{"total":106,"rows":[{"id":"2412.05579","title":"LLMs-as-Judges: A Comprehensive Survey on LLM-based Evaluation Methods","created":"2024-12-07","cited_by_count":465,"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":"2503.05061","title":"No Free Labels: Limitations of LLM-as-a-Judge Without Human Grounding","created":"2025-03-07","cited_by_count":54,"area":null},{"id":"2511.11562","title":"PRBench: Large-Scale Expert Rubrics for Evaluating High-Stakes Professional Reasoning","created":"2025-11-14","cited_by_count":32,"area":null},{"id":"2507.21028","title":"Multi-Agent-as-Judge: Aligning LLM-Agent-Based Automated Evaluation with Multi-Dimensional Human Evaluation","created":"2025-07-28","cited_by_count":30,"area":"agents"},{"id":"2501.18845","title":"Text Data Augmentation for Large Language Models: A Comprehensive Survey of Methods, Challenges, and Opportunities","created":"2025-01-31","cited_by_count":22,"area":null},{"id":"2504.05408","title":"Frontier AI's Impact on the Cybersecurity Landscape","created":"2025-04-07","cited_by_count":21,"area":null},{"id":"2506.08584","title":"CounselBench: A Large-Scale Expert Evaluation and Adversarial Benchmarking of Large Language Models in Mental Health Question Answering","created":"2025-06-10","cited_by_count":21,"area":null},{"id":"2507.01001","title":"SciArena: An Open Evaluation Platform for Non-Verifiable Scientific Literature-Grounded Tasks","created":"2025-07-01","cited_by_count":20,"area":null},{"id":"2509.21117","title":"TrustJudge: Inconsistencies of LLM-as-a-Judge and How to Alleviate Them","created":"2025-09-25","cited_by_count":20,"area":null},{"id":"2601.20251","title":"Efficient Evaluation of LLM Performance with Statistical Guarantees","created":"2026-01-28","cited_by_count":18,"area":null},{"id":"2504.15800","title":"FinDER: Financial Dataset for Question Answering and Evaluating Retrieval-Augmented Generation","created":"2025-04-22","cited_by_count":17,"area":"rag"},{"id":"2503.22353","title":"Firm or Fickle? Evaluating Large Language Models Consistency in Sequential Interactions","created":"2025-03-28","cited_by_count":13,"area":null},{"id":"2511.08522","title":"AlphaResearch: Accelerating New Algorithm Discovery with Language Models","created":"2025-11-11","cited_by_count":11,"area":"agents"},{"id":"2601.04745","title":"KnowMe-Bench: Benchmarking Person Understanding for Lifelong Digital Companions","created":"2026-01-08","cited_by_count":11,"area":null},{"id":"2508.12158","title":"LLM-as-a-Judge for Privacy Evaluation? Exploring the Alignment of Human and LLM Perceptions of Privacy in Textual Data","created":"2025-08-16","cited_by_count":10,"area":null},{"id":"2506.16655","title":"Arch-Router: Aligning LLM Routing with Human Preferences","created":"2025-06-19","cited_by_count":9,"area":"alignment"},{"id":"2606.03135","title":"Uncertainty-Aware Clarification in LLM Agents with Information Gain","created":"2026-06-02","cited_by_count":8,"area":"agents"},{"id":"2503.17684","title":"Can LLMs Automate Fact-Checking Article Writing?","created":"2025-03-22","cited_by_count":7,"area":null},{"id":"2504.05325","title":"Unequal Opportunities: Examining the Bias in Geographical Recommendations by Large Language Models","created":"2025-03-16","cited_by_count":7,"area":null},{"id":"2508.07955","title":"Expert Preference-based Evaluation of Automated Related Work Generation","created":"2025-08-11","cited_by_count":6,"area":null},{"id":"2509.15160","title":"An Evaluation-Centric Paradigm for Scientific Visualization Agents","created":"2025-09-18","cited_by_count":6,"area":"agents"},{"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":"2507.07419","title":"MedReadCtrl: Personalizing medical text generation with readability-controlled instruction learning","created":"2025-07-10","cited_by_count":5,"area":null},{"id":"2508.19813","title":"T2R-bench: A Benchmark for Generating Article-Level Reports from Real World Industrial Tables","created":"2025-08-27","cited_by_count":5,"area":"lr"},{"id":"2603.06942","title":"Deep Research, Shallow Evaluation: A Case Study in Meta-Evaluation for Long-Form QA