{"total":173,"rows":[{"id":"2412.08905","title":"Phi-4 Technical Report","created":"2024-12-12","cited_by_count":711,"area":null},{"id":"2504.12516","title":"BrowseComp: A Simple Yet Challenging Benchmark for Browsing Agents","created":"2025-04-16","cited_by_count":647,"area":null},{"id":"2501.14249","title":"Humanity's Last Exam","created":"2025-01-24","cited_by_count":491,"area":null},{"id":"2507.14843","title":"The Invisible Leash: Why RLVR May or May Not Escape Its Origin","created":"2025-07-20","cited_by_count":97,"area":null},{"id":"2504.17550","title":"HalluLens: LLM Hallucination Benchmark","created":"2025-04-24","cited_by_count":92,"area":null},{"id":"2503.00172","title":"A Survey of Uncertainty Estimation Methods on Large Language Models","created":"2025-02-28","cited_by_count":62,"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":"2501.03200","title":"The FACTS Grounding Leaderboard: Benchmarking LLMs' Ability to Ground Responses to Long-Form Input","created":"2025-01-06","cited_by_count":52,"area":null},{"id":"2507.02856","title":"Answer Matching Outperforms Multiple Choice for Language Model Evaluation","created":"2025-07-03","cited_by_count":41,"area":null},{"id":"2502.11028","title":"Mind the Confidence Gap: Overconfidence, Calibration, and Distractor Effects in Large Language Models","created":"2025-02-16","cited_by_count":40,"area":null},{"id":"2504.14693","title":"Video-MMLU: A Massive Multi-Discipline Lecture Understanding Benchmark","created":"2025-04-20","cited_by_count":37,"area":null},{"id":"2502.14815","title":"Optimizing Model Selection for Compound AI Systems","created":"2025-02-20","cited_by_count":36,"area":null},{"id":"2501.09731","title":"Predictions as Surrogates: Revisiting Surrogate Outcomes in the Age of AI","created":"2025-01-16","cited_by_count":34,"area":null},{"id":"2506.05334","title":"Search Arena: Analyzing Search-Augmented LLMs","created":"2025-06-05","cited_by_count":34,"area":null},{"id":"2508.12631","title":"Beyond GPT-5: Making LLMs Cheaper and Better via Performance-Efficiency Optimized Routing","created":"2025-08-18","cited_by_count":34,"area":null},{"id":"2508.20033","title":"DeepScholar-Bench: A Live Benchmark and Automated Evaluation for Generative Research Synthesis","created":"2025-08-27","cited_by_count":34,"area":null},{"id":"2509.03531","title":"Real-Time Detection of Hallucinated Entities in Long-Form Generation","created":"2025-08-26","cited_by_count":34,"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":"2505.14963","title":"MedBrowseComp: Benchmarking Medical Deep Research and Computer Use","created":"2025-05-20","cited_by_count":30,"area":null},{"id":"2411.14258","title":"Knowledge Graphs, Large Language Models, and Hallucinations: An NLP Perspective","created":"2024-11-21","cited_by_count":29,"area":null},{"id":"2502.11177","title":"The Mirage of Model Editing: Revisiting Evaluation in the Wild","created":"2025-02-16","cited_by_count":27,"area":null},{"id":"2512.08093","title":"Training LLMs for Honesty via Confessions","created":"2025-12-08","cited_by_count":22,"area":null},{"id":"2504.13677","title":"Revisiting Uncertainty Quantification Evaluation in Language Models: Spurious Interactions with Response Length Bias Results","created":"2025-04-18","cited_by_count":21,"area":null},{"id":"2502.19110","title":"Conformal Linguistic Calibration: Trading-off between Factuality and Specificity","created":"2025-02-26","cited_by_count":20,"area":null},{"id":"2510.15103","title":"Continual Learning via Sparse Memory Finetuning","created":"2025-10-16","cited_by_count":20,"area":null},{"id":"2506.00582","title":"Do Language Models Mirror Human Confidence? Exploring Psychological Insights to Address Overconfidence in LLMs","created":"2025-05-31","cited_by_count":19,"area":null},{"id":"2508.13180","title":"Search-Time Data