{"total":111,"rows":[{"id":"2312.09390","title":"Weak-to-Strong Generalization: Eliciting Strong Capabilities With Weak Supervision","created":"2023-12-14","cited_by_count":467,"area":"alignment"},{"id":"2401.01313","title":"A Comprehensive Survey of Hallucination Mitigation Techniques in Large Language Models","created":"2024-01-02","cited_by_count":269,"area":null},{"id":"2407.18418","title":"Know Your Limits: A Survey of Abstention in Large Language Models","created":"2024-07-25","cited_by_count":121,"area":null},{"id":"2407.18370","title":"Trust or Escalate: LLM Judges with Provable Guarantees for Human Agreement","created":"2024-07-25","cited_by_count":105,"area":null},{"id":"2402.19450","title":"Functional Benchmarks for Robust Evaluation of Reasoning Performance, and the Reasoning Gap","created":"2024-02-29","cited_by_count":79,"area":"lr"},{"id":"2411.06037","title":"Sufficient Context: A New Lens on Retrieval Augmented Generation Systems","created":"2024-11-09","cited_by_count":72,"area":"rag"},{"id":"2403.12027","title":"From Pixels to Insights: A Survey on Automatic Chart Understanding in the Era of Large Foundation Models","created":"2024-03-18","cited_by_count":53,"area":null},{"id":"2503.02623","title":"Rewarding Doubt: A Reinforcement Learning Approach to Calibrated Confidence Expression of Large Language Models","created":"2025-03-04","cited_by_count":52,"area":null},{"id":"2503.14477","title":"Calibrating Verbal Uncertainty as a Linear Feature to Reduce Hallucinations","created":"2025-03-18","cited_by_count":48,"area":null},{"id":"2402.18243","title":"Learning or Self-aligning? Rethinking Instruction Fine-tuning","created":"2024-02-28","cited_by_count":43,"area":"lr"},{"id":"2509.25760","title":"TruthRL: Incentivizing Truthful LLMs via Reinforcement Learning","created":"2025-09-30","cited_by_count":27,"area":null},{"id":"2407.08039","title":"Knowledge Overshadowing Causes Amalgamated Hallucination in Large Language Models","created":"2024-07-10","cited_by_count":25,"area":null},{"id":"2409.18786","title":"A Survey on the Honesty of Large Language Models","created":"2024-09-27","cited_by_count":23,"area":"alignment"},{"id":"2504.14045","title":"Metacognition and Uncertainty Communication in Humans and Large Language Models","created":"2025-04-18","cited_by_count":23,"area":null},{"id":"2407.12858","title":"Grounding and Evaluation for Large Language Models: Practical Challenges and Lessons Learned (Survey)","created":"2024-07-10","cited_by_count":20,"area":null},{"id":"2401.04695","title":"Narrowing the Knowledge Evaluation Gap: Open-Domain Question Answering with Multi-Granularity Answers","created":"2024-01-09","cited_by_count":18,"area":null},{"id":"2505.23912","title":"LoVeC: Reinforcement Learning for Better Verbalized Confidence in Long-Form Generations","created":"2025-05-29","cited_by_count":17,"area":null},{"id":"2402.11324","title":"EVEDIT: Event-based Knowledge Editing with Deductive Editing Boundaries","created":"2024-02-17","cited_by_count":16,"area":null},{"id":"2410.07627","title":"Automatic Curriculum Expert Iteration for Reliable LLM Reasoning","created":"2024-10-10","cited_by_count":16,"area":"lr"},{"id":"2502.07184","title":"Refine Knowledge of Large Language Models via Adaptive Contrastive Learning","created":"2025-02-11","cited_by_count":15,"area":null},{"id":"2407.01942","title":"Certainly Uncertain: A Benchmark and Metric for Multimodal Epistemic and Aleatoric Awareness","created":"2024-07-02","cited_by_count":14,"area":null},{"id":"2412.06748","title":"Refusal Tokens: A Simple Way to Calibrate Refusals in Large Language Models","created":"2024-12-09","cited_by_count":14,"area":null},{"id":"2503.14481","title":"Don't lie to your friends: Learning what you know from collaborative self-play","created":"2025-03-18","cited_by_count":14,"area":null},{"id":"2506.09669","title":"Query-Level Uncertainty in Large Language Models","created":"2025-06-11","cited_by_count":14,"area":null},{"id":"2410.17234","title":"Fine-Tuning