{"total":223,"rows":[{"id":"2402.14992","title":"tinyBenchmarks: evaluating LLMs with fewer examples","created":"2024-02-22","cited_by_count":310,"area":null},{"id":"2310.07521","title":"Survey on Factuality in Large Language Models: Knowledge, Retrieval and Domain-Specificity","created":"2023-10-11","cited_by_count":206,"area":null},{"id":"2312.02783","title":"Large Language Models on Graphs: A Comprehensive Survey","created":"2023-12-05","cited_by_count":192,"area":null},{"id":"2405.20362","title":"Hallucination-Free? Assessing the Reliability of Leading AI Legal Research Tools","created":"2024-05-30","cited_by_count":176,"area":null},{"id":"2401.01301","title":"Large Legal Fictions: Profiling Legal Hallucinations in Large Language Models","created":"2024-01-02","cited_by_count":150,"area":null},{"id":"2309.16289","title":"LawBench: Benchmarking Legal Knowledge of Large Language Models","created":"2023-09-28","cited_by_count":117,"area":null},{"id":"2309.07852","title":"ExpertQA: Expert-Curated Questions and Attributed Answers","created":"2023-09-14","cited_by_count":97,"area":null},{"id":"2406.05761","title":"The BiGGen Bench: A Principled Benchmark for Fine-grained Evaluation of Language Models with Language Models","created":"2024-06-09","cited_by_count":93,"area":null},{"id":"2310.12321","title":"A Survey of GPT-3 Family Large Language Models Including ChatGPT and GPT-4","created":"2023-10-04","cited_by_count":81,"area":null},{"id":"2311.08596","title":"Are You Sure? Challenging LLMs Leads to Performance Drops in The FlipFlop Experiment","created":"2023-11-14","cited_by_count":77,"area":null},{"id":"2402.09880","title":"Inadequacies of Large Language Model Benchmarks in the Era of Generative Artificial Intelligence","created":"2024-02-15","cited_by_count":68,"area":null},{"id":"2506.18123","title":"RoboArena: Distributed Real-World Evaluation of Generalist Robot Policies","created":"2025-06-22","cited_by_count":64,"area":null},{"id":"2402.01864","title":"(A)I Am Not a Lawyer, But...: Engaging Legal Experts towards Responsible LLM Policies for Legal Advice","created":"2024-02-02","cited_by_count":63,"area":null},{"id":"2510.17516","title":"SimBench: Benchmarking the Ability of Large Language Models to Simulate Human Behaviors","created":"2025-10-20","cited_by_count":52,"area":null},{"id":"2409.20288","title":"LexEval: A Comprehensive Chinese Legal Benchmark for Evaluating Large Language Models","created":"2024-09-30","cited_by_count":37,"area":null},{"id":"2602.16763","title":"When AI Benchmarks Plateau: A Systematic Study of Benchmark Saturation","created":"2026-02-18","cited_by_count":33,"area":null},{"id":"2412.04692","title":"Smoothie: Label Free Language Model Routing","created":"2024-12-06","cited_by_count":31,"area":null},{"id":"2406.08587","title":"CS-Bench: A Comprehensive Benchmark for Large Language Models towards Computer Science Mastery","created":"2024-06-12","cited_by_count":30,"area":null},{"id":"2505.14963","title":"MedBrowseComp: Benchmarking Medical Deep Research and Computer Use","created":"2025-05-20","cited_by_count":30,"area":null},{"id":"2506.07673","title":"How Benchmark Prediction from Fewer Data Misses the Mark","created":"2025-06-09","cited_by_count":28,"area":null},{"id":"2410.11163","title":"Model Swarms: Collaborative Search to Adapt LLM Experts via Swarm Intelligence","created":"2024-10-15","cited_by_count":27,"area":null},{"id":"2401.16212","title":"Better Call GPT, Comparing Large Language Models Against Lawyers","created":"2024-01-24","cited_by_count":26,"area":null},{"id":"2410.03492","title":"Towards Reproducible LLM Evaluation: Quantifying Uncertainty in LLM Benchmark