{"total":148,"rows":[{"id":"2205.05131","title":"UL2: Unifying Language Learning Paradigms","created":"2022-05-10","cited_by_count":295,"area":null},{"id":"2307.10928","title":"FLASK: Fine-grained Language Model Evaluation based on Alignment Skill Sets","created":"2023-07-20","cited_by_count":201,"area":"alignment"},{"id":"2201.03533","title":"SCROLLS: Standardized CompaRison Over Long Language Sequences","created":"2022-01-10","cited_by_count":170,"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":"2305.01625","title":"Unlimiformer: Long-Range Transformers with Unlimited Length Input","created":"2023-05-02","cited_by_count":128,"area":null},{"id":"2310.12963","title":"AutoMix: Automatically Mixing Language Models","created":"2023-10-19","cited_by_count":125,"area":null},{"id":"2303.01432","title":"WiCE: Real-World Entailment for Claims in Wikipedia","created":"2023-03-02","cited_by_count":120,"area":null},{"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":"2306.04618","title":"Revisiting Out-of-distribution Robustness in NLP: Benchmark, Analysis, and LLMs Evaluations","created":"2023-06-07","cited_by_count":97,"area":null},{"id":"2303.09752","title":"CoLT5: Faster Long-Range Transformers with Conditional Computation","created":"2023-03-17","cited_by_count":84,"area":null},{"id":"2208.00748","title":"Efficient Long-Text Understanding with Short-Text Models","created":"2022-08-01","cited_by_count":71,"area":null},{"id":"2305.07507","title":"LeXFiles and LegalLAMA: Facilitating English Multinational Legal Language Model Development","created":"2023-05-12","cited_by_count":54,"area":null},{"id":"2204.07447","title":"Stretching Sentence-pair NLI Models to Reason over Long Documents and Clusters","created":"2022-04-15","cited_by_count":44,"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":"2210.05529","title":"An Exploration of Hierarchical Attention Transformers for Efficient Long Document Classification","created":"2022-10-11","cited_by_count":38,"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":"2506.20923","title":"KaLM-Embedding-V2: Superior Training Techniques and Data Inspire A Versatile Embedding Model","created":"2025-06-26","cited_by_count":36,"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":"2402.18334","title":"Learning to Generate Instruction Tuning Datasets for Zero-Shot Task Adaptation","created":"2024-02-28","cited_by_count":27,"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":"2401.16421","title":"Two Stones Hit One Bird: Bilevel Positional Encoding for Better Length Extrapolation","created":"2024-01-29","cited_by_count":24,"area":null},{"id":"2310.13189","title":"Fast and Accurate Factual Inconsistency Detection Over Long Documents","created":"2023-10-19","cited_by_count":23,"area":null},{"id":"2411.05764","title":"FinDVer: Explainable Claim Verification over Long and Hybrid-Content Financial Documents","created":"2024-11-08","cited_by_count":19,"area":null},{"id":"2506.13351","title":"Direct Reasoning Optimization: Token-Level Reasoning Reflectivity Meets Rubric Gates for Unverifiable Tasks","created":"2025-06-16","cited_by_count":18,"area":"lr"},{"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":"2311.16989","title":"ChatGPT's One-year Anniversary: Are Open-Source Large Language Models Catching up?","created":"2023-11-28","cited_by_count":15,"area":null},{"id":"2308.05502","title":"Bringing order into the realm of Transformer-based language models for artificial intelligence and law","created":"2023-08-10","cited_by_count":13,"area":null},{"id":"2310.09107","title":"GLoRE: Evaluating Logical Reasoning of Large Language Models","created":"2023-10-13","cited_by_count":13,"area":"lr"},{"id":"2311.09782","title":"More Samples or More Prompts? Exploring Effective In-Context Sampling for LLM Few-Shot Prompt Engineering","created":"2023-11-16","cited_by_count":13,"area":null},{"id":"2311.09825","title":"Human Still Wins over LLM: An Empirical Study of Active Learning on Domain-Specific Annotation Tasks","created":"2023-11-16","cited_by_count":13,"area":null},{"id":"2402.04335","title":"LegalLens: Leveraging LLMs for Legal Violation Identification in Unstructured Text","created":"2024-02-06","cited_by_count":12,"area":null},{"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":"2406.12928","title":"Evaluating the Generalization Ability of Quantized LLMs: Benchmark, Analysis, and Toolbox","created":"2024-06-15","cited_by_count":11,"area":null},{"id":"2407.07799","title":"Attribute or Abstain: Large Language Models as Long Document Assistants","created":"2024-07-10","cited_by_count":11,"area":null},{"id":"2407.12797","title":"CEBench: A Benchmarking Toolkit for the Cost-Effectiveness of LLM Pipelines","created":"2024-06-20","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":"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":"2509.05218","title":"HoPE: Hyperbolic Rotary Positional Encoding for Stable Long-Range Dependency Modeling in Large Language Models","created":"2025-09-05","cited_by_count":10,"area":null},{"id":"2407.03545","title":"On Evaluating Explanation Utility for Human-AI Decision Making in NLP","created":"2024-07-03","cited_by_count":9,"area":null},{"id":"2507.20208","title":"From Benchmarks to Skills: Low-Rank Factors for LLM Evaluation","created":"2025-07-27","cited_by_count":9,"area":null},{"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":"2405.11877","title":"A Novel Cartography-Based Curriculum Learning Method Applied on RoNLI: The First Romanian Natural Language Inference Corpus","created":"2024-05-20","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":"2604.10079","title":"Why Supervised Fine-Tuning Fails to Learn: A Systematic Study of Incomplete Learning in Large Language Models","created":"2026-04-11","cited_by_count":8,"area":null},{"id":"2305.16259","title":"Neural Natural Language Processing for Long Texts: A Survey on Classification and Summarization","created":"2023-05-25","cited_by_count":7,"area":null},{"id":"2305.19585","title":"LAIT: Efficient Multi-Segment Encoding in Transformers with Layer-Adjustable Interaction","created":"2023-05-31","cited_by_count":7,"area":null},{"id":"2407.16615","title":"Lawma: The Power of Specialization for Legal Annotation","created":"2024-07-23","cited_by_count":7,"area":null},{"id":"2510.03418","title":"LegalWiz: A Multi-Agent Generation Framework for Contradiction Detection in Legal Documents","created":"2025-10-03","cited_by_count":7,"area":"rag"},{"id":"2212.03222","title":"LawngNLI: A Long-Premise Benchmark for In-Domain Generalization from Short to Long Contexts and for Implication-Based Retrieval","created":"2022-12-06","cited_by_count":6,"area":null},{"id":"2305.04241","title":"Vcc: Scaling Transformers to 128K Tokens or More by Prioritizing Important Tokens","created":"2023-05-07","cited_by_count":6,"area":null},{"id":"2305.14847","title":"Drafting Event Schemas using Language Models","created":"2023-05-24","cited_by_count":6,"area":null},{"id":"2407.08330","title":"HDT: Hierarchical Document Transformer","created":"2024-07-11","cited_by_count":6,"area":null},{"id":"2408.03325","title":"CoverBench: A Challenging Benchmark for Complex Claim Verification","created":"2024-08-06","cited_by_count":6,"area":null},{"id":"2510.13494","title":"LiteraryQA: Towards Effective Evaluation of Long-document Narrative QA","created":"2025-10-15","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":"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":"2409.13684","title":"The FIX Benchmark: Extracting Features Interpretable to eXperts","created":"2024-09-20","cited_by_count":5,"area":null},{"id":"2410.12064","title":"LegalLens Shared Task 2024: Legal Violation Identification in Unstructured Text","created":"2024-10-15","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":"2510.16458","title":"Agree, Disagree, Explain: Decomposing Human Label Variation in NLI through the Lens of Explanations","created":"2025-10-18","cited_by_count":5,"area":null},{"id":"2602.01766","title":"CoMeT: Collaborative Memory Transformer for Efficient Long Context Modeling","created":"2026-02-02","cited_by_count":5,"area":null},{"id":"2605.17467","title":"VerifyMAS: Hypothesis Verification for Failure Attribution in LLM Multi-Agent Systems","created":"2026-05-17","cited_by_count":5,"area":"agents"},{"id":"2209.13953","title":"ArNLI: Arabic Natural Language Inference for Entailment and Contradiction Detection","created":"2022-09-28","cited_by_count":4,"area":null},{"id":"2305.15045","title":"SETI: Systematicity Evaluation of Textual Inference","created":"2023-05-24","cited_by_count":4,"area":null},{"id":"2306.09918","title":"No Strong Feelings One Way or Another: Re-operationalizing Neutrality in Natural Language Inference","created":"2023-06-16","cited_by_count":4,"area":"lr"},{"id":"2310.18431","title":"SDOH-NLI: a Dataset for Inferring Social Determinants of Health from Clinical Notes","created":"2023-10-27","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":"2505.14607","title":"sudoLLM: On Multi-role Alignment of Language Models","created":"2025-05-20","cited_by_count":4,"area":"alignment"},{"id":"2511.07380","title":"Mining Useful General Data for Low-Resource Domain Adaptation","created":"2025-11-10","cited_by_count":4,"area":null},{"id":"2610.02076","title":"LLM-as-Jev: LLMs Are Already Jev-Style Decision Models -- When and How to Fine-Tune Them","created":"2026-10-01","cited_by_count":4,"area":null},{"id":"2502.06316","title":"Can AI Examine Novelty of Patents?: Novelty Evaluation Based on the Correspondence between Patent Claim and Prior Art","created":"2025-02-10","cited_by_count":3,"area":null},{"id":"2504.16188","title":"FinNLI: Novel Dataset