Large Language Models to Appropriately Abstain with Semantic Entropy","created":"2024-10-22","cited_by_count":11,"area":null},{"id":"2412.16974","title":"Cannot or Should Not? Automatic Analysis of Refusal Composition in IFT/RLHF Datasets and Refusal Behavior of Black-Box LLMs","created":"2024-12-22","cited_by_count":11,"area":"alignment"},{"id":"2406.14137","title":"MACAROON: Training Vision-Language Models To Be Your Engaged Partners","created":"2024-06-20","cited_by_count":10,"area":"mllm"},{"id":"2510.09913","title":"Don't Throw Away Your Pretrained Model","created":"2025-10-10","cited_by_count":10,"area":"lr"},{"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":"2405.00711","title":"Fake Artificial Intelligence Generated Contents (FAIGC): A Survey of Theories, Detection Methods, and Opportunities","created":"2024-04-25","cited_by_count":8,"area":"diffusion"},{"id":"2410.16736","title":"Forewarned is Forearmed: Leveraging LLMs for Data Synthesis through Failure-Inducing Exploration","created":"2024-10-22","cited_by_count":7,"area":"synth"},{"id":"2410.19290","title":"Fictitious Synthetic Data Can Improve LLM Factuality via Prerequisite Learning","created":"2024-10-25","cited_by_count":7,"area":"synth"},{"id":"2411.06528","title":"Epistemic Integrity in Large Language Models","created":"2024-11-10","cited_by_count":7,"area":null},{"id":"2507.02870","title":"Loki's Dance of Illusions: A Comprehensive Survey of Hallucination in Large Language Models","created":"2025-06-06","cited_by_count":7,"area":null},{"id":"2605.14038","title":"Model-Adaptive Tool Necessity Reveals the Knowing-Doing Gap in LLM Tool Use","created":"2026-05-13","cited_by_count":7,"area":"agents"},{"id":"2402.11707","title":"Search Engines Post-ChatGPT: How Generative Artificial Intelligence Could Make Search Less Reliable","created":"2024-02-18","cited_by_count":6,"area":null},{"id":"2502.12145","title":"Fast or Better? Balancing Accuracy and Cost in Retrieval-Augmented Generation with Flexible User Control","created":"2025-02-17","cited_by_count":6,"area":"rag"},{"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":"2506.00166","title":"Disentangled Safety Adapters Enable Efficient Guardrails and Flexible Inference-Time Alignment","created":"2025-05-30","cited_by_count":6,"area":"alignment"},{"id":"2510.01152","title":"MASH: Modeling Abstention via Selective Help-Seeking","created":"2025-10-01","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":"2512.16883","title":"AdaSearch: Balancing Parametric Knowledge and Search in Large Language Models via Reinforcement Learning","created":"2025-12-18","cited_by_count":6,"area":null},{"id":"2503.01550","title":"None of the Above, Less of the Right: Parallel Patterns between Humans and LLMs on Multi-Choice Questions Answering","created":"2025-03-03","cited_by_count":5,"area":null},{"id":"2505.07184","title":"Structural Entropy Guided Agent for Detecting and Repairing Knowledge Deficiencies in LLMs","created":"2025-05-12","cited_by_count":5,"area":"agents"},{"id":"2510.17733","title":"Train for Truth, Keep the Skills: Binary Retrieval-Augmented Reward Mitigates Hallucinations","created":"2025-10-20","cited_by_count":5,"area":"rag"},{"id":"2605.09698","title":"Ambig-DS: A Benchmark for Task-Framing Ambiguity in Data-Science Agents","created":"2026-05-10","cited_by_count":5,"area":"agents"},{"id":"2504.09895","title":"Learning from Reference Answers: Versatile Language Model Alignment without Binary Human Preference Data","created":"2025-04-14","cited_by_count":4,"area":"alignment"},{"id":"2504.18346","title":"Comparing Uncertainty Measurement and Mitigation Methods for Large Language Models: A Systematic Review","created":"2025-04-25","cited_by_count":4,"area":null},{"id":"2506.07309","title":"ConfRAG: Confidence-Guided Retrieval-Augmenting Generation","created":"2025-06-08","cited_by_count":4,"area":"rag"},{"id":"2507.08371","title":"The Curious