{"list":"other","total":53,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2505.09388","title":"Qwen3 Technical Report","created":"2025-05-14","cited_by_count":8820},{"id":"2210.03629","title":"ReAct: Synergizing Reasoning and Acting in Language Models","created":"2022-10-06","cited_by_count":8695},{"id":"1809.09600","title":"HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering","created":"2018-09-25","cited_by_count":3754},{"id":"1705.03551","title":"TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension","created":"2017-05-09","cited_by_count":2955},{"id":"1611.01144","title":"Categorical Reparameterization with Gumbel-Softmax","created":"2016-11-03","cited_by_count":2739},{"id":"1811.00937","title":"CommonsenseQA: A Question Answering Challenge Targeting Commonsense Knowledge","created":"2018-11-02","cited_by_count":1822},{"id":"2311.05232","title":"A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions","created":"2023-11-09","cited_by_count":1601},{"id":"2306.03341","title":"Inference-Time Intervention: Eliciting Truthful Answers from a Language Model","created":"2023-06-06","cited_by_count":1302},{"id":"2305.14251","title":"FActScore: Fine-grained Atomic Evaluation of Factual Precision in Long Form Text Generation","created":"2023-05-23","cited_by_count":1282},{"id":"2209.00796","title":"Diffusion Models: A Comprehensive Survey of Methods and Applications","created":"2022-09-02","cited_by_count":1114},{"id":"2205.14217","title":"Diffusion-LM Improves Controllable Text Generation","created":"2022-05-27","cited_by_count":1027},{"id":"2305.13301","title":"Training Diffusion Models with Reinforcement Learning","created":"2023-05-22","cited_by_count":982},{"id":"2306.13063","title":"Can LLMs Express Their Uncertainty? An Empirical Evaluation of Confidence Elicitation in LLMs","created":"2023-06-22","cited_by_count":974},{"id":"1612.00410","title":"Deep Variational Information Bottleneck","created":"2016-12-01","cited_by_count":930},{"id":"2502.09992","title":"Large Language Diffusion Models","created":"2025-02-14","cited_by_count":912},{"id":"2406.07524","title":"Simple and Effective Masked Diffusion Language Models","created":"2024-06-11","cited_by_count":848},{"id":"2302.09664","title":"Semantic Uncertainty: Linguistic Invariances for Uncertainty Estimation in Natural Language Generation","created":"2023-02-19","cited_by_count":819},{"id":"2303.08896","title":"SelfCheckGPT: Zero-Resource Black-Box Hallucination Detection for Generative Large Language Models","created":"2023-03-15","cited_by_count":810},{"id":"1503.02406","title":"Deep Learning and the Information Bottleneck Principle","created":"2015-03-09","cited_by_count":802},{"id":"2212.03827","title":"Discovering Latent Knowledge in Language Models Without Supervision","created":"2022-12-07","cited_by_count":767},{"id":"2205.14334","title":"Teaching Models to Express Their Uncertainty in Words","created":"2022-05-28","cited_by_count":751},{"id":"2310.06824","title":"The Geometry of Truth: Emergent Linear Structure in Large Language Model Representations of True/False Datasets","created":"2023-10-10","cited_by_count":712},{"id":"2309.01219","title":"Siren's Song in the AI Ocean: A Survey on Hallucination in Large Language Models","created":"2023-09-03","cited_by_count":698},{"id":"2304.13734","title":"The Internal State of an LLM Knows When It's Lying","created":"2023-04-26","cited_by_count":659},{"id":"2406.04329","title":"Simplified and Generalized Masked Diffusion for Discrete Data","created":"2024-06-06","cited_by_count":626},{"id":"2508.15487","title":"Dream 7B: Diffusion Large Language Models","created":"2025-08-21","cited_by_count":544},{"id":"2309.05922","title":"A Survey of Hallucination in Large Foundation