{"total":260,"rows":[{"id":"2502.11221","title":"PlanGenLLMs: A Modern Survey of LLM Planning Capabilities","created":"2025-02-16","cited_by_count":83,"area":null},{"id":"2501.10970","title":"The Alternative Annotator Test for LLM-as-a-Judge: How to Statistically Justify Replacing Human Annotators with LLMs","created":"2025-01-19","cited_by_count":74,"area":null},{"id":"2510.17281","title":"MemoryBench: A Benchmark for Memory and Continual Learning in LLM Systems","created":"2025-10-20","cited_by_count":61,"area":null},{"id":"2510.06265","title":"Large Language Models Hallucination: A Comprehensive Survey","created":"2025-10-05","cited_by_count":49,"area":null},{"id":"2508.18076","title":"Neither Valid nor Reliable? Investigating the Use of LLMs as Judges","created":"2025-08-25","cited_by_count":39,"area":null},{"id":"2510.27106","title":"Rating Roulette: Self-Inconsistency in LLM-As-A-Judge Frameworks","created":"2025-10-31","cited_by_count":38,"area":null},{"id":"2502.20576","title":"OmniRouter: Budget and Performance Controllable Multi-LLM Routing","created":"2025-02-27","cited_by_count":35,"area":null},{"id":"2510.15831","title":"VISTA: A Test-Time Self-Improving Video Generation Agent","created":"2025-10-17","cited_by_count":31,"area":null},{"id":"2606.19544","title":"Reliability without Validity: A Systematic, Large-Scale Evaluation of LLM-as-a-Judge Models Across Agreement, Consistency, and Bias","created":"2026-06-17","cited_by_count":28,"area":null},{"id":"2507.09313","title":"ProactiveVideoQA: A Comprehensive Benchmark Evaluating Proactive Interactions in Video Large Language Models","created":"2025-07-12","cited_by_count":27,"area":null},{"id":"2601.03193","title":"UniCorn: Towards Self-Improving Unified Multimodal Models through Self-Generated Supervision","created":"2026-01-06","cited_by_count":26,"area":null},{"id":"2501.18081","title":"Normative Evaluation of Large Language Models with Everyday Moral Dilemmas","created":"2025-01-30","cited_by_count":24,"area":null},{"id":"2506.13639","title":"An Empirical Study of LLM-as-a-Judge: How Design Choices Impact Evaluation Reliability","created":"2025-06-16","cited_by_count":19,"area":null},{"id":"2508.06225","title":"Overconfidence in LLM-as-a-Judge: Diagnosis and Confidence-Driven Solution","created":"2025-08-08","cited_by_count":18,"area":null},{"id":"2509.16533","title":"Challenging the Evaluator: LLM Sycophancy Under User Rebuttal","created":"2025-09-20","cited_by_count":18,"area":null},{"id":"2602.11865","title":"Intelligent AI Delegation","created":"2026-02-12","cited_by_count":18,"area":null},{"id":"2501.14844","title":"Unmasking Conversational Bias in AI Multiagent Systems","created":"2025-01-24","cited_by_count":17,"area":null},{"id":"2506.07371","title":"ARGUS: Hallucination and Omission Evaluation in Video-LLMs","created":"2025-06-09","cited_by_count":16,"area":null},{"id":"2602.00521","title":"Diagnosing the Reliability of LLM-as-a-Judge via Item Response Theory","created":"2026-01-31","cited_by_count":16,"area":null},{"id":"2501.03545","title":"Beyond Factual Accuracy: Evaluating Coverage of Diverse Factual Information in Long-form Text Generation","created":"2025-01-07","cited_by_count":15,"area":null},{"id":"2502.17955","title":"Language Models' Factuality Depends on the Language of Inquiry","created":"2025-02-25","cited_by_count":14,"area":null},{"id":"2504.01001","title":"Zero-shot Benchmarking: A Framework for Flexible and Scalable Automatic Evaluation of Language Models","created":"2025-04-01","cited_by_count":14,"area":null},{"id":"2504.11972","title":"Reassessing Extractive QA Datasets at Scale: LLM-as-a-Judge and In-Depth Analyses","created":"2025-04-16","cited_by_count":14,"area":null},{"id":"2510.08886","title":"FinAuditing: A Financial Taxonomy-Structured Multi-Document Benchmark for Evaluating LLMs","created":"2025-10-10","cited_by_count":14,"area":null},{"id":"2511.17826","title":"Deterministic Inference across Tensor Parallel Sizes That Eliminates Training-Inference