About
NLLP Workshop 2025 took place on 8 November 2025, co-located with the EMNLP 2025 conference.
The workshop proceedings are available here.
The recording of the workshop is available here:
Sponsors
Program
All times are in CST time zone
| 09:00 - 10:40 | Session 1 |
| 09:00 - 09:20 | Workshop opening |
| 09:20 - 09:25 | LeMAJ (Legal LLM-as-a-Judge): Bridging Legal Reasoning and LLM Evaluation Joseph Enguehard, Morgane Van Ermengem, Kate Atkinson, Sujeong Cha, Arijit Ghosh Chowdhury, Prashanth Kallur Ramaswamy, Jeremy Roghair, Hannah R Marlowe, Carina Suzana Negreanu, Kitty Boxall, Diana Mincu |
| 09:25 - 09:30 | PILOT-Bench: A Benchmark for Legal Reasoning in the Patent Domain with IRAC-Aligned Classification Tasks Yehoon Jang, Chaewon Lee, Hyun-seok Min, Sungchul Choi |
| 09:30 - 09:35 | Contemporary LLMs struggle with extracting formal legal arguments Lena Held, Ivan Habernal |
| 09:35 - 09:40 | Evaluating the Role of Verifiers in Test-Time Scaling for Legal Reasoning Tasks Davide Romano, Jonathan Richard Schwarz, Daniele Giofrè |
| 09:40 - 09:45 | GreekBarBench: A Challenging Benchmark for Free-Text Legal Reasoning and Citations Odysseas S. Chlapanis, Dimitris Galanis, Nikolaos Aletras, Ion Androutsopoulos |
| 09:45 - 09:50 | Evaluating Test-Time Scaling LLMs for Legal Reasoning: OpenAI o1, DeepSeek-R1, and Beyond Yinghao Hu, Yaoyao Yu, Leilei Gan, Bin Wei, Kun Kuang, Fei Wu |
| 09:50 - 09:55 | Are LLMs Court-Ready? Evaluating Frontier Models on Indian Legal Reasoning Kush Juvekar, Arghya Bhattacharya, Sai Khadloya, Utkarsh Saxena |
| 09:55 - 10:15 | Joint Q&A |
| 10:15 - 10:20 | The Automated but Risky Game: Modeling Agent-to-Agent Negotiations and Transactions in Consumer Markets Shenzhe Zhu, Jiao Sun, Yi Nian, Tobin South, Alex Pentland, Jiaxin Pei |
| 10:20 - 10:25 | LegalSim: Multi-Agent Simulation of Legal Systems for Discovering Procedural Exploits Sanket Badhe |
| 10:25 - 10:30 | Label-Free Distinctiveness: Building a Continuous Trademark Scale via Synthetic Anchors Huihui Xu, Kevin D. Ashley |
| 10:30 - 10:40 | Joint Q&A |
| 10:40 - 11:10 | Break |
| 11:10 - 12:30 | Session 2 |
| 11:10 - 11:15 |
Validate Your Authority: Benchmarking LLMs on Multi-Label Precedent Treatment Classification M. Mikail Demir, M Abdullah Canbaz |
| 11:15 - 11:20 |
ContractEval: Benchmarking LLMs for Clause-Level Legal Risk Identification in Commercial Contracts
Shuang Liu, Zelong Li, Ruoyun Ma, Haiyan Zhao, Mengnan Du |
| 11:20 - 11:25 |
Efficient Prompt Optimisation for Legal Text Classification with Proxy Prompt Evaluator
Hyunji Lee, Kevin Chenhao Li, Matthias Grabmair, Shanshan Xu |
| 11:25 - 11:30 |
Not ready for the bench: LLM legal interpretation is unstable and uncalibrated to human judgments
Abhishek Purushothama, Junghyun Min, Brandon Waldon, Nathan Schneider |
| 11:30 - 11:45 | Joint Q&A |
| 11:45 - 11:50 |
GReX: A Graph Neural Network-Based Rerank-then-Expand Method for Detecting Conflicts Among Legal Articles in Korean Criminal Law
Seonho An, Young-Yik Rhim, Min-Soo Kim |
| 11:50 - 11:55 |
Tracing Definitions: Lessons from Alliance Contracts in the Biopharmaceutical Industry
Maximilian Kreutner, Doerte Leusmann, Florian Lemmerich, Carolin Haeussler |
| 11:55 - 12:00 |
CourtNav: Voice-Guided, Anchor-Accurate Navigation of Long Legal Documents in Courtrooms
Sai Khadloya, Kush Juvekar, Arghya Bhattacharya, Utkarsh Saxena |
| 11:55 - 12:00 |
NyayGraph: A Knowledge Graph Enhanced Approach for Legal Statute Identification in Indian Law using Large Language Models
Siddharth Shukla, Tanuj Tyagi, Abhay Singh Bisht, Ashish Sharma, Basant Agarwal |
| 11:55 - 12:00 |
Beyond the Haystack: Sensitivity to Context in Legal Reference Recall
Eric Xia, Karthik Srikumar, Keshav Karthik, Advaith Renjith, Ashwinee Panda |