Benchmarks","created":"2026-03-06","cited_by_count":5,"area":null},{"id":"2506.03490","title":"Beyond Memorization: A Rigorous Evaluation Framework for Medical Knowledge Editing","created":"2025-06-04","cited_by_count":4,"area":null},{"id":"2506.13324","title":"Towards Pervasive Distributed Agentic Generative AI -- A State of The Art","created":"2025-06-16","cited_by_count":4,"area":"agents"},{"id":"2601.16356","title":"The Behavioral Fabric of LLM-Powered GUI Agents: Human Values and Interaction Outcomes","created":"2026-01-22","cited_by_count":4,"area":"agents"},{"id":"2601.20253","title":"Automated Benchmark Generation from Domain Guidelines Informed by Bloom's Taxonomy","created":"2026-01-28","cited_by_count":4,"area":null},{"id":"2604.19516","title":"From Experience to Skill: Multi-Agent Generative Engine Optimization via Reusable Strategy Learning","created":"2026-04-21","cited_by_count":4,"area":null},{"id":"2606.18203","title":"RubricsTree: Scalable and Evolving Open-Ended Evaluation of Personal Health Agents across Health Memory and Medical Skills","created":"2026-06-16","cited_by_count":4,"area":"agents"},{"id":"2502.12275","title":"Integrating Expert Knowledge into Logical Programs via LLMs","created":"2025-02-17","cited_by_count":3,"area":"lr"},{"id":"2502.18339","title":"Correlating and Predicting Human Evaluations of Language Models from Natural Language Processing Benchmarks","created":"2025-02-24","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":"2511.10984","title":"DiscoX: Benchmarking Discourse-Level Translation task in Expert Domains","created":"2025-11-14","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":"2512.08937","title":"When AI Gives Advice: Evaluating AI and Human Responses to Online Advice-Seeking for Well-Being","created":"2025-10-24","cited_by_count":3,"area":null},{"id":"2604.00555","title":"Ontology-Constrained Neural Reasoning in Enterprise Agentic Systems: A Neurosymbolic Architecture for Domain-Grounded AI Agents","created":"2026-04-01","cited_by_count":3,"area":"lr"},{"id":"2604.02359","title":"Using LLM-as-a-Judge/Jury to Advance Scalable, Clinically-Validated Safety Evaluations of Model Responses to Users Demonstrating Psychosis","created":"2026-03-20","cited_by_count":3,"area":null},{"id":"2604.05955","title":"Does Pass Rate Tell the Whole Story? Evaluating Design Constraint Compliance in LLM-based Issue Resolution","created":"2026-04-07","cited_by_count":3,"area":"agents"},{"id":"2606.07810","title":"SLMJury: Can Small Language Models Judge as Well as Large Ones?","created":"2026-06-05","cited_by_count":3,"area":null},{"id":"2505.08905","title":"Grounding Synthetic Data Evaluations of Language Models in Unsupervised Document Corpora","created":"2025-05-13","cited_by_count":2,"area":"synth"},{"id":"2505.19667","title":"LeCoDe: A Benchmark Dataset for Interactive Legal Consultation Dialogue Evaluation","created":"2025-05-26","cited_by_count":2,"area":null},{"id":"2508.07596","title":"From Prediction to Explanation: Multimodal, Explainable, and Interactive Deepfake Detection Framework for Non-Expert Users","created":"2025-08-11","cited_by_count":2,"area":null},{"id":"2508.17202","title":"Active Domain Knowledge Acquisition with 100-Dollar Budget: Enhancing LLMs via Cost-Efficient, Expert-Involved Interaction in Sensitive Domains","created":"2025-08-24","cited_by_count":2,"area":null},{"id":"2509.22545","title":"Does AI Coaching Prepare us for Workplace Negotiations?","created":"2025-09-26","cited_by_count":2,"area":null},{"id":"2511.04478","title":"Generate, Evaluate, Iterate: Synthetic Data for Human-in-the-Loop Refinement of LLM Judges","created":"2025-11-06","cited_by_count":2,"area":"synth"},{"id":"2511.09195","title":"Towards Trustworthy Dermatology MLLMs: A Benchmark and Multimodal Evaluator for Diagnostic Narratives","created":"2025-11-12","cited_by_count":2,"area":"mllm"},{"id":"2512.10687","title":"Safe for Whom? Rethinking How We Evaluate the Safety of LLMs for Real Users","created":"2025-12-11","cited_by_count":2,"area":"lr"},{"id":"2601.11374","title":"Reward Modeling for Scientific Writing Evaluation","created":"2026-01-16","cited_by_count":2,"area":"lr"},{"id":"2603.04033","title":"Who