Models","created":"2023-09-12","cited_by_count":368},{"id":"2402.03744","title":"INSIDE: LLMs' Internal States Retain the Power of Hallucination Detection","created":"2024-02-06","cited_by_count":323},{"id":"2305.19187","title":"Generating with Confidence: Uncertainty Quantification for Black-box Large Language Models","created":"2023-05-30","cited_by_count":293},{"id":"2406.15927","title":"Semantic Entropy Probes: Robust and Cheap Hallucination Detection in LLMs","created":"2024-06-22","cited_by_count":259},{"id":"2307.13528","title":"FacTool: Factuality Detection in Generative AI -- A Tool Augmented Framework for Multi-Task and Multi-Domain Scenarios","created":"2023-07-25","cited_by_count":251},{"id":"2505.15809","title":"MMaDA: Multimodal Large Diffusion Language Models","created":"2025-05-21","cited_by_count":250},{"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},{"id":"2209.15558","title":"Out-of-Distribution Detection and Selective Generation for Conditional Language Models","created":"2022-09-30","cited_by_count":197},{"id":"2504.12216","title":"d1: Scaling Reasoning in Diffusion Large Language Models via Reinforcement Learning","created":"2025-04-16","cited_by_count":186},{"id":"2403.06963","title":"The pitfalls of next-token prediction","created":"2024-03-11","cited_by_count":160},{"id":"2410.11414","title":"ReDeEP: Detecting Hallucination in Retrieval-Augmented Generation via Mechanistic Interpretability","created":"2024-10-15","cited_by_count":101},{"id":"2409.17504","title":"HaloScope: Harnessing Unlabeled LLM Generations for Hallucination Detection","created":"2024-09-26","cited_by_count":99},{"id":"1904.00876","title":"Significance-aware Information Bottleneck for Domain Adaptive Semantic Segmentation","created":"2019-04-01","cited_by_count":74},{"id":"2502.03628","title":"The Hidden Life of Tokens: Reducing Hallucination of Large Vision-Language Models via Visual Information Steering","created":"2025-02-05","cited_by_count":66},{"id":"2503.01917","title":"Steer LLM Latents for Hallucination Detection","created":"2025-03-01","cited_by_count":50},{"id":"2312.17484","title":"Truth Forest: Toward Multi-Scale Truthfulness in Large Language Models through Intervention without Tuning","created":"2023-12-29","cited_by_count":45},{"id":"2306.02109","title":"Encoding Time-Series Explanations through Self-Supervised Model Behavior Consistency","created":"2023-06-03","cited_by_count":42},{"id":"1909.07405","title":"BottleSum: Unsupervised and Self-supervised Sentence Summarization using the Information Bottleneck Principle","created":"2019-09-16","cited_by_count":39},{"id":"2405.09308","title":"TimeX++: Learning Time-Series Explanations with Information Bottleneck","created":"2024-05-15","cited_by_count":33},{"id":"2410.15644","title":"Procedural Content Generation in Games: A Survey with Insights on Emerging LLM Integration","created":"2024-10-21","cited_by_count":22},{"id":"2406.01549","title":"An Information Bottleneck Perspective for Effective Noise Filtering on Retrieval-Augmented Generation","created":"2024-06-03","cited_by_count":16},{"id":"2501.09997","title":"Attention-guided Self-reflection for Zero-shot Hallucination Detection in Large Language Models","created":"2025-01-17","cited_by_count":16},{"id":"2503.03595","title":"Towards Understanding Text Hallucination of Diffusion Models via Local Generation Bias","created":"2025-03-05","cited_by_count":11},{"id":"2502.20750","title":"Mitigating Hallucinations in Large Vision-Language Models by Adaptively Constraining Information Flow","created":"2025-02-28","cited_by_count":9},{"id":"2411.02603","title":"FactTest: Factuality Testing in Large Language Models with Finite-Sample and Distribution-Free Guarantees","created":"2024-11-04","cited_by_count":7}],"next_cursor":null}