{"total":26,"rows":[{"id":"2504.00125","title":"LLMs for Explainable AI: A Comprehensive Survey","created":"2025-03-31","cited_by_count":45,"area":null},{"id":"2502.03261","title":"CARROT: A Cost Aware Rate Optimal Router","created":"2025-02-05","cited_by_count":39,"area":null},{"id":"2505.16037","title":"Causal LLM Routing: End-to-End Regret Minimization from Observational Data","created":"2025-05-21","cited_by_count":28,"area":null},{"id":"2510.09738","title":"Judge's Verdict: A Comprehensive Analysis of LLM Judge Capability Through Human Agreement","created":"2025-10-10","cited_by_count":25,"area":null},{"id":"2503.15620","title":"Does Context Matter? ContextualJudgeBench for Evaluating LLM-based Judges in Contextual Settings","created":"2025-03-19","cited_by_count":24,"area":null},{"id":"2506.08354","title":"Position: Text Embeddings Should Capture Implicit Semantics, Not Just Surface Meaning","created":"2025-06-10","cited_by_count":10,"area":null},{"id":"2504.01509","title":"PROPHET: An Inferable Future Forecasting Benchmark with Causal Intervened Likelihood Estimation","created":"2025-04-02","cited_by_count":8,"area":null},{"id":"2602.02888","title":"HALT: Hallucination Assessment via Log-probs as Time series","created":"2026-02-02","cited_by_count":8,"area":null},{"id":"2507.20930","title":"FRED: Financial Retrieval-Enhanced Detection and Editing of Hallucinations in Language Models","created":"2025-07-28","cited_by_count":6,"area":null},{"id":"2606.30306","title":"Always-OnAgents:A Survey of Persistent Memory, State, and Governance in LLMAgents","created":"2026-06-29","cited_by_count":5,"area":null},{"id":"2507.18392","title":"CLEAR: Error Analysis via LLM-as-a-Judge Made Easy","created":"2025-07-24","cited_by_count":3,"area":null},{"id":"2412.05223","title":"100% Elimination of Hallucinations on RAGTruth for GPT-4 and GPT-3.5 Turbo","created":"2024-12-06","cited_by_count":2,"area":null},{"id":"2509.25184","title":"Incentive-Aligned Multi-Source LLM Summaries","created":"2025-09-29","cited_by_count":1,"area":null},{"id":"2601.16967","title":"Empowering Medical Equipment Sustainability in Low-Resource Settings: An AI-Powered Diagnostic and Support Platform for Biomedical Technicians","created":"2026-01-23","cited_by_count":1,"area":null},{"id":"2602.16942","title":"SourceBench: Can AI Answers Reference Quality Web Sources?","created":"2026-02-18","cited_by_count":1,"area":null},{"id":"2604.17943","title":"A Benchmark Construction and Evaluation Framework for Specialist Domains: Case Study on Defense-related Documents","created":"2026-04-20","cited_by_count":1,"area":null},{"id":"2605.21102","title":"ACL-Verbatim: hallucination-free question answering for research","created":"2026-05-20","cited_by_count":1,"area":null},{"id":"2606.04646","title":"QO-Bench: Diagnosing Query-Operator-Preserving Retrieval over Typed Event Tuples","created":"2026-06-03","cited_by_count":1,"area":null},{"id":"2506.07940","title":"Gradients: When Markets Meet Fine-tuning -- A Distributed Approach to Model Optimisation","created":"2025-06-09","cited_by_count":0,"area":null},{"id":"2508.02074","title":"The SMeL Test: A simple benchmark for media literacy in language models","created":"2025-08-04","cited_by_count":0,"area":null},{"id":"2605.00964","title":"Seeking Information with RAG-Assistants: Does Model Size Matter in Human-AI Collaborations?","created":"2026-05-01","cited_by_count":0,"area":null},{"id":"2607.25765","title":"WorkSurface-Bench: Benchmarking Enterprise Agents on Multi-Surface Knowledge Routing","created":"2026-07-28","cited_by_count":0,"area":null},{"id":"2608.11584","title":"EnterpriseRAG: Benchmarking LLM Instruction Adherence and Robustness under Non-Ideal Enterprise Retrieval","created":"2026-08-12","cited_by_count":0,"area":null},{"id":"2608.23812","title":"From Preferences to Principles: Rubric-Based Alignment for Grounded Knowledge Answers","created":"2026-08-24","cited_by_count":0,"area":null},{"id":"2608.28300","title":"MaCoPlanner: LLM-Assisted Manual-Compiled Task Planning with Proactive Safety Verification for Robotic Industrial Panel Operation","created":"2026-08-28","cited_by_count":0,"area":null},{"id":"2610.19198","title":"Embedding Geometry Shapes LLM Routing: Tracing Failure Modes and Improving Generalization","created":"2026-10-13","cited_by_count":0,"area":null}],"next_cursor":null}