Judges the Judge? Evaluating LLM-as-a-Judge for French Medical open-ended QA","created":"2026-03-04","cited_by_count":2,"area":null},{"id":"2604.03376","title":"Towards Better Aligned LLM Judges for Radiology Report Evaluation across Modalities and Anatomies","created":"2026-04-03","cited_by_count":2,"area":null},{"id":"2605.19228","title":"Diagnosing Multi-step Reasoning Failures in Black-box LLMs via Stepwise Confidence Attribution","created":"2026-05-19","cited_by_count":2,"area":"lr"},{"id":"2606.20470","title":"Analyzing Defensive Misdirection Against Model-Guided Automated Attacks on Agentic AI Systems","created":"2026-06-18","cited_by_count":2,"area":"agents"},{"id":"2503.00619","title":"PinLanding: Content-First Keyword Landing Page Generation via Multi-Modal AI for Web-Scale Discovery","created":"2025-03-01","cited_by_count":1,"area":null},{"id":"2504.03822","title":"Arti-\"fickle\" Intelligence: Using LLMs as a Tool for Inference in the Political and Social Sciences","created":"2025-04-04","cited_by_count":1,"area":null},{"id":"2506.19185","title":"Spiritual-LLM : Gita Inspired Mental Health Therapy In the Era of LLMs","created":"2025-06-23","cited_by_count":1,"area":null},{"id":"2507.03829","title":"RELRaE: LLM-Based Relationship Extraction, Labelling, Refinement, and Evaluation","created":"2025-07-04","cited_by_count":1,"area":null},{"id":"2507.10585","title":"A Taxonomy for Design and Evaluation of Prompt-Based Natural Language Explanations","created":"2025-07-11","cited_by_count":1,"area":null},{"id":"2509.08593","title":"No-Knowledge Alarms for Misaligned LLMs-as-Judges","created":"2025-09-10","cited_by_count":1,"area":null},{"id":"2509.25535","title":"Meta-Router: Bridging Gold-standard and Preference-based Evaluations in Large Language Model Routing","created":"2025-09-29","cited_by_count":1,"area":null},{"id":"2509.26205","title":"Human-Centered Evaluation of RAG outputs: a framework and questionnaire for human-AI collaboration","created":"2025-09-30","cited_by_count":1,"area":"rag"},{"id":"2510.10415","title":"CQA-Eval: Designing Reliable Evaluations of Multi-paragraph Clinical QA under Resource Constraints","created":"2025-10-12","cited_by_count":1,"area":null},{"id":"2511.00924","title":"The Biased Oracle: Assessing LLMs' Understandability and Empathy in Medical Diagnoses","created":"2025-11-02","cited_by_count":1,"area":null},{"id":"2511.04366","title":"Towards Aligning Multimodal LLMs with Human Experts: A Focus on Parent-Child Interaction","created":"2025-11-06","cited_by_count":1,"area":"mllm"},{"id":"2601.03553","title":"Evaluating LLMs for Police Decision-Making: A Framework Based on Police Action Scenarios","created":"2026-01-07","cited_by_count":1,"area":null},{"id":"2601.15511","title":"AdversaRiskQA: An Adversarial Factuality Benchmark for High-Risk Domains","created":"2026-01-21","cited_by_count":1,"area":null},{"id":"2602.14357","title":"Key Considerations for Domain Expert Involvement in LLM Design and Evaluation: An Ethnographic Study","created":"2026-02-16","cited_by_count":1,"area":null},{"id":"2604.15827","title":"UsefulBench: Towards Decision-Useful Information as a Target for Information Retrieval","created":"2026-04-17","cited_by_count":1,"area":null},{"id":"2606.04660","title":"LifeSide: Benchmarking Agents as Lifelong Digital Companions","created":"2026-06-03","cited_by_count":1,"area":null},{"id":"2606.12250","title":"Reassessing High-Performing LLMs on Polish Medical Exams: True Competence or Bias-Driven Performance?","created":"2026-06-10","cited_by_count":1,"area":null},{"id":"2506.05950","title":"Elementary Math Word Problem Generation using Large Language Models","created":"2025-06-06","cited_by_count":0,"area":null},{"id":"2506.17449","title":"OmniReflect: Discovering Transferable Constitutions for LLM agents via Neuro-Symbolic Reflections","created":"2025-06-20","cited_by_count":0,"area":"agents"},{"id":"2509.19680","title":"PolicyPad: Collaborative Prototyping of LLM Policies","created":"2025-09-24","cited_by_count":0,"area":null},{"id":"2510.00324","title":"Which Programming Language and Model Work Best With LLM-as-a-Judge For