{"total":236,"rows":[{"id":"2307.03109","title":"A Survey on Evaluation of Large Language Models","created":"2023-07-06","cited_by_count":1242,"area":null},{"id":"2403.19887","title":"Jamba: A Hybrid Transformer-Mamba Language Model","created":"2024-03-28","cited_by_count":401,"area":"moe"},{"id":"2308.11462","title":"LegalBench: A Collaboratively Built Benchmark for Measuring Legal Reasoning in Large Language Models","created":"2023-08-20","cited_by_count":336,"area":"lr"},{"id":"2110.00976","title":"LexGLUE: A Benchmark Dataset for Legal Language Understanding in English","created":"2021-10-03","cited_by_count":310,"area":null},{"id":"2307.11088","title":"L-Eval: Instituting Standardized Evaluation for Long Context Language Models","created":"2023-07-20","cited_by_count":233,"area":null},{"id":"2208.03306","title":"Branch-Train-Merge: Embarrassingly Parallel Training of Expert Language Models","created":"2022-08-05","cited_by_count":191,"area":null},{"id":"2110.01799","title":"ContractNLI: A Dataset for Document-level Natural Language Inference for Contracts","created":"2021-10-05","cited_by_count":148,"area":null},{"id":"2108.05036","title":"DEMix Layers: Disentangling Domains for Modular Language Modeling","created":"2021-08-11","cited_by_count":132,"area":null},{"id":"2412.19442","title":"A Survey on Large Language Model Acceleration based on KV Cache Management","created":"2024-12-27","cited_by_count":131,"area":"lr"},{"id":"2408.10343","title":"LegalBench-RAG: A Benchmark for Retrieval-Augmented Generation in the Legal Domain","created":"2024-08-19","cited_by_count":118,"area":"rag"},{"id":"2407.11005","title":"RAGBench: Explainable Benchmark for Retrieval-Augmented Generation Systems","created":"2024-06-25","cited_by_count":117,"area":"rag"},{"id":"2105.03887","title":"Lawformer: A Pre-trained Language Model for Chinese Legal Long Documents","created":"2021-05-09","cited_by_count":116,"area":null},{"id":"2207.00220","title":"Pile of Law: Learning Responsible Data Filtering from the Law and a 256GB Open-Source Legal Dataset","created":"2022-07-01","cited_by_count":113,"area":null},{"id":"2109.00904","title":"MultiEURLEX -- A multi-lingual and multi-label legal document classification dataset for zero-shot cross-lingual transfer","created":"2021-09-02","cited_by_count":90,"area":null},{"id":"2212.06470","title":"Position: Considerations for Differentially Private Learning with Large-Scale Public Pretraining","created":"2022-12-13","cited_by_count":88,"area":null},{"id":"2308.06374","title":"Large Language Models and Knowledge Graphs: Opportunities and Challenges","created":"2023-08-11","cited_by_count":71,"area":null},{"id":"2212.02199","title":"Legal Prompt Engineering for Multilingual Legal Judgement Prediction","created":"2022-12-05","cited_by_count":55,"area":null},{"id":"2410.12189","title":"DocETL: Agentic Query Rewriting and Evaluation for Complex Document Processing","created":"2024-10-16","cited_by_count":52,"area":"agents"},{"id":"2206.10883","title":"Multi-LexSum: Real-World Summaries of Civil Rights Lawsuits at Multiple Granularities","created":"2022-06-22","cited_by_count":47,"area":null},{"id":"2305.09955","title":"Knowledge Card: Filling LLMs' Knowledge Gaps with Plug-in Specialized Language Models","created":"2023-05-17","cited_by_count":46,"area":null},{"id":"2206.05224","title":"A Multi-Task Benchmark for Korean Legal Language Understanding and Judgement Prediction","created":"2022-06-10","cited_by_count":44,"area":null},{"id":"2501.08828","title":"MMDocIR: Benchmarking Multimodal Retrieval for Long Documents","created":"2025-01-15","cited_by_count":43,"area":null},{"id":"2410.21306","title":"Natural Language Processing for the Legal Domain: A Survey of Tasks, Datasets, Models, and Challenges","created":"2024-10-25","cited_by_count":42,"area":null},{"id":"2108.11792","title":"A Statutory Article Retrieval Dataset in French","created":"2021-08-26","cited_by_count":40,"area":null},{"id":"2502.03261","title":"CARROT: A Cost Aware Rate Optimal Router","created":"2025-02-05","cited_by_count":39,"area":null},{"id":"2203.08556","title":"LEVEN: A Large-Scale Chinese Legal Event Detection