Contamination","created":"2025-08-12","cited_by_count":19,"area":null},{"id":"2505.08253","title":"Evaluating LLM Metrics Through Real-World Capabilities","created":"2025-05-13","cited_by_count":18,"area":null},{"id":"2505.17656","title":"Too Consistent to Detect: A Study of Self-Consistent Errors in LLMs","created":"2025-05-23","cited_by_count":18,"area":null},{"id":"2512.19920","title":"Mitigating LLM Hallucination via Behaviorally Calibrated Reinforcement Learning","created":"2025-12-22","cited_by_count":18,"area":null},{"id":"2512.10791","title":"The FACTS Leaderboard: A Comprehensive Benchmark for Large Language Model Factuality","created":"2025-12-11","cited_by_count":17,"area":null},{"id":"2505.24858","title":"MetaFaith: Faithful Natural Language Uncertainty Expression in LLMs","created":"2025-05-30","cited_by_count":16,"area":null},{"id":"2506.09669","title":"Query-Level Uncertainty in Large Language Models","created":"2025-06-11","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":"2511.13029","title":"AA-Omniscience: Evaluating Cross-Domain Knowledge Reliability in Large Language Models","created":"2025-11-17","cited_by_count":13,"area":null},{"id":"2505.15962","title":"Pre-training Limited Memory Language Models with Internal and External Knowledge","created":"2025-05-21","cited_by_count":12,"area":null},{"id":"2509.21545","title":"Evidence for Limited Metacognition in LLMs","created":"2025-09-25","cited_by_count":12,"area":null},{"id":"2505.16483","title":"Teaching Large Language Models to Maintain Contextual Faithfulness via Synthetic Tasks and Reinforcement Learning","created":"2025-05-22","cited_by_count":11,"area":null},{"id":"2601.05503","title":"Over-Searching in Search-Augmented Large Language Models","created":"2026-01-09","cited_by_count":11,"area":null},{"id":"2502.14828","title":"Fundamental Limitations in Pointwise Defences of LLM Finetuning APIs","created":"2025-02-20","cited_by_count":10,"area":null},{"id":"2509.04292","title":"Inverse IFEval: Can LLMs Unlearn Stubborn Training Conventions to Follow Real Instructions?","created":"2025-09-04","cited_by_count":10,"area":null},{"id":"2512.24661","title":"Do Large Language Models Know What They Are Capable Of?","created":"2025-12-31","cited_by_count":10,"area":null},{"id":"2603.22161","title":"Causal Evidence that Language Models use Confidence to Drive Behavior","created":"2026-03-23","cited_by_count":10,"area":null},{"id":"2501.01558","title":"Predicting the Performance of Black-box LLMs through Follow-up Queries","created":"2025-01-02","cited_by_count":9,"area":null},{"id":"2506.08572","title":"The Geometries of Truth Are Orthogonal Across Tasks","created":"2025-06-10","cited_by_count":9,"area":null},{"id":"2507.03120","title":"How Overconfidence in Initial Choices and Underconfidence Under Criticism Modulate Change of Mind in Large Language Models","created":"2025-07-03","cited_by_count":9,"area":null},{"id":"2602.01031","title":"HalluHard: A Hard Multi-Turn Hallucination Benchmark","created":"2026-02-01","cited_by_count":9,"area":null},{"id":"2501.07482","title":"TiEBe: Tracking Language Model Recall of Notable Worldwide Events Through Time","created":"2025-01-13","cited_by_count":8,"area":null},{"id":"2506.10060","title":"Textual Bayes: Quantifying Prompt Uncertainty in LLM-Based Systems","created":"2025-06-11","cited_by_count":8,"area":null},{"id":"2601.03042","title":"BaseCal: Unsupervised Confidence Calibration via Base Model Signals","created":"2026-01-06","cited_by_count":8,"area":null},{"id":"2606.29490","title":"Reported Confidence in LLMs Tracks Commitment More Than Correctness","created":"2026-06-28","cited_by_count":8,"area":null},{"id":"2412.15265","title":"Chinese SafetyQA: A Safety Short-form Factuality Benchmark for Large Language Models","created":"2024-12-17","cited_by_count":7,"area":null},{"id":"2505.22860","title":"Permissioned