Scores","created":"2024-10-04","cited_by_count":25,"area":null},{"id":"2410.15319","title":"Causality for Large Language Models","created":"2024-10-20","cited_by_count":25,"area":null},{"id":"2412.07951","title":"From Lived Experience to Insight: Unpacking the Psychological Risks of Using AI Conversational Agents","created":"2024-12-10","cited_by_count":25,"area":null},{"id":"2406.14322","title":"Mind the Privacy Unit! User-Level Differential Privacy for Language Model Fine-Tuning","created":"2024-06-20","cited_by_count":24,"area":null},{"id":"2510.18941","title":"ProfBench: Multi-Domain Rubrics requiring Professional Knowledge to Answer and Judge","created":"2025-10-21","cited_by_count":24,"area":null},{"id":"2508.01059","title":"Llama-3.1-FoundationAI-SecurityLLM-8B-Instruct Technical Report","created":"2025-08-01","cited_by_count":23,"area":null},{"id":"2510.02263","title":"RLAD: Training LLMs to Discover Abstractions for Solving Reasoning Problems","created":"2025-10-02","cited_by_count":21,"area":null},{"id":"2504.01833","title":"YourBench: Easy Custom Evaluation Sets for Everyone","created":"2025-04-02","cited_by_count":20,"area":null},{"id":"2404.13957","title":"How Well Can LLMs Echo Us? Evaluating AI Chatbots' Role-Play Ability with ECHO","created":"2024-04-22","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":"2407.16695","title":"Stress-Testing Long-Context Language Models with Lifelong ICL and Task Haystack","created":"2024-07-23","cited_by_count":19,"area":null},{"id":"2505.18585","title":"RvLLM: LLM Runtime Verification with Domain Knowledge","created":"2025-05-24","cited_by_count":17,"area":null},{"id":"2405.05506","title":"Cross-Care: Assessing the Healthcare Implications of Pre-training Data on Language Model Bias","created":"2024-05-09","cited_by_count":15,"area":null},{"id":"2408.13442","title":"A Law of Next-Token Prediction in Large Language Models","created":"2024-08-24","cited_by_count":15,"area":null},{"id":"2503.16402","title":"The Emperor's New Clothes in Benchmarking? A Rigorous Examination of Mitigation Strategies for LLM Benchmark Data Contamination","created":"2025-03-20","cited_by_count":15,"area":null},{"id":"2601.12471","title":"Knowing When to Abstain: Medical LLMs Under Clinical Uncertainty","created":"2026-01-18","cited_by_count":15,"area":null},{"id":"2402.01656","title":"Promises and pitfalls of artificial intelligence for legal applications","created":"2024-01-10","cited_by_count":14,"area":null},{"id":"2508.09494","title":"Learning Facts at Scale with Active Reading","created":"2025-08-13","cited_by_count":13,"area":null},{"id":"2504.21202","title":"Automatic Legal Writing Evaluation of LLMs","created":"2025-04-29","cited_by_count":12,"area":null},{"id":"2406.16746","title":"The Responsible Foundation Model Development Cheatsheet: A Review of Tools & Resources","created":"2024-06-24","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":"2408.07983","title":"ArabLegalEval: A Multitask Benchmark for Assessing Arabic Legal Knowledge in Large Language Models","created":"2024-08-15","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":"2311.12233","title":"Unifying Corroborative and Contributive Attributions in Large Language Models","created":"2023-11-20","cited_by_count":10,"area":null},{"id":"2409.11798","title":"The Factuality of Large Language Models in the Legal Domain","created":"2024-09-18","cited_by_count":10,"area":null},{"id":"2410.11672","title":"Leaving the barn door open for Clever Hans: Simple features predict LLM benchmark answers","created":"2024-10-15","cited_by_count":9,"area":null},{"id":"2405.05938","title":"DOLOMITES: Domain-Specific Long-Form Methodical Tasks","created":"2024-05-09","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":"2504.13938","title":"Never