{"total":221,"rows":[{"id":"2405.14734","title":"SimPO: Simple Preference Optimization with a Reference-Free Reward","created":"2024-05-23","cited_by_count":963,"area":"alignment"},{"id":"2403.07691","title":"ORPO: Monolithic Preference Optimization without Reference Model","created":"2024-03-12","cited_by_count":562,"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":"2402.01306","title":"KTO: Model Alignment as Prospect Theoretic Optimization","created":"2024-02-02","cited_by_count":264,"area":"lr"},{"id":"2406.15927","title":"Semantic Entropy Probes: Robust and Cheap Hallucination Detection in LLMs","created":"2024-06-22","cited_by_count":259,"area":null},{"id":"2410.02707","title":"LLMs Know More Than They Show: On the Intrinsic Representation of LLM Hallucinations","created":"2024-10-03","cited_by_count":244,"area":null},{"id":"2405.05904","title":"Does Fine-Tuning LLMs on New Knowledge Encourage Hallucinations?","created":"2024-05-09","cited_by_count":232,"area":null},{"id":"2509.04664","title":"Why Language Models Hallucinate","created":"2025-09-04","cited_by_count":220,"area":null},{"id":"2401.01286","title":"A Comprehensive Study of Knowledge Editing for Large Language Models","created":"2024-01-02","cited_by_count":163,"area":null},{"id":"2405.20003","title":"Kernel Language Entropy: Fine-grained Uncertainty Quantification for LLMs from Semantic Similarities","created":"2024-05-30","cited_by_count":159,"area":null},{"id":"2401.01301","title":"Large Legal Fictions: Profiling Legal Hallucinations in Large Language Models","created":"2024-01-02","cited_by_count":150,"area":null},{"id":"2405.17220","title":"RLAIF-V: Open-Source AI Feedback Leads to Super GPT-4V Trustworthiness","created":"2024-05-27","cited_by_count":131,"area":"alignment"},{"id":"2502.06233","title":"Confidence Improves Self-Consistency in LLMs","created":"2025-02-10","cited_by_count":113,"area":"lr"},{"id":"2404.07503","title":"Best Practices and Lessons Learned on Synthetic Data","created":"2024-04-11","cited_by_count":106,"area":"synth"},{"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":"2406.08391","title":"Large Language Models Must Be Taught to Know What They Don't Know","created":"2024-06-12","cited_by_count":100,"area":null},{"id":"2403.05612","title":"Unfamiliar Finetuning Examples Control How Language Models Hallucinate","created":"2024-03-08","cited_by_count":87,"area":"alignment"},{"id":"2405.16908","title":"Can Large Language Models Faithfully Express Their Intrinsic Uncertainty in Words?","created":"2024-05-27","cited_by_count":87,"area":null},{"id":"2502.18439","title":"MAPoRL: Multi-Agent Post-Co-Training for Collaborative Large Language Models with Reinforcement Learning","created":"2025-02-25","cited_by_count":86,"area":"lr"},{"id":"2402.09267","title":"Self-Alignment for Factuality: Mitigating Hallucinations in LLMs via Self-Evaluation","created":"2024-02-14","cited_by_count":80,"area":"alignment"},{"id":"2312.15710","title":"Alleviating Hallucinations of Large Language Models through Induced Hallucinations","created":"2023-12-25","cited_by_count":79,"area":null},{"id":"2405.14622","title":"Calibrated Self-Rewarding Vision Language Models","created":"2024-05-23","cited_by_count":78,"area":"mllm"},{"id":"2402.02420","title":"Factuality of Large Language Models: A Survey","created":"2024-02-04","cited_by_count":66,"area":null},{"id":"2406.10279","title":"We Have a Package for You! A Comprehensive Analysis of Package Hallucinations by Code Generating LLMs","created":"2024-06-12","cited_by_count":65,"area":null},{"id":"2404.00213","title":"Injecting New Knowledge into Large Language Models via Supervised Fine-Tuning","created":"2024-03-30","cited_by_count":58,"area":null},{"id":"2404.11972","title":"Aligning Language Models to Explicitly Handle Ambiguity","created":"2024-04-18","cited_by_count":56,"area":"agents"},{"id":"2402.12847","title":"Instruction-tuned Language Models are Better Knowledge