{"list":"other","total":65,"rows":[{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"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":"2401.06209","title":"Eyes Wide Shut? Exploring the Visual Shortcomings of Multimodal LLMs","created":"2024-01-11","cited_by_count":735},{"id":"2309.14525","title":"Aligning Large Multimodal Models with Factually Augmented RLHF","created":"2023-09-25","cited_by_count":712},{"id":"2311.16922","title":"Mitigating Object Hallucinations in Large Vision-Language Models through Visual Contrastive Decoding","created":"2023-11-28","cited_by_count":688},{"id":"2304.13734","title":"The Internal State of an LLM Knows When It's Lying","created":"2023-04-26","cited_by_count":659},{"id":"1703.09788","title":"Towards Automatic Learning of Procedures from Web Instructional Videos","created":"2017-03-28","cited_by_count":619},{"id":"2311.17911","title":"OPERA: Alleviating Hallucination in Multi-Modal Large Language Models via Over-Trust Penalty and Retrospection-Allocation","created":"2023-11-29","cited_by_count":478},{"id":"2306.14565","title":"Mitigating Hallucination in Large Multi-Modal Models via Robust Instruction Tuning","created":"2023-06-26","cited_by_count":445},{"id":"2309.05922","title":"A Survey of Hallucination in Large Foundation Models","created":"2023-09-12","cited_by_count":368},{"id":"2302.12813","title":"Check Your Facts and Try Again: Improving Large Language Models with External Knowledge and Automated Feedback","created":"2023-02-24","cited_by_count":353},{"id":"2305.13534","title":"How Language Model Hallucinations Can Snowball","created":"2023-05-22","cited_by_count":311},{"id":"2309.15112","title":"InternLM-XComposer: A Vision-Language Large Model for Advanced Text-image Comprehension and Composition","created":"2023-09-26","cited_by_count":297},{"id":"2210.08726","title":"RARR: Researching and Revising What Language Models Say, Using Language Models","created":"2022-10-17","cited_by_count":287},{"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":"2304.09116","title":"NaturalSpeech 2: Latent Diffusion Models are Natural and Zero-Shot Speech and Singing Synthesizers","created":"2023-04-18","cited_by_count":235},{"id":"2311.16839","title":"Beyond Hallucinations: Enhancing LVLMs through Hallucination-Aware Direct Preference Optimization","created":"2023-11-28","cited_by_count":225},{"id":"2307.03987","title":"A Stitch in Time Saves Nine: Detecting and Mitigating Hallucinations of LLMs by Validating Low-Confidence Generation","created":"2023-07-08","cited_by_count":206},{"id":"2403.18715","title":"Mitigating Hallucinations in Large Vision-Language Models with Instruction Contrastive Decoding","created":"2024-03-27","cited_by_count":203},{"id":"2305.14552","title":"Sources of Hallucination by Large Language Models on Inference Tasks","created":"2023-05-23","cited_by_count":169},{"id":"2304.13731","title":"Text-to-Audio Generation using Instruction-Tuned LLM and Latent Diffusion Model","created":"2023-04-24","cited_by_count":145},{"id":"2206.07696","title":"Diffusion Models for Video Prediction and Infilling","created":"2022-06-15","cited_by_count":135},{"id":"2303.16104","title":"Hallucinations in Large Multilingual Translation Models","created":"2023-03-28","cited_by_count":129},{"id":"2305.15852","title":"Self-contradictory Hallucinations of Large Language Models: Evaluation, Detection and Mitigation","created":"2023-05-25","cited_by_count":124},{"id":"2312.15915","title":"ChartBench: A Benchmark for Complex Visual Reasoning in Charts","created":"2023-12-26","cited_by_count":120},{"id":"2003.07758","title":"Multi-modal Dense Video Captioning","created":"2020-03-17","cited_by_count":113},{"id":"2307.06908","title":"Generating Benchmarks for Factuality Evaluation of Language Models","created":"2023-07-13","cited_by_count":105},{"id":"2308.01546","title":"MusicLDM: Enhancing Novelty in Text-to-Music Generation Using Beat-Synchronous Mixup Strategies","created":"2023-08-03","cited_by_count":94},{"id":"2307.16372","title":"LP-MusicCaps: LLM-Based Pseudo Music Captioning","created":"2023-07-31","cited_by_count":83},{"id":"2308.12714","title":"VIGC: Visual Instruction Generation and Correction","created":"2023-08-24","cited_by_count":80},{"id":"2210.07688","title":"Plausible May Not Be Faithful: Probing Object Hallucination in Vision-Language Pre-training","created":"2022-10-14","cited_by_count":72},{"id":"2309.02301","title":"CIEM: Contrastive Instruction Evaluation Method for Better Instruction Tuning","created":"2023-09-05","cited_by_count":69},{"id":"2309.05767","title":"Natural Language Supervision for General-Purpose