Dataset","created":"2022-03-16","cited_by_count":36,"area":null},{"id":"2207.04043","title":"The Harvard USPTO Patent Dataset: A Large-Scale, Well-Structured, and Multi-Purpose Corpus of Patent Applications","created":"2022-07-08","cited_by_count":33,"area":null},{"id":"2301.00876","title":"MAUD: An Expert-Annotated Legal NLP Dataset for Merger Agreement Understanding","created":"2023-01-02","cited_by_count":33,"area":null},{"id":"2305.04417","title":"Unlocking Practical Applications in Legal Domain: Evaluation of GPT for Zero-Shot Semantic Annotation of Legal Texts","created":"2023-05-08","cited_by_count":33,"area":null},{"id":"2508.04183","title":"Characterizing Deep Research: A Benchmark and Formal Definition","created":"2025-08-06","cited_by_count":30,"area":null},{"id":"2407.00402","title":"Is It Really Long Context if All You Need Is Retrieval? Towards Genuinely Difficult Long Context NLP","created":"2024-06-29","cited_by_count":27,"area":null},{"id":"2412.02592","title":"OCR Hinders RAG: Evaluating the Cascading Impact of OCR on Retrieval-Augmented Generation","created":"2024-12-03","cited_by_count":26,"area":"rag"},{"id":"2503.01747","title":"Position: Don't Use the CLT in LLM Evals With Fewer Than a Few Hundred Datapoints","created":"2025-03-03","cited_by_count":23,"area":null},{"id":"2306.02051","title":"A Comprehensive Survey on Relation Extraction: Recent Advances and New Frontiers","created":"2023-06-03","cited_by_count":22,"area":null},{"id":"2206.14157","title":"How to Steer Your Adversary: Targeted and Efficient Model Stealing Defenses with Gradient Redirection","created":"2022-06-28","cited_by_count":21,"area":null},{"id":"2506.12364","title":"MM-R5: MultiModal Reasoning-Enhanced ReRanker via Reinforcement Learning for Document Retrieval","created":"2025-06-14","cited_by_count":21,"area":"lr"},{"id":"2306.01966","title":"GENTLE: A Genre-Diverse Multilayer Challenge Set for English NLP and Linguistic Evaluation","created":"2023-06-03","cited_by_count":19,"area":null},{"id":"2406.11044","title":"Evaluating the Performance of Large Language Models via Debates","created":"2024-06-16","cited_by_count":19,"area":null},{"id":"2402.10400","title":"Chain of Logic: Rule-Based Reasoning with Large Language Models","created":"2024-02-16","cited_by_count":18,"area":"lr"},{"id":"2209.06120","title":"LegalBench: Prototyping a Collaborative Benchmark for Legal Reasoning","created":"2022-09-13","cited_by_count":17,"area":null},{"id":"2211.00582","title":"ClassActionPrediction: A Challenging Benchmark for Legal Judgment Prediction of Class Action Cases in the US","created":"2022-11-01","cited_by_count":17,"area":null},{"id":"2309.12269","title":"The Cambridge Law Corpus: A Dataset for Legal AI Research","created":"2023-09-21","cited_by_count":14,"area":null},{"id":"2507.17131","title":"Enabling Self-Improving Agents to Learn at Test Time With Human-In-The-Loop Guidance","created":"2025-07-23","cited_by_count":14,"area":"agents"},{"id":"2211.17135","title":"BudgetLongformer: Can we Cheaply Pretrain a SotA Legal Language Model From Scratch?","created":"2022-11-30","cited_by_count":13,"area":null},{"id":"2311.12850","title":"PrivImage: Differentially Private Synthetic Image Generation using Diffusion Models with Semantic-Aware Pretraining","created":"2023-10-19","cited_by_count":13,"area":"diffusion"},{"id":"2505.14661","title":"Abacus: A Cost-Based Optimizer for Semantic Operator Systems","created":"2025-05-20","cited_by_count":13,"area":null},{"id":"2310.14880","title":"Can ChatGPT Perform Reasoning Using the IRAC Method in Analyzing Legal Scenarios Like a Lawyer?","created":"2023-10-23","cited_by_count":12,"area":"lr"},{"id":"2510.06999","title":"Towards Reliable Retrieval in RAG Systems for Large Legal Datasets","created":"2025-10-08","cited_by_count":12,"area":"rag"},{"id":"2601.05163","title":"DocDancer: Towards Agentic Document-Grounded Information Seeking","created":"2026-01-08","cited_by_count":12,"area":"agents"},{"id":"2305.01645","title":"Distill or Annotate? Cost-Efficient Fine-Tuning of Compact Models","created":"2023-05-02","cited_by_count":11,"area":null},{"id":"2405.14211","title":"ChronosLex: Time-aware Incremental Training for Temporal Generalization of Legal Classification Tasks","created":"2024-05-23","cited_by_count":11,"area":null},{"id":"2501.06582","title":"ACORD: An Expert-Annotated Retrieval Dataset for Legal Contract Drafting","created":"2025-01-11","cited_by_count":11,"area":null},{"id":"2609.27678","title":"Same Scores, Different Decisions: Evaluating JEV and Language Models for Legal Document Understanding","created":"2026-09-23","cited_by_count":11,"area":null},{"id":"2311.09693","title":"BLT: Can Large Language Models Handle Basic Legal Text?","created":"2023-11-16","cited_by_count":10,"area":null},{"id":"2404.00399","title":"Aurora-M: Open Source Continual Pre-training for Multilingual Language and Code","created":"2024-03-30","cited_by_count":10,"area":null},{"id":"2404.02127","title":"LawInstruct: A Resource for Studying Language Model Adaptation to the Legal Domain","created":"2024-04-02","cited_by_count":10,"area":null},{"id":"2509.09969","title":"Large Language Models Meet Legal Artificial Intelligence: A Survey","created":"2025-09-12","cited_by_count":10,"area":null},{"id":"2505.00263","title":"EnronQA: Towards Personalized RAG over Private Documents","created":"2025-05-01","cited_by_count":9,"area":"rag"},{"id":"2508.03080","title":"ContractEval: Benchmarking LLMs for Clause-Level Legal Risk Identification in Commercial Contracts","created":"2025-08-05","cited_by_count":9,"area":null},{"id":"2508.07827","title":"Evaluating Large Language Models as Expert Annotators","created":"2025-08-11","cited_by_count":9,"area":"lr"},{"id":"2205.15172","title":"Billions of Parameters Are Worth More Than In-domain Training Data: A case study in the Legal Case Entailment Task","created":"2022-05-30","cited_by_count":8,"area":null},{"id":"2310.14346","title":"The Law and NLP: Bridging Disciplinary Disconnects","created":"2023-10-22","cited_by_count":8,"area":null},{"id":"2403.04791","title":"LLM vs. Lawyers: Identifying a Subset of Summary Judgments in a Large UK Case Law Dataset","created":"2024-03-04","cited_by_count":8,"area":null},{"id":"2410.09527","title":"LexSumm and LexT5: Benchmarking and Modeling Legal Summarization Tasks in English","created":"2024-10-12","cited_by_count":8,"area":null},{"id":"2510.02557","title":"Orchestrating Human-AI Teams: The Manager Agent as a Unifying Research Challenge","created":"2025-10-02","cited_by_count":8,"area":"agents"},{"id":"2210.08855","title":"PeerDA: Data Augmentation via Modeling Peer Relation for Span Identification Tasks","created":"2022-10-17","cited_by_count":7,"area":null},{"id":"2211.12752","title":"Agent-Specific Deontic Modality Detection in Legal Language","created":"2022-11-23","cited_by_count":7,"area":"agents"},{"id":"2407.16615","title":"Lawma: The Power of Specialization for Legal Annotation","created":"2024-07-23","cited_by_count":7,"area":null},{"id":"2510.08710","title":"Thinking Longer, Not Always Smarter: Evaluating LLM Capabilities in Hierarchical Legal Reasoning","created":"2025-10-09","cited_by_count":7,"area":"lr"},{"id":"2604.14572","title":"Corpus2Skill: Distilling Enterprise Knowledge into Navigable Agent Skills for QA and RAG","created":"2026-04-16","cited_by_count":7,"area":"rag"},{"id":"2302.03222","title":"Bringing the State-of-the-Art to Customers: A Neural Agent Assistant Framework for Customer Service Support","created":"2023-02-07","cited_by_count":6,"area":null},{"id":"2312.08618","title":"Zebra: Extending Context Window with Layerwise Grouped Local-Global Attention","created":"2023-12-14","cited_by_count":6,"area":null},{"id":"2409.14473","title":"A Large Language Model and Denoising Diffusion Framework for Targeted Design of Microstructures with Commands in Natural Language","created":"2024-09-22","cited_by_count":6,"area":"diffusion"},{"id":"2504.03101","title":"Single-Pass Document Scanning for Question Answering","created":"2025-04-04","cited_by_count":6,"area":null},{"id":"2508.05534","title":"CoCoLex: Confidence-guided Copy-based Decoding for Grounded Legal Text Generation","created":"2025-08-07","cited_by_count":6,"area":null},{"id":"2510.01474","title":"AIReg-Bench: Benchmarking