Learners","created":"2024-02-20","cited_by_count":55,"area":null},{"id":"2401.13275","title":"Can AI Assistants Know What They Don't Know?","created":"2024-01-24","cited_by_count":50,"area":null},{"id":"2407.14507","title":"Internal Consistency and Self-Feedback in Large Language Models: A Survey","created":"2024-07-19","cited_by_count":50,"area":"lr"},{"id":"2412.15280","title":"Context-DPO: Aligning Language Models for Context-Faithfulness","created":"2024-12-18","cited_by_count":50,"area":"alignment"},{"id":"2402.02713","title":"Position: What Can Large Language Models Tell Us about Time Series Analysis","created":"2024-02-05","cited_by_count":47,"area":null},{"id":"2402.13220","title":"How Easy is It to Fool Your Multimodal LLMs? An Empirical Analysis on Deceptive Prompts","created":"2024-02-20","cited_by_count":47,"area":"mllm"},{"id":"2405.01525","title":"FLAME: Factuality-Aware Alignment for Large Language Models","created":"2024-05-02","cited_by_count":47,"area":"alignment"},{"id":"2407.14937","title":"Operationalizing a Threat Model for Red-Teaming Large Language Models (LLMs)","created":"2024-07-20","cited_by_count":46,"area":"safety"},{"id":"2311.09533","title":"Effective Large Language Model Adaptation for Improved Grounding and Citation Generation","created":"2023-11-16","cited_by_count":45,"area":null},{"id":"2505.22501","title":"EvolveSearch: An Iterative Self-Evolving Search Agent","created":"2025-05-28","cited_by_count":43,"area":"agents"},{"id":"2403.09972","title":"Think Twice Before Trusting: Self-Detection for Large Language Models through Comprehensive Answer Reflection","created":"2024-03-15","cited_by_count":41,"area":"lr"},{"id":"2403.16073","title":"Combining Fine-Tuning and LLM-based Agents for Intuitive Smart Contract Auditing with Justifications","created":"2024-03-24","cited_by_count":41,"area":"agents"},{"id":"2412.12472","title":"Knowledge Boundary of Large Language Models: A Survey","created":"2024-12-17","cited_by_count":40,"area":null},{"id":"2503.15888","title":"Parameters vs. Context: Fine-Grained Control of Knowledge Reliance in Language Models","created":"2025-03-20","cited_by_count":39,"area":"rag"},{"id":"2311.09114","title":"Ever: Mitigating Hallucination in Large Language Models through Real-Time Verification and Rectification","created":"2023-11-15","cited_by_count":38,"area":null},{"id":"2410.21252","title":"LongReward: Improving Long-context Large Language Models with AI Feedback","created":"2024-10-28","cited_by_count":34,"area":"alignment"},{"id":"2504.04635","title":"Steering off Course: Reliability Challenges in Steering Language Models","created":"2025-04-06","cited_by_count":34,"area":null},{"id":"2402.06544","title":"Calibrating Long-form Generations from Large Language Models","created":"2024-02-09","cited_by_count":32,"area":null},{"id":"2406.10881","title":"Teaching Large Language Models to Express Knowledge Boundary from Their Own Signals","created":"2024-06-16","cited_by_count":32,"area":null},{"id":"2410.18881","title":"Diff-Instruct++: Training One-step Text-to-image Generator Model to Align with Human Preferences","created":"2024-10-24","cited_by_count":31,"area":"diffusion"},{"id":"2501.01306","title":"Think More, Hallucinate Less: Mitigating Hallucinations via Dual Process of Fast and Slow Thinking","created":"2025-01-02","cited_by_count":31,"area":"lr"},{"id":"2410.22685","title":"Improving Uncertainty Quantification in Large Language Models via Semantic Embeddings","created":"2024-10-30","cited_by_count":30,"area":null},{"id":"2501.06521","title":"Fine-tuning Large Language Models for Improving Factuality in Legal Question Answering","created":"2025-01-11","cited_by_count":28,"area":null},{"id":"2503.10728","title":"DarkBench: Benchmarking Dark Patterns in Large Language Models","created":"2025-03-13","cited_by_count":28,"area":null},{"id":"2507.12455","title":"Mitigating Object Hallucinations via Sentence-Level Early Intervention","created":"2025-07-16","cited_by_count":28,"area":"mllm"},{"id":"2410.15595","title":"A