Start from Scratch: Expediting On-Device LLM Personalization via Explainable Model Selection","created":"2025-04-15","cited_by_count":8,"area":null},{"id":"2603.01919","title":"Real Money, Fake Models: Deceptive Model Claims in Shadow APIs","created":"2026-03-02","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":"2407.16615","title":"Lawma: The Power of Specialization for Legal Annotation","created":"2024-07-23","cited_by_count":7,"area":null},{"id":"2405.11612","title":"Sociotechnical Implications of Generative Artificial Intelligence for Information Access","created":"2024-05-19","cited_by_count":6,"area":null},{"id":"2410.21195","title":"Belief in the Machine: Investigating Epistemological Blind Spots of Language Models","created":"2024-10-28","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":"2407.06798","title":"It Cannot Be Right If It Was Written by AI: On Lawyers' Preferences of Documents Perceived as Authored by an LLM vs a Human","created":"2024-07-09","cited_by_count":5,"area":null},{"id":"2409.07713","title":"Experimenting with Legal AI Solutions: The Case of Question-Answering for Access to Justice","created":"2024-09-12","cited_by_count":5,"area":null},{"id":"2410.12857","title":"Enterprise Benchmarks for Large Language Model Evaluation","created":"2024-10-11","cited_by_count":5,"area":null},{"id":"2504.04949","title":"L3AC: Towards a Lightweight and Lossless Audio Codec","created":"2025-04-07","cited_by_count":5,"area":null},{"id":"2505.09595","title":"WorldView-Bench: A Benchmark for Evaluating Global Cultural Perspectives in Large Language Models","created":"2025-05-14","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":"2506.06390","title":"Benchmarking Large Language Models on Homework Assessment in Circuit Analysis","created":"2025-06-05","cited_by_count":5,"area":null},{"id":"2506.20274","title":"Enterprise Large Language Model Evaluation Benchmark","created":"2025-06-25","cited_by_count":5,"area":null},{"id":"2509.08480","title":"Acquiescence Bias in Large Language Models","created":"2025-09-10","cited_by_count":5,"area":null},{"id":"2509.24506","title":"Building Benchmarks from the Ground Up: Community-Centered Evaluation of LLMs in Healthcare Chatbot Settings","created":"2025-09-29","cited_by_count":5,"area":null},{"id":"2511.11500","title":"Honesty over Accuracy: Trustworthy Language Models through Reinforced Hesitation","created":"2025-11-14","cited_by_count":5,"area":null},{"id":"2605.25240","title":"JudgmentBench: Comparing Rubric and Preference Evaluation for Quality Assessment","created":"2026-05-24","cited_by_count":5,"area":null},{"id":"2402.01758","title":"Aalap: AI Assistant for Legal & Paralegal Functions in India","created":"2024-01-30","cited_by_count":4,"area":null},{"id":"2411.10137","title":"Legal Evalutions and Challenges of Large Language Models","created":"2024-11-15","cited_by_count":4,"area":null},{"id":"2503.04734","title":"What can large language models do for sustainable food?","created":"2025-02-02","cited_by_count":4,"area":null},{"id":"2505.12808","title":"Decentralized Arena: Towards Democratic and Scalable Automatic Evaluation of Language Models","created":"2025-05-19","cited_by_count":4,"area":null},{"id":"2505.19804","title":"Compliance-to-Code: Enhancing Financial Compliance Checking via Code Generation","created":"2025-05-26","cited_by_count":4,"area":null},{"id":"2510.05126","title":"Generalization of Fine-Tuned Uncertainty Communication and Metacognition in Large Language Models","created":"2025-09-30","cited_by_count":4,"area":null},{"id":"2605.10267","title":"IndustryBench: Probing the Industrial Knowledge Boundaries of