Mismatch","created":"2025-11-21","cited_by_count":14,"area":null},{"id":"2603.07244","title":"PresentBench: A Fine-Grained Rubric-Based Benchmark for Slide Generation","created":"2026-03-07","cited_by_count":14,"area":null},{"id":"2506.00777","title":"Improving Automatic Evaluation of Large Language Models (LLMs) in Biomedical Relation Extraction via LLMs-as-the-Judge","created":"2025-06-01","cited_by_count":13,"area":null},{"id":"2510.09869","title":"NarraBench: A Comprehensive Framework for Narrative Benchmarking","created":"2025-10-10","cited_by_count":13,"area":null},{"id":"2601.19922","title":"HEART: A Unified Benchmark for Assessing Humans and LLMs in Emotional Support Dialogue","created":"2026-01-09","cited_by_count":13,"area":null},{"id":"2603.00039","title":"CARE: Confounder-Aware Aggregation for Reliable LLM Evaluation","created":"2026-02-09","cited_by_count":13,"area":null},{"id":"2603.06865","title":"Counting on Consensus: Selecting the Right Inter-annotator Agreement Metric for NLP Annotation and Evaluation","created":"2026-03-06","cited_by_count":13,"area":null},{"id":"2504.08762","title":"InteractiveSurvey: An LLM-based Personalized and Interactive Survey Paper Generation System","created":"2025-03-31","cited_by_count":12,"area":null},{"id":"2504.09754","title":"Integrating Large Language Models for Automated Structural Analysis","created":"2025-04-13","cited_by_count":12,"area":null},{"id":"2512.16856","title":"Distributional AGI Safety","created":"2025-12-18","cited_by_count":12,"area":null},{"id":"2604.01707","title":"Memory in the LLM Era: Modular Architectures and Strategies in a Unified Framework","created":"2026-04-02","cited_by_count":12,"area":null},{"id":"2601.19532","title":"Benchmarks Saturate When The Model Gets Smarter Than The Judge","created":"2026-01-27","cited_by_count":11,"area":null},{"id":"2502.17057","title":"ExpandR: Teaching Dense Retrievers Beyond Queries with LLM Guidance","created":"2025-02-24","cited_by_count":10,"area":null},{"id":"2505.11613","title":"MedGUIDE: Benchmarking Clinical Decision-Making in Large Language Models","created":"2025-05-16","cited_by_count":10,"area":null},{"id":"2505.18215","title":"Do BERT-Like Bidirectional Models Still Perform Better on Text Classification in the Era of LLMs?","created":"2025-05-23","cited_by_count":10,"area":null},{"id":"2511.18491","title":"MindEval: Benchmarking Language Models on Multi-turn Mental Health Support","created":"2025-11-23","cited_by_count":10,"area":null},{"id":"2604.23478","title":"JudgeSense: A Benchmark for Prompt Sensitivity in LLM-as-a-Judge Systems","created":"2026-04-26","cited_by_count":10,"area":null},{"id":"2511.07678","title":"AIA Forecaster: Technical Report","created":"2025-11-10","cited_by_count":9,"area":null},{"id":"2501.02039","title":"An Investigation into Value Misalignment in LLM-Generated Texts for Cultural Heritage","created":"2025-01-03","cited_by_count":8,"area":null},{"id":"2502.01754","title":"Evaluation of Large Language Models via Coupled Token Generation","created":"2025-02-03","cited_by_count":8,"area":null},{"id":"2502.17943","title":"CaseGen: A Benchmark for Multi-Stage Legal Case Documents Generation","created":"2025-02-25","cited_by_count":8,"area":null},{"id":"2507.23220","title":"Model Directions, Not Words: Mechanistic Topic Models Using Sparse Autoencoders","created":"2025-07-31","cited_by_count":8,"area":null},{"id":"2508.09998","title":"INTIMA: A Benchmark for Human-AI Companionship Behavior","created":"2025-08-04","cited_by_count":8,"area":null},{"id":"2510.05115","title":"SAC-Opt: Semantic Anchors for Iterative Correction in Optimization Modeling","created":"2025-09-28","cited_by_count":8,"area":null},{"id":"2601.13537","title":"When Wording Steers the Evaluation: Framing Bias in LLM judges","created":"2026-01-20","cited_by_count":8,"area":null},{"id":"2506.22157","title":"Training Language Model to Critique for Better Refinement","created":"2025-06-27","cited_by_count":7,"area":null},{"id":"2507.17747","title":"Pretraining on the Test Set Is No Longer All You Need: A Debate-Driven Approach