LLMs: Enforcing Access Control in Large Language Models","created":"2025-05-28","cited_by_count":7,"area":null},{"id":"2506.03278","title":"FailureSensorIQ: A Multi-Choice QA Dataset for Understanding Sensor Relationships and Failure Modes","created":"2025-06-03","cited_by_count":7,"area":null},{"id":"2510.10238","title":"The Achilles' Heel of LLMs: How Altering a Handful of Neurons Can Cripple Language Abilities","created":"2025-10-11","cited_by_count":7,"area":null},{"id":"2602.13540","title":"On Calibration of Large Language Models: From Response To Capability","created":"2026-02-14","cited_by_count":7,"area":null},{"id":"2604.03216","title":"BAS: A Decision-Theoretic Approach to Evaluating Large Language Model Confidence","created":"2026-04-03","cited_by_count":7,"area":null},{"id":"2607.06973","title":"Rethinking Multimodal Time-Series Forecasting Evaluation","created":"2026-07-08","cited_by_count":7,"area":null},{"id":"2503.01332","title":"Answer, Refuse, or Guess? Investigating Risk-Aware Decision Making in Language Models","created":"2025-03-03","cited_by_count":6,"area":null},{"id":"2505.09338","title":"Llama See, Llama Do: A Mechanistic Perspective on Contextual Entrainment and Distraction in LLMs","created":"2025-05-14","cited_by_count":6,"area":null},{"id":"2505.20295","title":"SelfReflect: Can LLMs Communicate Their Internal Answer Distribution?","created":"2025-05-26","cited_by_count":6,"area":null},{"id":"2508.00109","title":"FACTORY: A Challenging Human-Verified Prompt Set for Long-Form Factuality","created":"2025-07-31","cited_by_count":6,"area":null},{"id":"2510.01782","title":"Can LLMs Refuse Questions They Do Not Know? Measuring Knowledge-Aware Refusal in Factual Tasks","created":"2025-10-02","cited_by_count":6,"area":null},{"id":"2510.07238","title":"When Benchmarks Age: Temporal Misalignment through Large Language Model Factuality Evaluation","created":"2025-10-08","cited_by_count":6,"area":null},{"id":"2605.13829","title":"Negation Neglect: When models fail to learn negations in training","created":"2026-05-13","cited_by_count":6,"area":null},{"id":"2606.14502","title":"From Chatbot to Digital Colleague: The Paradigm Shift Toward Persistent Autonomous AI","created":"2026-06-12","cited_by_count":6,"area":null},{"id":"2505.21115","title":"Will It Still Be True Tomorrow? Multilingual Evergreen Question Classification to Improve Trustworthy QA","created":"2025-05-27","cited_by_count":5,"area":null},{"id":"2506.15662","title":"CC-LEARN: Cohort-based Consistency Learning","created":"2025-06-18","cited_by_count":5,"area":null},{"id":"2509.24202","title":"Can Large Language Models Express Uncertainty Like Human?","created":"2025-09-29","cited_by_count":5,"area":null},{"id":"2604.03904","title":"I-CALM: Incentivizing Confidence-Aware Abstention for LLM Selective Answering","created":"2026-04-05","cited_by_count":5,"area":null},{"id":"2605.01428","title":"Hallucinations Undermine Trust; Metacognition is a Way Forward","created":"2026-05-02","cited_by_count":5,"area":null},{"id":"2605.19276","title":"OpenCompass: A Universal Evaluation Platform for Large Language Models","created":"2026-05-19","cited_by_count":5,"area":null},{"id":"2503.00812","title":"BOSE: A Systematic Evaluation Method Optimized for Base Models","created":"2025-03-02","cited_by_count":4,"area":null},{"id":"2510.14660","title":"An Efficient Rubric-based Generative Verifier for Search-Augmented LLMs","created":"2025-10-16","cited_by_count":4,"area":null},{"id":"2511.04234","title":"Reusing Pre-Training Data at Test Time is a Compute Multiplier","created":"2025-11-06","cited_by_count":4,"area":null},{"id":"2512.14220","title":"Estimating problem difficulty without ground truth using Large Language Model comparisons","created":"2025-12-16","cited_by_count":4,"area":null},{"id":"2605.06350","title":"Is