| 12:10 - 12:30 | Joint Q&A |
| 12:30 - 14:00 | Lunch & In-Person Poster Session (Lunch provided) |
| 14:00 - 15:30 | Session 3 |
| 14:00 - 14:05 |
A Framework to Retrieve Relevant Laws for Will Execution
Md Asiful Islam, Alice Saebom Kwak, Derek Bambauer, Clayton T Morrison, Mihai Surdeanu |
| 14:05 - 14:10 |
Grounded Answers from Multi-Passage Regulations: Learning-to-Rank for Regulatory RAG
Tuba Gokhan, Ted Briscoe |
| 14:10 - 14:15 |
GuRE:Generative Query REwriter for Legal Passage Retrieval
Daehui Kim, Deokhyung Kang, Jonghwi Kim, Sangwon Ryu, Gary Lee |
| 14:15 - 14:20 |
Towards Reliable Retrieval in RAG Systems for Large Legal Datasets
Markus Reuter, Tobias Lingenberg, Ruta Liepina, Francesca Lagioia, Marco Lippi, Giovanni Sartor, Andrea Passerini, Burcu Sayin |
| 14:20 - 14:25 |
KoLEG: On-the-Fly Korean Legal Knowledge Editing with Continuous Retrieval
Jaehyung Seo, Dahyun Jung, Jaewook Lee, Yongchan Chun, Dongjun Kim, Hwijung Ryu, Donghoon Shin, Heuiseok Lim |
| 14:25 - 14:45 | Joint Q&A |
| 14:45 - 14:50 |
Labor Lex: A New Portuguese Corpus and Pipeline for Information Extraction in Brazilian Legal Texts
Pedro Vitor Quinta de Castro, Nadia Felix Felipe da Silva |
| 14:50 - 14:55 |
Aligning LLMs for Thai Legal Question Answering with Efficient Semantic-Similarity Rewards
Pawitsapak Akarajaradwong, Chompakorn Chaksangchaichot, Pirat Pothavorn, Ekapol Chuangsuwanich, Attapol Rutherford, Sarana Nutanong |
| 14:55 - 15:00 |
ClaimGen-CN: A Large-scale Chinese Dataset for Legal Claim Generation
Siying Zhou, Yiquan Wu, Hui Chen, Xueyu Hu, Kun Kuang, Adam Jatowt, Chunyan Zheng, Fei Wu |
| 15:00 - 15:05 |
Translating Tax Law to Code with LLMs: A Benchmark and Evaluation Framework
Gabriele Lorenzo, Aldo Pietromatera, Nils Holzenberger |
| 15:05 - 15:10 |
Linking Transparency and Accountability: Analysing The Connection Between TikTok's Terms of Service and Moderation Decisions
Leonard Eßer, Gerasimos Spanakis |
| 15:10 - 15:30 | Joint Q&A |
| 15:30 - 16:00 | Break |
| 16:00 - 17:30 | Session 4 |
| 16:00 - 16:05 | Modeling Motivated Reasoning in Law: Evaluating Strategic Role Conditioning in LLM Summarization Eunjung Cho, Alexander Miserlis Hoyle, Yoan Hermstrüwer |
| 16:05 - 16:10 | Domain Adapted Text Summarization with Self-Generated Guidelines Andrianos Michail, Bartosz Rudnikowicz, Pavlos Fragkogiannis, Cristina Kadar |
| 16:10 - 16:15 | Risks and Limits of Automatic Consolidation of Statutes Max Prior, Adrian Hof, Niklas Wais, Matthias Grabmair |
| 16:15 - 16:20 | Unlocking Legal Knowledge: A Multilingual Dataset for Judicial Summarization in Switzerland Luca Rolshoven, Vishvaksenan Rasiah, Srinanda Brügger Bose, Sarah Hostettler, Lara Burkhalter, Matthias Stürmer, Joel Niklaus |
| 16:20 - 16:25 | Extract-Explain-Abstract: A Rhetorical Role-Driven Domain-Specific Summarisation Framework for Indian Legal Documents Veer Chheda, Aaditya Uday Ghaisas, Avantika Sankhe, Dr. Narendra Shekokar |
| 16:25 - 16:45 | Joint Q&A |
| 16:45 - 16:50 | Copyright Infringement by Large Language Models in the EU: Misalignment, Safeguards, and the Path Forward Noah Scharrenberg, Chang Sun |
| 16:50 - 16:55 | Machine Unlearning of Personally Identifiable Information in Large Language Models Dan Parii, Thomas van Osch, Chang Sun |
| 16:55 - 17:00 | Evaluating LLM-Generated Legal Explanations for Regulatory Compliance in Social Media Influencer Marketing Haoyang Gui, Thales Bertaglia, Taylor Annabell, Catalina Goanta, Tjomme Dooper, Gerasimos Spanakis |
| 17:00 - 17:05 | Nine Ways to Break Copyright Law and Why Our LLM Won’t: A Fair Use Aligned Generation Framework Aakash Sen Sharma, Debdeep Sanyal, Priyansh Srivastava, Sundar Athreya H, Shirish Karande, Mohan Kankanhalli, Murari Mandal |