Audio Representations","created":"2023-09-11","cited_by_count":61},{"id":"1904.03870","title":"Streamlined Dense Video Captioning","created":"2019-04-08","cited_by_count":57},{"id":"2308.16890","title":"TouchStone: Evaluating Vision-Language Models by Language Models","created":"2023-08-31","cited_by_count":55},{"id":"2304.14406","title":"Putting People in Their Place: Affordance-Aware Human Insertion into Scenes","created":"2023-04-27","cited_by_count":53},{"id":"2305.14908","title":"PURR: Efficiently Editing Language Model Hallucinations by Denoising Language Model Corruptions","created":"2023-05-24","cited_by_count":53},{"id":"2403.11116","title":"PhD: A ChatGPT-Prompted Visual hallucination Evaluation Dataset","created":"2024-03-17","cited_by_count":45},{"id":"2310.08753","title":"CompA: Addressing the Gap in Compositional Reasoning in Audio-Language Models","created":"2023-10-12","cited_by_count":43},{"id":"2312.11541","title":"CLIPSyntel: CLIP and LLM Synergy for Multimodal Question Summarization in Healthcare","created":"2023-12-16","cited_by_count":43},{"id":"2310.06498","title":"A New Benchmark and Reverse Validation Method for Passage-level Hallucination Detection","created":"2023-10-10","cited_by_count":42},{"id":"2308.12792","title":"Sparks of Large Audio Models: A Survey and Outlook","created":"2023-08-24","cited_by_count":41},{"id":"2311.15548","title":"Deficiency of Large Language Models in Finance: An Empirical Examination of Hallucination","created":"2023-11-27","cited_by_count":41},{"id":"2306.09525","title":"Explaining Legal Concepts with Augmented Large Language Models (GPT-4)","created":"2023-06-15","cited_by_count":40},{"id":"2111.08919","title":"EMScore: Evaluating Video Captioning via Coarse-Grained and Fine-Grained Embedding Matching","created":"2021-11-17","cited_by_count":36},{"id":"2402.06118","title":"ViGoR: Improving Visual Grounding of Large Vision Language Models with Fine-Grained Reward Modeling","created":"2024-02-09","cited_by_count":34},{"id":"2308.10253","title":"StableLLaVA: Enhanced Visual Instruction Tuning with Synthesized Image-Dialogue Data","created":"2023-08-20","cited_by_count":33},{"id":"2311.01463","title":"Creating Trustworthy LLMs: Dealing with Hallucinations in Healthcare AI","created":"2023-09-26","cited_by_count":33},{"id":"2401.17690","title":"EnCLAP: Combining Neural Audio Codec and Audio-Text Joint Embedding for Automated Audio Captioning","created":"2024-01-31","cited_by_count":28},{"id":"2206.00100","title":"VALHALLA: Visual Hallucination for Machine Translation","created":"2022-05-31","cited_by_count":27},{"id":"2309.08051","title":"Retrieval-Augmented Text-to-Audio Generation","created":"2023-09-14","cited_by_count":24},{"id":"2402.00282","title":"PAM: Prompting Audio-Language Models for Audio Quality Assessment","created":"2024-02-01","cited_by_count":20},{"id":"2108.01912","title":"Internal Video Inpainting by Implicit Long-range Propagation","created":"2021-08-04","cited_by_count":19},{"id":"2303.02961","title":"Models See Hallucinations: Evaluating the Factuality in Video Captioning","created":"2023-03-06","cited_by_count":19},{"id":"2401.01596","title":"MedSumm: A Multimodal Approach to Summarizing Code-Mixed Hindi-English Clinical Queries","created":"2024-01-03","cited_by_count":19},{"id":"2402.06986","title":"Cacophony: An Improved Contrastive Audio-Text Model","created":"2024-02-10","cited_by_count":18},{"id":"2303.07902","title":"BLAT: Bootstrapping Language-Audio Pre-training based on AudioSet Tag-guided Synthetic Data","created":"2023-03-14","cited_by_count":15},{"id":"2401.09774","title":"On the Audio Hallucinations in Large Audio-Video Language Models","created":"2024-01-18","cited_by_count":15},{"id":"2110.06100","title":"Improving the Performance of Automated Audio Captioning via Integrating the Acoustic and Semantic Information","created":"2021-10-12","cited_by_count":11},{"id":"2403.17306","title":"Visual Hallucination: Definition, Quantification, and Prescriptive Remediations","created":"2024-03-26","cited_by_count":11},{"id":"2403.19113","title":"FACTOID: FACtual enTailment fOr hallucInation Detection","created":"2024-03-28","cited_by_count":10},{"id":"2106.04144","title":"Adversarial Semantic Hallucination for Domain Generalized Semantic Segmentation","created":"2021-06-08","cited_by_count":9},{"id":"2311.10961","title":"Journey of Hallucination-minimized Generative AI Solutions for Financial Decision Makers","created":"2023-11-18","cited_by_count":7},{"id":"2311.04480","title":"CLearViD: Curriculum Learning for Video Description","created":"2023-11-08","cited_by_count":1}],"next_cursor":null}