Code Retrieval?","created":"2025-09-30","cited_by_count":0,"area":null},{"id":"2510.02549","title":"Knowledge-Graph Based RAG System Evaluation Framework","created":"2025-10-02","cited_by_count":0,"area":"rag"},{"id":"2510.11390","title":"Medical Interpretability and Knowledge Maps of Large Language Models","created":"2025-10-13","cited_by_count":0,"area":"mechinterp"},{"id":"2512.04728","title":"Measuring the Unspoken: A Disentanglement Model and Benchmark for Psychological Analysis in the Wild","created":"2025-12-04","cited_by_count":0,"area":"mllm"},{"id":"2601.23206","title":"High-quality generation of dynamic game content via small language models: A proof of concept","created":"2026-01-30","cited_by_count":0,"area":null},{"id":"2603.00774","title":"Structure Matters: Evaluating Multi-Agents Orchestration in Generative Therapeutic Chatbots","created":"2026-02-28","cited_by_count":0,"area":"agents"},{"id":"2603.08392","title":"COACH meets QUORUM: A Framework and Pipeline for Aligning User, Expert and Developer Perspectives in LLM-generated Health Counselling","created":"2026-03-09","cited_by_count":0,"area":null},{"id":"2603.15044","title":"Prompt Readiness Levels (PRL): a maturity scale and scoring framework for production grade prompt assets","created":"2026-03-16","cited_by_count":0,"area":null},{"id":"2604.05371","title":"LLM-as-Judge for Semantic Judging of Powerline Segmentation in UAV Inspection","created":"2026-04-07","cited_by_count":0,"area":null},{"id":"2604.26986","title":"BatteryPass-12K: The First Dataset for the Novel Digital Battery Passport Conformance Task","created":"2026-04-28","cited_by_count":0,"area":null},{"id":"2605.05427","title":"The Refusal--Compliance Tradeoff: A Large-Scale Safety Behavior Audit of Large Language Models","created":"2026-05-06","cited_by_count":0,"area":"safety"},{"id":"2605.07032","title":"A Systematic Investigation of RL-Jailbreaking in LLMs","created":"2026-05-07","cited_by_count":0,"area":"safety"},{"id":"2605.23970","title":"Faithful or Fabricated? A Causal Framework for Rationalization Bias in LLM Judges","created":"2026-05-13","cited_by_count":0,"area":null},{"id":"2605.27156","title":"LitSeg: Narrative-Aware Document Segmentation for Literary RAG","created":"2026-05-26","cited_by_count":0,"area":"rag"},{"id":"2606.00136","title":"Generative AI and Digital Ecosystem Resilience: A Proactive Lifecycle-Based Survey","created":"2026-05-28","cited_by_count":0,"area":null},{"id":"2606.24734","title":"Task Decomposition for Efficient Annotation","created":"2026-06-23","cited_by_count":0,"area":null},{"id":"2606.25552","title":"SFL-MTSC: Leveraging Semantic Frame-Level Multi-Task Self-Consistency for Robust Multi-Intent Spoken Language Understanding","created":"2026-06-24","cited_by_count":0,"area":"lr"},{"id":"2606.30219","title":"EvalSafetyGap: A Hybrid Survey and Conceptual Framework for LLM Evaluation-Safety Failures","created":"2026-06-29","cited_by_count":0,"area":null},{"id":"2607.16660","title":"From Adoption to Deployment: A Qualitative Study on AI Integration in Software Development Practice","created":"2026-07-18","cited_by_count":0,"area":null},{"id":"2607.18068","title":"Human Grounded Evaluation of Large Language Models for Optical Network Automation","created":"2026-07-20","cited_by_count":0,"area":null},{"id":"2608.04240","title":"Hallucinations on the Board: Tool-Augmented Evaluation of LLM Chess Commentary","created":"2026-08-04","cited_by_count":0,"area":null},{"id":"2608.04549","title":"EuroExec: Frontier Language Models Fall Short of Expert Judgment on European Executive Decision Tasks","created":"2026-08-05","cited_by_count":0,"area":null},{"id":"2608.05823","title":"Decomposed Entailment for Factuality Checking and Hallucination Detection","created":"2026-08-06","cited_by_count":0,"area":null},{"id":"2609.02371","title":"Diagnosing with Insights: Structured Analysis of Agent Failures via Behavioral Abstractions","created":"2026-09-02","cited_by_count":0,"area":"agents"},{"id":"2609.04835","title":"On Epistemic Diversity in Large Language Models","created":"2026-09-04","cited_by_count":0,"area":null}],"next_cursor":"100"}