LLMs","created":"2026-05-11","cited_by_count":4,"area":null},{"id":"2503.03444","title":"Taxation Perspectives from Large Language Models: A Case Study on Additional Tax Penalties","created":"2025-03-05","cited_by_count":3,"area":null},{"id":"2505.14104","title":"Legal Rule Induction: Towards Generalizable Principle Discovery from Analogous Judicial Precedents","created":"2025-05-20","cited_by_count":3,"area":null},{"id":"2505.16514","title":"AppealCase: A Dataset and Benchmark for Civil Case Appeal Scenarios","created":"2025-05-22","cited_by_count":3,"area":null},{"id":"2505.24826","title":"LegalEval-Q: A New Benchmark for The Quality Evaluation of LLM-Generated Legal Text","created":"2025-05-30","cited_by_count":3,"area":null},{"id":"2506.00694","title":"Measuring Faithfulness and Abstention: An Automated Pipeline for Evaluating LLM-Generated 3-ply Case-Based Legal Arguments","created":"2025-05-31","cited_by_count":3,"area":null},{"id":"2506.06084","title":"WisWheat: A Three-Tiered Vision-Language Dataset for Wheat Management","created":"2025-06-06","cited_by_count":3,"area":null},{"id":"2506.07458","title":"KScope: A Framework for Characterizing the Knowledge Status of Language Models","created":"2025-06-09","cited_by_count":3,"area":null},{"id":"2508.06030","title":"Efficient Knowledge Probing of Large Language Models by Adapting Pre-trained Embeddings","created":"2025-08-08","cited_by_count":3,"area":null},{"id":"2509.17044","title":"AgriDoctor: A Multimodal Intelligent Assistant for Agriculture","created":"2025-09-21","cited_by_count":3,"area":null},{"id":"2511.04205","title":"LLM-as-a-Judge is Bad, Based on AI Attempting the Exam Qualifying for the Member of the Polish National Board of Appeal","created":"2025-11-06","cited_by_count":3,"area":null},{"id":"2603.06610","title":"CapTrack: Multifaceted Evaluation of Forgetting in LLM Post-Training","created":"2026-02-19","cited_by_count":3,"area":null},{"id":"2604.10718","title":"SciPredict: Can LLMs Predict the Outcomes of Scientific Experiments in Natural Sciences?","created":"2026-04-12","cited_by_count":3,"area":null},{"id":"2605.10186","title":"LegalCiteBench: Evaluating Citation Reliability in Legal Language Models","created":"2026-05-11","cited_by_count":3,"area":null},{"id":"2311.15716","title":"Justifiable Artificial Intelligence: Engineering Large Language Models for Legal Applications","created":"2023-11-27","cited_by_count":2,"area":null},{"id":"2407.14727","title":"Economy Watchers Survey Provides Datasets and Tasks for Japanese Financial Domain","created":"2024-07-20","cited_by_count":2,"area":null},{"id":"2410.15460","title":"Hallucination Detox: Sensitivity Dropout (SenD) for Large Language Model Training","created":"2024-10-20","cited_by_count":2,"area":null},{"id":"2411.15626","title":"Aligning Generalisation Between Humans and Machines","created":"2024-11-23","cited_by_count":2,"area":null},{"id":"2412.06136","title":"AIDE: Attribute-Guided MultI-Hop Data Expansion for Data Scarcity in Task-Specific Fine-tuning","created":"2024-12-09","cited_by_count":2,"area":null},{"id":"2501.00106","title":"LicenseGPT: A Fine-tuned Foundation Model for Publicly Available Dataset License Compliance","created":"2024-12-30","cited_by_count":2,"area":null},{"id":"2502.16357","title":"LegalBench.PT: A Benchmark for Portuguese Law","created":"2025-02-22","cited_by_count":2,"area":null},{"id":"2503.04305","title":"Computational Law: Datasets, Benchmarks, and Ontologies","created":"2025-03-06","cited_by_count":2,"area":null},{"id":"2505.02172","title":"Identifying Legal Holdings with LLMs: A Systematic Study of Performance, Scale, and Memorization","created":"2025-05-04","cited_by_count":2,"area":null}],"next_cursor":"100"}