Case of Factuality Finetuning: Models' Internal Beliefs Can Improve Factuality","created":"2025-07-11","cited_by_count":4,"area":"synth"},{"id":"2512.15528","title":"EmoCaliber: Advancing Reliable Visual Emotion Comprehension via Confidence Verbalization and Calibration","created":"2025-12-17","cited_by_count":4,"area":null},{"id":"2605.29648","title":"Beyond Math and Code: Lightweight Corpus-Grounded Process Rewards for Factual Question Answering","created":"2026-05-28","cited_by_count":4,"area":"lr"},{"id":"2606.32032","title":"Reinforcement Learning with Metacognitive Feedback Elicits Faithful Uncertainty Expression in LLMs","created":"2026-06-30","cited_by_count":4,"area":"alignment"},{"id":"2407.00365","title":"Financial Knowledge Large Language Model","created":"2024-06-29","cited_by_count":3,"area":null},{"id":"2409.16913","title":"Tell Me What You Don't Know: Enhancing Refusal Capabilities of Role-Playing Agents via Representation Space Analysis and Editing","created":"2024-09-25","cited_by_count":3,"area":null},{"id":"2506.14387","title":"SEAT: Sparse Entity-Aware Tuning for Knowledge Adaptation while Preserving Epistemic Abstention","created":"2025-06-17","cited_by_count":3,"area":null},{"id":"2510.17509","title":"Annotation-Efficient Universal Honesty Alignment","created":"2025-10-20","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":"2607.01612","title":"Scaling with Confidence: Calibrating Confidence of LLMs for Adaptive Test Time Scaling","created":"2026-07-02","cited_by_count":3,"area":"lr"},{"id":"2608.26846","title":"Evaluating Confidence-Gated Retrieval with Matched Trajectory Replay","created":"2026-08-27","cited_by_count":3,"area":"agents"},{"id":"2505.10792","title":"Finetune-RAG: Fine-Tuning Language Models to Resist Hallucination in Retrieval-Augmented Generation","created":"2025-05-16","cited_by_count":2,"area":"rag"},{"id":"2506.04051","title":"High Accuracy, Less Talk (HALT): Reliable LLMs through Capability-Aligned Finetuning","created":"2025-06-04","cited_by_count":2,"area":null},{"id":"2602.02605","title":"Fine-Tuning Language Models to Know What They Know","created":"2026-02-02","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},{"id":"2608.11977","title":"Retry, Switch, or Abstain? Learning Strategy-Aware Tool-Use Policies via Controlled Error Injection","created":"2026-08-12","cited_by_count":2,"area":"agents"},{"id":"2409.06601","title":"LaMsS: When Large Language Models Meet Self-Skepticism","created":"2024-09-10","cited_by_count":1,"area":null},{"id":"2412.16615","title":"Large Language Model Can Be a Foundation for Hidden Rationale-Based Retrieval","created":"2024-12-21","cited_by_count":1,"area":"rag"},{"id":"2505.21218","title":"Pretrained LLMs Learn Multiple Types of Uncertainty","created":"2025-05-27","cited_by_count":1,"area":null},{"id":"2509.23570","title":"Improving constraint-based discovery with robust propagation and reliable LLM priors","created":"2025-09-28","cited_by_count":1,"area":null},{"id":"2604.26419","title":"Delineating Knowledge Boundaries for Honest Large Vision-Language Models","created":"2026-04-29","cited_by_count":1,"area":"mllm"},{"id":"2605.15416","title":"Margin-Adaptive Confidence Ranking for Reliable LLM Judgement","created":"2026-05-14","cited_by_count":1,"area":null},{"id":"2605.18792","title":"Trust or Abstain? A Self-Aware RAG Approach","created":"2026-05-11","cited_by_count":1,"area":"rag"},{"id":"2606.00251","title":"Capability Self-Assessment in Large Language Models","created":"2026-05-29","cited_by_count":1,"area":null},{"id":"2606.32012","title":"CoMet: Context and Multiplicity Decomposition for Multimodal Uncertainty Estimation","created":"2026-06-30","cited_by_count":1,"area":null},{"id":"2607.00447","title":"Understanding Why Language Models Hallucinate: Testing Reasoning Against Priors","created":"2026-07-01","cited_by_count":1,"area":"lr"},{"id":"2607.20492","title":"PhantomFill: When the Form Demands an Answer, Language