to QA Benchmarks","created":"2025-07-23","cited_by_count":7,"area":null},{"id":"2508.12792","title":"Bridging Human and LLM Judgments: Understanding and Narrowing the Gap","created":"2025-08-18","cited_by_count":7,"area":null},{"id":"2502.05467","title":"Position: LLMs Can be Good Tutors in English Education","created":"2025-02-08","cited_by_count":6,"area":null},{"id":"2503.02359","title":"Add-One-In: Incremental Sample Selection for Large Language Models via a Choice-Based Greedy Paradigm","created":"2025-03-04","cited_by_count":6,"area":null},{"id":"2503.08542","title":"CLEV: LLM-Based Evaluation Through Lightweight Efficient Voting for Free-Form Question-Answering","created":"2025-03-11","cited_by_count":6,"area":null},{"id":"2506.10403","title":"Time To Impeach LLM-as-a-Judge: Programs are the Future of Evaluation","created":"2025-06-12","cited_by_count":6,"area":null},{"id":"2508.12711","title":"Drifting Away from Truth: GenAI-Driven News Diversity Challenges LVLM-Based Misinformation Detection","created":"2025-08-18","cited_by_count":6,"area":null},{"id":"2509.19163","title":"Measuring AI \"Slop\" in Text","created":"2025-09-23","cited_by_count":6,"area":null},{"id":"2510.05154","title":"Can AI Truly Represent Your Voice in Deliberations? A Comprehensive Study of Large-Scale Opinion Aggregation with LLMs","created":"2025-10-02","cited_by_count":6,"area":null},{"id":"2510.12462","title":"Evaluating and Mitigating LLM-as-a-judge Bias in Communication Systems","created":"2025-10-14","cited_by_count":6,"area":null},{"id":"2507.01936","title":"The Thin Line Between Comprehension and Persuasion in LLMs","created":"2025-07-02","cited_by_count":5,"area":null},{"id":"2508.14317","title":"SurveyGen-I: Consistent Scientific Survey Generation with Evolving Plans and Memory-Guided Writing","created":"2025-08-20","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":"2511.05124","title":"QuAnTS: Question Answering on Time Series","created":"2025-11-07","cited_by_count":5,"area":null},{"id":"2601.08843","title":"Rubric-Conditioned LLM Grading: Alignment, Uncertainty, and Robustness","created":"2025-12-21","cited_by_count":5,"area":null},{"id":"2601.22548","title":"Are LLM Evaluators Really Narcissists? Sanity Checking Self-Preference Evaluations","created":"2026-01-30","cited_by_count":5,"area":null},{"id":"2602.06625","title":"FairJudge: An Adaptive, Debiased, and Consistent LLM-as-a-Judge","created":"2026-02-06","cited_by_count":5,"area":null},{"id":"2603.00024","title":"Personalization Increases Affective Alignment but Has Role-Dependent Effects on Epistemic Independence in LLMs","created":"2026-02-03","cited_by_count":5,"area":null},{"id":"2603.29403","title":"Security in LLM-as-a-Judge: A Comprehensive SoK","created":"2026-03-31","cited_by_count":5,"area":null},{"id":"2603.29791","title":"Reasoning-Driven Synthetic Data Generation and Evaluation","created":"2026-03-31","cited_by_count":5,"area":null},{"id":"2605.22148","title":"Ratchet: How Reliable Must an LLM Judge Be to Retire a Skill?","created":"2026-05-21","cited_by_count":5,"area":null},{"id":"2606.01629","title":"Benchmarking LLM-as-a-Judge for Long-Form Output Evaluation","created":"2026-06-01","cited_by_count":5,"area":null},{"id":"2503.00501","title":"Qilin: A Multimodal Information Retrieval Dataset with APP-level User Sessions","created":"2025-03-01","cited_by_count":4,"area":null},{"id":"2504.04141","title":"Self-Adaptive Cognitive Debiasing for Large Language Models in Decision-Making","created":"2025-04-05","cited_by_count":4,"area":null},{"id":"2504.21117","title":"Beyond One-Size-Fits-All: Inversion Learning for Highly Effective NLG Evaluation Prompts","created":"2025-04-29","cited_by_count":4,"area":null},{"id":"2505.12301","title":"Beyond Single-Point Judgment: Distribution Alignment for LLM-as-a-Judge","created":"2025-05-18","cited_by_count":4,"area":null},{"id":"2505.15386","title":"RePPL: Recalibrating Perplexity by Uncertainty in Semantic Propagation and Language Generation for Explainable QA Hallucination