Comprehensive Survey of Direct Preference Optimization: Datasets, Theories, Variants, and Applications","created":"2024-10-21","cited_by_count":27,"area":"lr"},{"id":"2509.25760","title":"TruthRL: Incentivizing Truthful LLMs via Reinforcement Learning","created":"2025-09-30","cited_by_count":27,"area":null},{"id":"2406.15718","title":"Beyond the Turn-Based Game: Enabling Real-Time Conversations with Duplex Models","created":"2024-06-22","cited_by_count":26,"area":null},{"id":"2502.00883","title":"SimPER: A Minimalist Approach to Preference Alignment without Hyperparameters","created":"2025-02-02","cited_by_count":25,"area":"alignment"},{"id":"2312.02073","title":"A Glitch in the Matrix? Locating and Detecting Language Model Grounding with Fakepedia","created":"2023-12-04","cited_by_count":24,"area":null},{"id":"2402.11452","title":"AutoPRM: Automating Procedural Supervision for Multi-Step Reasoning via Controllable Question Decomposition","created":"2024-02-18","cited_by_count":24,"area":"lr"},{"id":"2406.11267","title":"Mitigating Large Language Model Hallucination with Faithful Finetuning","created":"2024-06-17","cited_by_count":24,"area":null},{"id":"2503.02846","title":"Mask-DPO: Generalizable Fine-grained Factuality Alignment of LLMs","created":"2025-03-04","cited_by_count":24,"area":"alignment"},{"id":"2311.16842","title":"RELIC: Investigating Large Language Model Responses using Self-Consistency","created":"2023-11-28","cited_by_count":23,"area":"lr"},{"id":"2402.11827","title":"Ask Optimal Questions: Aligning Large Language Models with Retriever's Preference in Conversation","created":"2024-02-19","cited_by_count":23,"area":"alignment"},{"id":"2409.18786","title":"A Survey on the Honesty of Large Language Models","created":"2024-09-27","cited_by_count":23,"area":"alignment"},{"id":"2502.17214","title":"CoT-UQ: Improving Response-wise Uncertainty Quantification in LLMs with Chain-of-Thought","created":"2025-02-24","cited_by_count":23,"area":"lr"},{"id":"2401.08574","title":"Deductive Closure Training of Language Models for Coherence, Accuracy, and Updatability","created":"2024-01-16","cited_by_count":22,"area":null},{"id":"2411.19187","title":"Beyond Logit Lens: Contextual Embeddings for Robust Hallucination Detection & Grounding in VLMs","created":"2024-11-28","cited_by_count":22,"area":"mllm"},{"id":"2501.10799","title":"Step-KTO: Optimizing Mathematical Reasoning through Stepwise Binary Feedback","created":"2025-01-18","cited_by_count":22,"area":"lr"},{"id":"2404.10315","title":"Enhancing Confidence Expression in Large Language Models Through Learning from Past Experience","created":"2024-04-16","cited_by_count":21,"area":null},{"id":"2412.06141","title":"MMedPO: Aligning Medical Vision-Language Models with Clinical-Aware Multimodal Preference Optimization","created":"2024-12-09","cited_by_count":21,"area":"mllm"},{"id":"2404.14986","title":"$\\texttt{MiniMol}$: A Parameter-Efficient Foundation Model for Molecular Learning","created":"2024-04-23","cited_by_count":20,"area":null},{"id":"2405.12701","title":"OLAPH: Improving Factuality in Biomedical Long-form Question Answering","created":"2024-05-21","cited_by_count":20,"area":null},{"id":"2406.07457","title":"Estimating the Hallucination Rate of Generative AI","created":"2024-06-11","cited_by_count":20,"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":"2506.19807","title":"KnowRL: Exploring Knowledgeable Reinforcement Learning for Factuality","created":"2025-06-24","cited_by_count":20,"area":"lr"},{"id":"2404.09971","title":"Constructing Benchmarks and Interventions for Combating Hallucinations in LLMs","created":"2024-04-15","cited_by_count":19,"area":null},{"id":"2408.12325","title":"Improving Factuality in Large Language Models via Decoding-Time Hallucinatory and Truthful Comparators","created":"2024-08-22","cited_by_count":19,"area":null},{"id":"2410.14309","title":"LoGU: Long-form Generation with Uncertainty