination, which integrates three components. First, PatEx-Bench provides 1K realistic examination tasks, two large-scale retrieval corpora containing over 1M patents and 52K scientific papers, and a harness runtime supporting iterative search, document visits, reasoning, and OA generation. Second, we introduce PASS, an annotation-free Prior-Art Agentic Search Trajectory Synthesis framework. Specifically, it exploits document visits as implicit relevance signals and evidence-acquisition anchors to model intra-turn query behavior, inter-turn search progression, and trajectory-level evidence and outcome quality, yielding PatEx-SynData. Third, we train PatEx-Agent at the 4B scale via supervised fine-tuning on the curated trajectories, establishing a lightweight baseline. Extensive experiments show that final decision accuracy alone does not fully reflect examination quality, while prior-art discovery remains difficult even for strong frontier models. Our PatEx-Agent achieves competitive performance against substantially larger general-purpose agents. These results show that training on PatEx-SynData enables a compact 4B model to serve as a competitive baseline for prior-art search and patent examination. We view patent examination as a demanding testbed for agentic search and deep research agents.