NLLP 2024 Workshop @ EMNLP 2024
Miami, FL, 16 November 2024
Website: nllpw.org/workshop
Twitter: x.com/nllpworkshop
__________
=== Session 1 (Chair: Jerry Spanakis)
00:00:00 - Workshop Introduction
00:13:30 - Summarizing Long Regulatory Documents with a Multi-Step Pipeline
00:19:50 - Towards an Automated Pointwise Evaluation Metric for Generated Long-Form Legal Summaries
00:25:50 - Cross Examine: An Ensemble-based approach to leverage Large Language Models for Legal Text Analytics
00:32:45 - LexSumm and LexT5: Benchmarking and Modeling Legal Summarization Tasks in English
00:36:50 - Algorithm for Automatic Legislative Text Consolidation
00:42:40 - Q&A
00:52:00 - LeGen: Complex Information Extraction from Legal Sentences using Generative Models
00:59:25 - Information Extraction for Planning Court Cases
01:08:00 - Automated Anonymization of Parole Hearing Transcripts
01:14:00 - BLT: Can Large Language Models Handle Basic Legal Text?
01:20:20 - Classify First, and Then Extract: Prompt Chaining Technique for Information Extraction
01:25:40 - HiCuLR: Hierarchical Curriculum Learning for Rhetorical Role Labeling of Legal Documents
01:30:30 - Q&A
=== Session 2 (Chair: Leslie Barrett)
01:37:05 - Rethinking Legal Judgement Prediction in a Realistic Scenario in the Era of Large Language Models
01:46:05 - The CLC-UKET Dataset: Benchmarking Case Outcome Prediction for the UK Employment Tribunal
01:52:40 - Transductive Legal Judgment Prediction Combining BERT Embeddings with Delaunay-Based GNNs
02:01:10 - Comparative Study of Explainability Methods for Legal Outcome Prediction
02:06:30 - Incorporating Precedents for Legal Judgement Prediction on European Court of Human Rights Cases
02:11:55 - The Craft of Selective Prediction: Towards Reliable Case Outcome Classification - An Empirical Study on European Court of Human Rights Cases
02:18:15 - Q&A
02:31:15 - Attributed Question Answering for Preconditions in the Dutch Law
02:38:20 - Measuring the Groundedness of Legal Question-Answering Systems
02:44:20 - Q&A
=== Session 3 (Chair: Jerry Spanakis)
02:53:00 - Keynote Talk: Omri Ben-Shahar - Privacy Protection, At What Cost?
03:56:20 - Shared Task: Enhancing Legal Violation Identification with LLMs and Deep Learning Techniques: Achievements in the LegalLens 2024 Competition
04:12:50 - LegalLens: Masala Chai Group Submission
04:19:45 - uOttawa at LegalLens-2024: Transformer-based Classification Experiments
=== Session 4 (Chair: Daniel Preotiuc-Pietro)
04:27:50 - LLMs to the Rescue: Explaining DSA Statements of Reason with Platform's Terms of Services
04:36:40 - Enhancing Contract Negotiations with LLM-Based Legal Document Comparison
04:43:40 - Multi-Property Multi-Label Documents Metadata Recommendation based on Encoder Embeddings
04:49:55 - CLERC: A Dataset for U. S. Legal Case Retrieval and Retrieval-Augmented Analysis Generation
04:55:35 - Empowering Air Travelers: A Chatbot for Canadian Air Passenger Rights
05:05:40 - The impact of formulaic language in the Court of Justice of the European Union on the performance of lexical and dense retrieval methods
05:12:10 - Q&A
05:20:10 - Gaps or Hallucinations? Scrutinizing Machine-Generated Legal Analysis for Fine-grained Text Evaluations
05:27:40 - Towards Supporting Legal Argumentation with NLP: Is More Data Really All You Need?
05:36:30 - How Many Van Goghs Does It Take to Van Gogh? Finding the Imitation Threshold
05:42:55 - Misinformation with Legal Consequences (MisLC): A New Task Towards Harnessing Societal Harm of Misinformation
05:48:50 - LAR-ECHR: A New Legal Argument Reasoning Task and Dataset for Cases of the European Court of Human Rights
05:55:30 - Developing a Pragmatic Benchmark for Assessing Korean Legal Language Understanding in Large Language Models
===
06:02:50 - Closing & Best Presentation Award