Language Models That Assess AI Regulation Compliance","created":"2025-10-01","cited_by_count":6,"area":null},{"id":"2510.19365","title":"The Massive Legal Embedding Benchmark (MLEB)","created":"2025-10-22","cited_by_count":6,"area":null},{"id":"2510.20941","title":"Do LLMs Truly Understand When a Precedent Is Overruled?","created":"2025-10-23","cited_by_count":6,"area":null},{"id":"2511.00340","title":"Better Call CLAUSE: A Discrepancy Benchmark for Auditing LLMs Legal Reasoning Capabilities","created":"2025-11-01","cited_by_count":6,"area":"lr"},{"id":"2604.12352","title":"MultiDocFusion: Hierarchical and Multimodal Chunking Pipeline for Enhanced RAG on Long Industrial Documents","created":"2026-04-14","cited_by_count":6,"area":null},{"id":"2210.08697","title":"ConReader: Exploring Implicit Relations in Contracts for Contract Clause Extraction","created":"2022-10-17","cited_by_count":5,"area":null},{"id":"2211.11724","title":"Legal and Political Stance Detection of SCOTUS Language","created":"2022-11-21","cited_by_count":5,"area":null},{"id":"2312.15551","title":"On the Benefits of Public Representations for Private Transfer Learning under Distribution Shift","created":"2023-12-24","cited_by_count":5,"area":null},{"id":"2406.00975","title":"Luna: An Evaluation Foundation Model to Catch Language Model Hallucinations with High Accuracy and Low Cost","created":"2024-06-03","cited_by_count":5,"area":null},{"id":"2406.13217","title":"Automating IRAC Analysis in Malaysian Contract Law using a Semi-Structured Knowledge Base","created":"2024-06-19","cited_by_count":5,"area":null},{"id":"2505.12837","title":"The Hidden Structure -- Improving Legal Document Understanding Through Explicit Text Formatting","created":"2025-05-19","cited_by_count":5,"area":null},{"id":"2505.16014","title":"Ranking Free RAG: Replacing Re-ranking with Selection in RAG for Sensitive Domains","created":"2025-05-21","cited_by_count":5,"area":"rag"},{"id":"2107.08128","title":"The Law of Large Documents: Understanding the Structure of Legal Contracts Using Visual Cues","created":"2021-07-16","cited_by_count":4,"area":null},{"id":"2205.13434","title":"Jointly Learning Span Extraction and Sequence Labeling for Information Extraction from Business Documents","created":"2022-05-26","cited_by_count":4,"area":null},{"id":"2403.20101","title":"RealKIE: Five Novel Datasets for Enterprise Key Information Extraction","created":"2024-03-29","cited_by_count":4,"area":null},{"id":"2406.06809","title":"AGB-DE: A Corpus for the Automated Legal Assessment of Clauses in German Consumer Contracts","created":"2024-06-10","cited_by_count":4,"area":null},{"id":"2412.04119","title":"GRAF: Graph Retrieval Augmented by Facts for Romanian Legal Multi-Choice Question Answering","created":"2024-12-05","cited_by_count":4,"area":"rag"},{"id":"2502.12509","title":"LegalCore: A Dataset for Event Coreference Resolution in Legal Documents","created":"2025-02-18","cited_by_count":4,"area":null},{"id":"2504.18762","title":"SynLexLM: Scaling Legal LLMs with Synthetic Data and Curriculum Learning","created":"2025-04-26","cited_by_count":4,"area":"synth"},{"id":"2505.14607","title":"sudoLLM: On Multi-role Alignment of Language Models","created":"2025-05-20","cited_by_count":4,"area":"alignment"},{"id":"2507.19995","title":"VLQA: The First Comprehensive, Large, and High-Quality Vietnamese Dataset for Legal Question Answering","created":"2025-07-26","cited_by_count":4,"area":null},{"id":"2510.08111","title":"Evaluating LLM-Generated Legal Explanations for Regulatory Compliance in Social Media Influencer Marketing","created":"2025-10-09","cited_by_count":4,"area":null},{"id":"2601.04758","title":"PILOT-Bench: A Benchmark for Legal Reasoning in the Patent Domain with IRAC-Aligned Classification Tasks","created":"2026-01-08","cited_by_count":4,"area":"lr"},{"id":"2211.01692","title":"Data-efficient End-to-end Information Extraction for Statistical Legal Analysis","created":"2022-11-03","cited_by_count":3,"area":null},{"id":"2212.08967","title":"Foundation models in brief: A historical, socio-technical focus","created":"2022-12-17","cited_by_count":3,"area":null}],"next_cursor":"100"}