Detection","created":"2025-05-21","cited_by_count":4,"area":null},{"id":"2506.00469","title":"Massively Multilingual Adaptation of Large Language Models Using Bilingual Translation Data","created":"2025-05-31","cited_by_count":4,"area":null},{"id":"2507.15557","title":"Evaluating Text Style Transfer: A Nine-Language Benchmark for Text Detoxification","created":"2025-07-21","cited_by_count":4,"area":null},{"id":"2509.24678","title":"Reference-Free Rating of LLM Responses via Latent Information","created":"2025-09-29","cited_by_count":4,"area":null},{"id":"2510.09724","title":"InteractScience: Programmatic and Visually-Grounded Evaluation of Interactive Scientific Demonstration Code Generation","created":"2025-10-10","cited_by_count":4,"area":null},{"id":"2511.18271","title":"Beyond Words and Pixels: A Benchmark for Implicit World Knowledge Reasoning in Generative Models","created":"2025-11-23","cited_by_count":4,"area":null},{"id":"2512.04578","title":"LexGenius: An Expert-Level Benchmark for Large Language Models in Legal General Intelligence","created":"2025-12-04","cited_by_count":4,"area":null},{"id":"2512.08121","title":"Balanced Accuracy: The Right Metric for Evaluating LLM Judges -- Explained through Youden's J statistic","created":"2025-12-08","cited_by_count":4,"area":null},{"id":"2512.09874","title":"Benchmarking Document Parsers on Mathematical Formula Extraction from PDFs","created":"2025-12-10","cited_by_count":4,"area":null},{"id":"2601.15307","title":"DeepSurvey-Bench: Evaluating Academic Value of Automatically Generated Scientific Surveys","created":"2026-01-13","cited_by_count":4,"area":null},{"id":"2602.05088","title":"AI Chatbot Suicide Risk Detection and Response: Human Validation Study of the Open-Source VERA-MH Safety Evaluation","created":"2026-02-04","cited_by_count":4,"area":null},{"id":"2602.11173","title":"Author-in-the-Loop Response Generation and Evaluation: Integrating Author Expertise and Intent in Responses to Peer Review","created":"2026-01-19","cited_by_count":4,"area":null},{"id":"2604.16790","title":"Bias in the Loop: Auditing LLM-as-a-Judge for Software Engineering","created":"2026-04-18","cited_by_count":4,"area":null},{"id":"2607.12885","title":"LLM Judges Can Be Too Generous When There Is No Reference Answer","created":"2026-07-14","cited_by_count":4,"area":null},{"id":"2503.16456","title":"Position: Beyond Assistance -- Reimagining LLMs as Ethical and Adaptive Co-Creators in Mental Health Care","created":"2025-02-21","cited_by_count":3,"area":null},{"id":"2507.16217","title":"Towards Compute-Optimal Many-Shot In-Context Learning","created":"2025-07-22","cited_by_count":3,"area":null},{"id":"2507.21117","title":"A Comprehensive Review on Harnessing Large Language Models to Overcome Recommender System Challenges","created":"2025-07-17","cited_by_count":3,"area":null},{"id":"2508.06374","title":"Evaluating Style-Personalized Text Generation: Challenges and Directions","created":"2025-08-08","cited_by_count":3,"area":null},{"id":"2508.15846","title":"CyPortQA: Benchmarking Multimodal Large Language Models for Cyclone Preparedness in Port Operation","created":"2025-08-19","cited_by_count":3,"area":null},{"id":"2510.11520","title":"mmWalk: Towards Multi-modal Multi-view Walking Assistance","created":"2025-10-13","cited_by_count":3,"area":null},{"id":"2510.22242","title":"PaperAsk: A Benchmark for Reliability Evaluation of LLMs in Paper Search and Reading","created":"2025-10-25","cited_by_count":3,"area":null},{"id":"2511.16544","title":"WER is Unaware: Assessing How ASR Errors Distort Clinical Understanding in Patient Facing Dialogue","created":"2025-11-20","cited_by_count":3,"area":null},{"id":"2511.18597","title":"Toward Trustworthy Difficulty Assessments: Large Language Models as Judges in Programming and Synthetic Tasks","created":"2025-11-23","cited_by_count":3,"area":null},{"id":"2601.05563","title":"What's Left Unsaid? Detecting and Correcting Misleading Omissions in Multimodal News Previews","created":"2026-01-09","cited_by_count":3,"area":null}],"next_cursor":"100"}