Expressions","created":"2024-10-18","cited_by_count":19,"area":null},{"id":"2402.11456","title":"FactPICO: Factuality Evaluation for Plain Language Summarization of Medical Evidence","created":"2024-02-18","cited_by_count":18,"area":null},{"id":"2404.18928","title":"Stylus: Automatic Adapter Selection for Diffusion Models","created":"2024-04-29","cited_by_count":18,"area":"diffusion"},{"id":"2406.09264","title":"Position: Towards Bidirectional Human-AI Alignment","created":"2024-06-13","cited_by_count":18,"area":"alignment"},{"id":"2502.15845","title":"Verify when Uncertain: Beyond Self-Consistency in Black Box Hallucination Detection","created":"2025-02-20","cited_by_count":18,"area":"lr"},{"id":"2506.17252","title":"Adaptive Batch-Wise Sample Scheduling for Direct Preference Optimization","created":"2025-06-08","cited_by_count":17,"area":"alignment"},{"id":"2407.03572","title":"Core: Robust Factual Precision with Informative Sub-Claim Identification","created":"2024-07-04","cited_by_count":16,"area":null},{"id":"2410.15821","title":"The effect of fine-tuning on language model toxicity","created":"2024-10-21","cited_by_count":16,"area":null},{"id":"2411.02433","title":"SLED: Self Logits Evolution Decoding for Improving Factuality in Large Language Models","created":"2024-11-01","cited_by_count":16,"area":"moe"},{"id":"2505.24858","title":"MetaFaith: Faithful Natural Language Uncertainty Expression in LLMs","created":"2025-05-30","cited_by_count":16,"area":null},{"id":"2402.07896","title":"Suppressing Pink Elephants with Direct Principle Feedback","created":"2024-02-12","cited_by_count":15,"area":"alignment"},{"id":"2406.10991","title":"Adaptive Query Rewriting: Aligning Rewriters through Marginal Probability of Conversational Answers","created":"2024-06-16","cited_by_count":15,"area":"alignment"},{"id":"2408.13808","title":"Towards Reliable Medical Question Answering: Techniques and Challenges in Mitigating Hallucinations in Language Models","created":"2024-08-25","cited_by_count":15,"area":null},{"id":"2410.18359","title":"Improving Model Factuality with Fine-grained Critique-based Evaluator","created":"2024-10-24","cited_by_count":15,"area":null},{"id":"2404.01295","title":"Towards Safety and Helpfulness Balanced Responses via Controllable Large Language Models","created":"2024-04-01","cited_by_count":14,"area":null},{"id":"2410.03767","title":"Reasoning Elicitation in Language Models via Counterfactual Feedback","created":"2024-10-02","cited_by_count":14,"area":"lr"},{"id":"2410.22071","title":"Distinguishing Ignorance from Error in LLM Hallucinations","created":"2024-10-29","cited_by_count":14,"area":null},{"id":"2505.02686","title":"Sailing by the Stars: A Survey on Reward Models and Learning Strategies for Learning from Rewards","created":"2025-05-05","cited_by_count":14,"area":"lr"},{"id":"2509.25532","title":"Calibrating Verbalized Confidence with Self-Generated Distractors","created":"2025-09-29","cited_by_count":14,"area":"synth"},{"id":"2404.03862","title":"Verifiable by Design: Aligning Language Models to Quote from Pre-Training Data","created":"2024-04-05","cited_by_count":13,"area":"alignment"},{"id":"2406.13124","title":"Learning to Generate Answers with Citations via Factual Consistency Models","created":"2024-06-19","cited_by_count":13,"area":null},{"id":"2412.11803","title":"UAlign: Leveraging Uncertainty Estimations for Factuality Alignment on Large Language Models","created":"2024-12-16","cited_by_count":13,"area":"alignment"},{"id":"2412.12151","title":"SMARTCAL: An Approach to Self-Aware Tool-Use Evaluation and Calibration","created":"2024-12-11","cited_by_count":13,"area":"agents"},{"id":"2503.05079","title":"On a Connection Between Imitation Learning and RLHF","created":"2025-03-07","cited_by_count":13,"area":"alignment"},{"id":"2506.13342","title":"Verifying the Verifiers: Unveiling Pitfalls and Potentials in Fact Verifiers","created":"2025-06-16","cited_by_count":13,"area":null}],"next_cursor":"100"}