{"total":52,"rows":[{"id":"2507.20534","title":"Kimi K2: Open Agentic Intelligence","created":"2025-07-28","cited_by_count":567,"area":"agents"},{"id":"2504.17550","title":"HalluLens: LLM Hallucination Benchmark","created":"2025-04-24","cited_by_count":92,"area":null},{"id":"2509.07968","title":"SimpleQA Verified: A Reliable Factuality Benchmark to Measure Parametric Knowledge","created":"2025-09-09","cited_by_count":54,"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":"2506.08500","title":"DRAGged into Conflicts: Detecting and Addressing Conflicting Sources in Search-Augmented LLMs","created":"2025-06-10","cited_by_count":25,"area":"rag"},{"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":"2504.18041","title":"RAG LLMs are Not Safer: A Safety Analysis of Retrieval-Augmented Generation for Large Language Models","created":"2025-04-25","cited_by_count":24,"area":"rag"},{"id":"2508.11133","title":"MoNaCo: More Natural and Complex Questions for Reasoning Across Dozens of Documents","created":"2025-08-15","cited_by_count":21,"area":"lr"},{"id":"2502.18934","title":"Kanana: Compute-efficient Bilingual Language Models","created":"2025-02-26","cited_by_count":20,"area":null},{"id":"2505.04847","title":"Benchmarking LLM Faithfulness in RAG with Evolving Leaderboards","created":"2025-05-07","cited_by_count":20,"area":"rag"},{"id":"2505.08253","title":"Evaluating LLM Metrics Through Real-World Capabilities","created":"2025-05-13","cited_by_count":18,"area":null},{"id":"2503.19092","title":"Rankers, Judges, and Assistants: Towards Understanding the Interplay of LLMs in Information Retrieval Evaluation","created":"2025-03-24","cited_by_count":15,"area":null},{"id":"2506.13342","title":"Verifying the Verifiers: Unveiling Pitfalls and Potentials in Fact Verifiers","created":"2025-06-16","cited_by_count":13,"area":null},{"id":"2502.18635","title":"Faster, Cheaper, Better: Multi-Objective Hyperparameter Optimization for LLM and RAG Systems","created":"2025-02-25","cited_by_count":12,"area":"rag"},{"id":"2509.21361","title":"Context Is What You Need: The Maximum Effective Context Window for Real World Limits of LLMs","created":"2025-09-21","cited_by_count":12,"area":null},{"id":"2510.26160","title":"CRAG-MM: Multi-modal Multi-turn Comprehensive RAG Benchmark","created":"2025-10-30","cited_by_count":10,"area":"rag"},{"id":"2511.09008","title":"A Neurosymbolic Approach to Natural Language Formalization and Verification","created":"2025-11-12","cited_by_count":9,"area":null},{"id":"2502.18817","title":"Judge as A Judge: Improving the Evaluation of Retrieval-Augmented Generation through the Judge-Consistency of Large Language Models","created":"2025-02-26","cited_by_count":8,"area":"rag"},{"id":"2505.00612","title":"Position: AI Competitions Provide the Gold Standard for Empirical Rigor in GenAI Evaluation","created":"2025-05-01","cited_by_count":8,"area":null},{"id":"2510.12839","title":"FaStfact: Faster, Stronger Long-Form Factuality Evaluations in LLMs","created":"2025-10-13","cited_by_count":8,"area":null},{"id":"2505.23295","title":"How Does Response Length Affect Long-Form Factuality","created":"2025-05-29","cited_by_count":6,"area":null},{"id":"2507.05424","title":"\"Lost-in-the-Later\": Framework for Quantifying Contextual Grounding in Large Language Models","created":"2025-07-07","cited_by_count":5,"area":"lr"},{"id":"2603.24579","title":"MARCH: Multi-Agent Reinforced Self-Check for LLM Hallucination","created":"2026-03-25","cited_by_count":5,"area":"rag"},{"id":"2505.00065","title":"ConSens: Assessing context grounding in open-book question answering","created":"2025-04-30","cited_by_count":4,"area":null},{"id":"2507.09751","title":"Sound and Complete Neurosymbolic Reasoning with LLM-Grounded Interpretations","created":"2025-07-13","cited_by_count":4,"area":"lr"},{"id":"2507.21340","title":"StructText: A Synthetic Table-to-Text Approach for Benchmark Generation with Multi-Dimensional Evaluation","created":"2025-07-28","cited_by_count":4,"area":null},{"id":"2602.05897","title":"Stop Rewarding Hallucinated Steps: Faithfulness-Aware Step-Level Reinforcement Learning for Small Reasoning Models","created":"2026-02-05","cited_by_count":4,"area":"lr"},{"id":"2605.01357","title":"On