Models Invent One","created":"2026-06-11","cited_by_count":1,"area":null},{"id":"2508.14025","title":"Ask Good Questions for Large Language Models","created":"2025-08-19","cited_by_count":0,"area":null},{"id":"2511.06073","title":"Stemming Hallucination in Language Models Using a Licensing Oracle","created":"2025-11-08","cited_by_count":0,"area":null},{"id":"2602.02258","title":"Alignment-Aware Model Adaptation via Feedback-Guided Optimization","created":"2026-02-02","cited_by_count":0,"area":null},{"id":"2602.10801","title":"Deep Learning-based Method for Expressing Knowledge Boundary of Black-Box LLM","created":"2026-02-11","cited_by_count":0,"area":null},{"id":"2603.29492","title":"Calibrated Confidence Expression for Radiology Report Generation","created":"2026-03-31","cited_by_count":0,"area":"mllm"},{"id":"2604.14170","title":"Stateful Evidence-Driven Retrieval-Augmented Generation with Iterative Reasoning","created":"2026-03-25","cited_by_count":0,"area":"lr"},{"id":"2605.01749","title":"Only Say What You Know: Calibration-Aware Generation for Long-Form Factuality","created":"2026-05-03","cited_by_count":0,"area":"lr"},{"id":"2605.12384","title":"Scalable Token-Level Hallucination Detection in Large Language Models","created":"2026-05-12","cited_by_count":0,"area":null},{"id":"2605.17029","title":"Task Abstention for Large Language Models in Code Generation","created":"2026-05-16","cited_by_count":0,"area":null},{"id":"2605.26902","title":"ICICLE: Expanding Retrieval with In-Context Documents","created":"2026-05-26","cited_by_count":0,"area":null},{"id":"2606.00919","title":"Towards Lightweight Reliability: Using Soft Prompts for Hallucination Mitigation in Large Language Models","created":"2026-05-30","cited_by_count":0,"area":null},{"id":"2606.07523","title":"Retrieval Augmented Generation Framework for the Nepali Legal Domain Question Answering","created":"2026-04-20","cited_by_count":0,"area":"rag"},{"id":"2606.13171","title":"NTS-CoT: Mitigating Hallucinations in LLM-based News Timeline Summarization with Chain-of-Thought Reasoning","created":"2026-06-11","cited_by_count":0,"area":"lr"},{"id":"2607.12831","title":"Knowledgeless Language Models: Suppressing Parametric Recall for Evidence-Grounded Language Modeling","created":"2026-07-14","cited_by_count":0,"area":null},{"id":"2607.20500","title":"FlowEdit: Information-Theoretic Control of LLM Reasoning Flows for Ill-posed Problems Involving Conflicts","created":"2026-06-20","cited_by_count":0,"area":"lr"},{"id":"2608.02553","title":"A Taxonomy of Cognitive Capability Gaps in Generative and Agentic AI","created":"2026-08-03","cited_by_count":0,"area":"agents"},{"id":"2608.10315","title":"Is This Your Final Answer? Cross-Contextual Consistency as a Measure of LLM Credibility","created":"2026-08-10","cited_by_count":0,"area":null},{"id":"2608.22483","title":"Claim-Level Confidence Calibration for Reliable Decision Making with Large Language Models","created":"2026-08-23","cited_by_count":0,"area":null},{"id":"2608.26121","title":"Can a Model Catch Its Own Hallucinations for Free?: Label-Free Doubt Signals Hold Their Own Against a Labelled Dataset for Abstention","created":"2026-06-19","cited_by_count":0,"area":null},{"id":"2608.26168","title":"Hallucinations in LLMs: A Lifecycle-Based Survey of Causes, Detection, Mitigation, and Prevention","created":"2026-07-20","cited_by_count":0,"area":null},{"id":"2609.02771","title":"From Reweighting to Rewriting: Unlocking the Intervention Effects of Influential Samples in Training Data Attribution","created":"2026-09-02","cited_by_count":0,"area":null},{"id":"2609.17516","title":"When Should LLMs Abstain? Chain-of-Self-Questioning for Selective Risk Control","created":"2026-09-15","cited_by_count":0,"area":null},{"id":"2609.17708","title":"Confidence Comes from Experience: Experiential Confidence Estimation from Reasoning to Agents","created":"2026-09-15","cited_by_count":0,"area":"lr"}],"next_cursor":"100"}