Escalation Worth It? On the Depth of LLM Cascades","created":"2026-05-07","cited_by_count":4,"area":null},{"id":"2607.08186","title":"Hidden Decoding at Scale: Latent Computation Scaling for Large Language Models","created":"2026-07-09","cited_by_count":4,"area":null},{"id":"2502.06655","title":"Unbiased Evaluation of Large Language Models from a Causal Perspective","created":"2025-02-10","cited_by_count":3,"area":null},{"id":"2505.16591","title":"Evaluating Large Language Model with Knowledge Oriented Language Specific Simple Question Answering","created":"2025-05-22","cited_by_count":3,"area":null},{"id":"2508.00673","title":"MELAC: Massive Evaluation of Large Language Models with Alignment of Culture in Persian Language","created":"2025-08-01","cited_by_count":3,"area":null},{"id":"2511.07318","title":"When Bias Pretends to Be Truth: How Spurious Correlations Undermine Hallucination Detection in LLMs","created":"2025-11-10","cited_by_count":3,"area":null},{"id":"2512.23547","title":"Lie to Me: Knowledge Graphs for Robust Hallucination Self-Detection in LLMs","created":"2025-12-29","cited_by_count":3,"area":null},{"id":"2601.08847","title":"Scalable and Reliable Evaluation of AI Knowledge Retrieval Systems: RIKER and the Coherent Simulated Universe","created":"2025-12-22","cited_by_count":3,"area":null},{"id":"2603.05881","title":"Confidence Before Answering: A Paradigm Shift for Efficient LLM Uncertainty Estimation","created":"2026-03-06","cited_by_count":3,"area":null},{"id":"2604.08519","title":"Cram Less to Fit More: Training Data Pruning Improves Memorization of Facts","created":"2026-04-09","cited_by_count":3,"area":null},{"id":"2605.25052","title":"Faithfulness Metrics Don't Measure Faithfulness: A Meta-Evaluation with Ground Truth","created":"2026-05-24","cited_by_count":3,"area":null},{"id":"2606.17574","title":"DeepInsight: A Unified Evaluation Infrastructure Across the Physical AI Stack","created":"2026-06-16","cited_by_count":3,"area":null},{"id":"2607.05752","title":"When Should LLMs Search? Counterfactual Supervision for Search Routing","created":"2026-07-07","cited_by_count":3,"area":null},{"id":"2607.28109","title":"Beyond Rephrasing: Book-Level Organization Improves Synthetic Textbook Data for Mid-Training","created":"2026-07-30","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":"2502.14275","title":"Fact or Guesswork? Evaluating Large Language Models' Medical Knowledge with Structured One-Hop Judgments","created":"2025-02-20","cited_by_count":2,"area":null},{"id":"2505.14101","title":"MultiHal: Multilingual Dataset for Knowledge-Graph Grounded Evaluation of LLM Hallucinations","created":"2025-05-20","cited_by_count":2,"area":null},{"id":"2505.15242","title":"Adaptive Plan-Execute Framework for Smart Contract Security Auditing","created":"2025-05-21","cited_by_count":2,"area":null},{"id":"2512.16108","title":"WeMusic-Agent: Efficient Conversational Music Recommendation via Knowledge Internalization and Agentic Boundary Learning","created":"2025-12-18","cited_by_count":2,"area":null},{"id":"2601.05905","title":"Illusions of Confidence? Diagnosing LLM Truthfulness via Neighborhood Consistency","created":"2026-01-09","cited_by_count":2,"area":null},{"id":"2603.04857","title":"FireBench: Evaluating Instruction Following in Enterprise and API-Driven LLM Applications","created":"2026-03-05","cited_by_count":2,"area":null},{"id":"2604.02368","title":"Xpertbench: Expert Level Tasks with Rubrics-Based Evaluation","created":"2026-03-27","cited_by_count":2,"area":null},{"id":"2604.03695","title":"POEMetric: The Last Stanza of Humanity","created":"2026-04-04","cited_by_count":2,"area":null},{"id":"2605.28778","title":"Can LLMs Use Linguistic Uncertainty Markers to Reliably Reflect Intrinsic Confidence?","created":"2026-05-27","cited_by_count":2,"area":null}],"next_cursor":"100"}