for Multi-Genre Financial Natural Language Inference Benchmarking","created":"2025-04-22","cited_by_count":3,"area":null},{"id":"2506.21601","title":"Hierarchical Patch Compression for ColPali: Efficient Multi-Vector Document Retrieval with Dynamic Pruning and Quantization","created":"2025-06-19","cited_by_count":3,"area":null},{"id":"2507.20783","title":"On The Role of Pretrained Language Models in General-Purpose Text Embeddings: A Survey","created":"2025-07-28","cited_by_count":3,"area":null},{"id":"2509.22472","title":"Evaluating the Limits of Large Language Models in Multilingual Legal Reasoning","created":"2025-09-26","cited_by_count":3,"area":"lr"},{"id":"2602.21103","title":"Prompt-Level Distillation: A Non-Parametric Alternative to Model Fine-Tuning for Efficient Reasoning","created":"2026-02-24","cited_by_count":3,"area":"lr"},{"id":"2604.10740","title":"RCBSF: A Multi-Agent Framework for Automated Contract Revision via Stackelberg Game","created":"2026-04-12","cited_by_count":3,"area":"agents"},{"id":"2606.16118","title":"Know Your Limits : On the Faithfulness of LLMs as Solvers and Autoformalizers in Legal Reasoning","created":"2026-06-15","cited_by_count":3,"area":"lr"},{"id":"2210.13086","title":"Legal-Tech Open Diaries: Lesson learned on how to develop and deploy light-weight models in the era of humongous Language Models","created":"2022-10-24","cited_by_count":2,"area":null},{"id":"2211.08112","title":"An Efficient Active Learning Pipeline for Legal Text Classification","created":"2022-11-15","cited_by_count":2,"area":null},{"id":"2404.02269","title":"Extracting Norms from Contracts Via ChatGPT: Opportunities and Challenges","created":"2024-04-02","cited_by_count":2,"area":null},{"id":"2504.12324","title":"Cross-Document Cross-Lingual NLI via RST-Enhanced Graph Fusion and Interpretability Prediction","created":"2025-04-11","cited_by_count":2,"area":null},{"id":"2506.04636","title":"CHANCERY: Evaluating Corporate Governance Reasoning Capabilities in Language Models","created":"2025-06-05","cited_by_count":2,"area":"lr"},{"id":"2607.23815","title":"Kalypso: Relational LLM Serving","created":"2026-07-26","cited_by_count":2,"area":"inference"},{"id":"2608.28607","title":"RegDivergence-101: An LLM Benchmark for Cross-Jurisdiction Regulatory Contradiction Detection in Life Sciences","created":"2026-07-08","cited_by_count":2,"area":null},{"id":"2210.16989","title":"Validity Assessment of Legal Will Statements as Natural Language Inference","created":"2022-10-30","cited_by_count":1,"area":null},{"id":"2310.04592","title":"From Nuisance to News Sense: Augmenting the News with Cross-Document Evidence and Context","created":"2023-10-06","cited_by_count":1,"area":null},{"id":"2409.00077","title":"Are LLM-based methods good enough for detecting unfair terms of service?","created":"2024-08-24","cited_by_count":1,"area":null},{"id":"2505.19191","title":"Misleading through Inconsistency: A Benchmark for Political Inconsistencies Detection","created":"2025-05-25","cited_by_count":1,"area":null},{"id":"2506.00608","title":"PAKTON: A Multi-Agent Framework for Question Answering in Long Legal Agreements","created":"2025-05-31","cited_by_count":1,"area":null},{"id":"2507.01234","title":"The Medium Is Not the Message: Deconfounding Document Embeddings via Linear Concept Erasure","created":"2025-07-01","cited_by_count":1,"area":null},{"id":"2511.06618","title":"GRAPH-GRPO-LEX: Contract Graph Modeling and Reinforcement Learning with Group Relative Policy Optimization","created":"2025-11-10","cited_by_count":1,"area":"lr"},{"id":"2511.19935","title":"EfficientXpert: Efficient Domain Adaptation for Large Language Models via Propagation-Aware Pruning","created":"2025-11-25","cited_by_count":1,"area":null},{"id":"2601.06164","title":"Contract2Plan: Verified Contract-Grounded Retrieval-Augmented Optimization for BOM-Aware Procurement and Multi-Echelon Inventory Planning","created":"2026-01-07","cited_by_count":1,"area":null},{"id":"2601.15267","title":"Evaluation of Large Language Models in Legal Applications: Challenges, Methods, and Future Directions","created":"2026-01-21","cited_by_count":1,"area":null},{"id":"2603.14257","title":"Automatic Inter-document Multi-hop Scientific QA Generation","created":"2026-03-15","cited_by_count":1,"area":null},{"id":"2604.04565","title":"PassiveQA: A Three-Action Framework for Epistemically Calibrated Question Answering via Supervised Finetuning","created":"2026-04-06","cited_by_count":1,"area":"rag"},{"id":"2605.00116","title":"ViLegalNLI: Natural Language Inference for Vietnamese Legal Texts","created":"2026-04-30","cited_by_count":1,"area":null},{"id":"2605.05532","title":"A Few Good Clauses: Comparing LLMs vs Domain-Trained Small Language Models on Structured Contract Extraction","created":"2026-05-07","cited_by_count":1,"area":null}],"next_cursor":"100"}