Stable Long-Form Generation: Benchmarking and Mitigating Length Volatility","created":"2026-05-02","cited_by_count":4,"area":null},{"id":"2505.19259","title":"Towards Large Reasoning Models for Agriculture","created":"2025-05-25","cited_by_count":3,"area":"lr"},{"id":"2509.26601","title":"MENLO: From Preferences to Proficiency -- Evaluating and Modeling Native-like Quality Across 47 Languages","created":"2025-09-30","cited_by_count":3,"area":"alignment"},{"id":"2603.02960","title":"Architecting Trust in Artificial Epistemic Agents","created":"2026-03-03","cited_by_count":3,"area":"agents"},{"id":"2510.03231","title":"Reward Models are Metrics in a Trench Coat","created":"2025-10-03","cited_by_count":2,"area":"alignment"},{"id":"2602.11509","title":"Multimodal Fact-Level Attribution for Verifiable Reasoning","created":"2026-02-12","cited_by_count":2,"area":"lr"},{"id":"2602.14778","title":"A Geometric Analysis of Small-sized Language Model Hallucinations","created":"2026-02-16","cited_by_count":2,"area":"agents"},{"id":"2605.19341","title":"HalluWorld: A Controlled Benchmark for Hallucination via Reference World Models","created":"2026-05-19","cited_by_count":2,"area":"wm"},{"id":"2607.19322","title":"Two-Level Meta-Rubrics for Evaluating Open-Ended Generation: GAMUT, a Benchmark for Factual Completeness","created":"2026-07-21","cited_by_count":2,"area":null},{"id":"2608.27147","title":"Thomson: Continual Learning of Frontier Models for SovereignAI","created":"2026-08-27","cited_by_count":2,"area":null},{"id":"2508.13816","title":"The illusion of a perfect metric: Why evaluating AI's words is harder than it looks","created":"2025-08-19","cited_by_count":1,"area":null},{"id":"2511.17432","title":"SMILE: A Composite Lexical-Semantic Metric for Question-Answering Evaluation","created":"2025-11-21","cited_by_count":1,"area":null},{"id":"2605.07677","title":"TRACE: Tourism Recommendation with Accountable Citation Evidence","created":"2026-05-08","cited_by_count":1,"area":null},{"id":"2512.08944","title":"Enhancing Reliability across Short and Long-Form QA via Reinforcement Learning","created":"2025-11-19","cited_by_count":0,"area":"lr"},{"id":"2602.09158","title":"What do Geometric Hallucination Detection Metrics Actually Measure?","created":"2026-02-09","cited_by_count":0,"area":null},{"id":"2605.11330","title":"Rethinking Evaluation for LLM Hallucination Detection: A Desiderata, A New RAG-based Benchmark, New Insights","created":"2026-05-11","cited_by_count":0,"area":"lr"},{"id":"2606.06871","title":"Evidence-Grounded Ensemble Diagnosis of 802.11 Packet Captures: A Multi-Stage Pipeline with Deterministic Reliability Scoring","created":"2026-06-05","cited_by_count":0,"area":null},{"id":"2606.11459","title":"APEX: Automated Prompt Engineering eXpert with Dynamic Data Selection","created":"2026-06-09","cited_by_count":0,"area":null},{"id":"2606.26437","title":"ConflictScore: Identifying and Measuring How Language Models Handle Conflicting Evidence","created":"2026-06-24","cited_by_count":0,"area":null},{"id":"2607.07993","title":"Hallucination Self-Play: Bootstrapping Reinforced Detector via Evolved Generator","created":"2026-07-08","cited_by_count":0,"area":"alignment"},{"id":"2607.28237","title":"AI and Authenticity in Islamic Research: A Critical Evaluation of Generative AI Reliability, Hallucination, and Source Fidelity in Quranic, Hadith, and Fiqh Knowledge","created":"2026-07-30","cited_by_count":0,"area":null},{"id":"2608.07838","title":"Counterfactual Benchmarking and Training for Factuality Consistency and Order-Robust Grounded Reasoning in LLMs over Heterogeneous Knowledge","created":"2026-08-08","cited_by_count":0,"area":"lr"},{"id":"2608.28384","title":"MAP: A Benchmark on Multimodal Accessibility Planning for Real World Places","created":"2026-08-28","cited_by_count":0,"area":null},{"id":"2609.27606","title":"State-Grounded Conditioning: Wrapping User-Facing LLM Agents Where Direction Depends on Live State","created":"2026-09-23","cited_by_count":0,"area":"agents"},{"id":"2609.36515","title":"Large-scale factor analysis shows machine intelligence is only partially interpretable","created":"2026-09-29","cited_by_count":0,"area":null}],"next_cursor":null}