| 17:05 - 17:20 | Joint Q&A |
| 17:20 - 17:30 | Best Presentation Award and Closing |
Organizing Committee
- Nikolaos Aletras - University of Sheffield (UK)
- Leslie Barrett - Bloomberg Law (US)
- Ilias Chalkidis - University of Copenhagen (Denmark)
- Catalina Goanta - Utrecht University (The Netherlands)
- Daniel Preotiuc-Pietro - Bloomberg (US)
- Gerasimos (Jerry) Spanakis - Maastricht University (The Netherlands)
Program Committee
- Sallam Abualhaija - University of Luxembourg (Luxembourg)
- Tomaso Agnoloni - Institute of Legal Information Theory and Technologies (Italy)
- Ion Androutsopoulos - Athens University of Economics and Business (Greece)
- Tom Ault - Bloomberg (US)
- Jaap Baaij - Utrecht University (The Netherlands)
- Ilayda Balaban - Utrecht University (The Netherlands)
- Breck Baldwin - Columbia University (US)
- Claire Barale - University of Edinburgh (UK)
- Thales Bertaglia - Maastricht University (The Netherlands)
- Floris Bex - Utrecht University (The Netherlands)
- Luca Cagliero - Politecnico di Torino (Italy)
- Jiahong Chen - University of Sheffield (UK)
- Odysseas Spyridon Chlapanis - Athens University of Business and Economics (Greece)
- Ashish Chouhan - Heidelberg University & SRH Hochschule Heidelberg (Germany)
- Bram Duivenvoorde - Utrecht University (The Netherlands)
- Dominik Dworniczak - University of Zurich (Switzerland)
- Arthur Dyevre - KU Leuven (Belgium)
- Dimitrios Galanis - Athena Research Center (Greece)
- Piyush Ghai - Relativity (US)
- Ivan Habernal - Technical University of Darmstadt (Germany)
- Ben Hagag - Darrow (Israel)
- Nils Holzenberger - Johns Hopkins University (US)
- Abe Hou - Johns Hopkins University (US)
- Abderrahmane Issam - Maastricht University (The Netherlands)
- Constantinos Karouzos - University of Sheffield (UK)
- Aykut Koç - Bilkent University (Turkey)
- Hellen van der Kroef - Maastricht University (The Netherlands)
- Alice Kwak - Univesity of Arizona (US)
- Tong Liang - Dynosaur Tech (US)
- Ruta Liepina - University of Bologna (Italy)
- Chu Luo - Queen's University (CA)
- Megan Ma - Stanford Law School (US)
- Pawel Maka - Maastricht University (The Netherlands)
- Adam Meyers - New York University (US)
- Jelena Mitrović - University of Passau (Germany) & Institute for AI R&D of Serbia (Serbia)
- Rohan Nanda - Maastricht University (The Netherlands)
- Joel Niklaus - University of Bern (Switzerland)
- Henrik Palmer Olsen - University of Copenhagen (Denmark)
- Katsikouli Panagiota - University of Copenhagen (Denmark)
- Ioannis Panagis - University of Copenhagen (Denmark)
- Anu Pradhan - Bloomberg (US)
- Paulo Quaresma - University of Evora (Portugal)
- Vageesh Saxena - Maastricht University (The Netherlands)
- Yusuf Can Semerci - Maastricht University (The Netherlands)
- Gil Semo - Darrow (Israel)
- Madhavan Seshadri - Bloomberg (US)
- Samyak Sheth - Maastricht University (The Netherlands)
- Dan Simonson - BlackBoiler LLC (US)
- Christoph Sorge - Universität des Saarlandes (Germany)
- Jerrold Soh - Singapore Management University (Singapore)
- Alexandru Sotropa - VU Amsterdam & eMAG (The Netherlands/Romania)
- Ieva Staliunaite - University of Cambridge (UK)
- T.Y.S.S. Santosh - Amazon (US)
- Dimitrios Tsarapatsanis - University of York (UK)
- Kalpana Tyagi - Maastricht University (The Netherlands)
- Gijs Van Dijck - Maastricht University (The Netherlands)
- Jianqiang Wang - University of Buffalo (US)
- Hannes Westermann - Maastricht University (The Netherlands)
- ShanShan Xu - Technical University of Munich (Germany)
- Huiyin Xue - University of Sheffield (UK)
- Marcos Zampieri - Rochester Institute of Technology (US)
- Frederike Zufall - Max Planck Institute for Research on Collective Goods (Germany)
- Miri Zilka - University of Cambridge (UK)