{"list":"other","total":52,"rows":[{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"2305.18290","title":"Direct Preference Optimization: Your Language Model is Secretly a Reward Model","created":"2023-05-29","cited_by_count":8065},{"id":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"id":"2301.12597","title":"BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models","created":"2023-01-30","cited_by_count":6137},{"id":"1706.03741","title":"Deep reinforcement learning from human preferences","created":"2017-06-12","cited_by_count":3912},{"id":"2204.05862","title":"Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback","created":"2022-04-12","cited_by_count":3720},{"id":"2304.10592","title":"MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models","created":"2023-04-20","cited_by_count":2711},{"id":"2411.15594","title":"A Survey on LLM-as-a-Judge","created":"2024-11-23","cited_by_count":1423},{"id":"2311.07911","title":"Instruction-Following Evaluation for Large Language Models","created":"2023-11-14","cited_by_count":1228},{"id":"2304.14178","title":"mPLUG-Owl: Modularization Empowers Large Language Models with Multimodality","created":"2023-04-27","cited_by_count":1040},{"id":"1805.07836","title":"Generalized Cross Entropy Loss for Training Deep Neural Networks with Noisy Labels","created":"2018-05-20","cited_by_count":997},{"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":"2304.06767","title":"RAFT: Reward rAnked FineTuning for Generative Foundation Model Alignment","created":"2023-04-13","cited_by_count":686},{"id":"1809.02156","title":"Object Hallucination in Image Captioning","created":"2018-09-06","cited_by_count":669},{"id":"2403.07691","title":"ORPO: Monolithic Preference Optimization without Reference Model","created":"2024-03-12","cited_by_count":562},{"id":"2411.16594","title":"From Generation to Judgment: Opportunities and Challenges of LLM-as-a-judge","created":"2024-11-25","cited_by_count":494},{"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":"2304.05302","title":"RRHF: Rank Responses to Align Language Models with Human Feedback without tears","created":"2023-04-11","cited_by_count":463},{"id":"2211.08411","title":"Large Language Models Struggle to Learn Long-Tail Knowledge","created":"2022-11-15","cited_by_count":458},{"id":"2312.00849","title":"RLHF-V: Towards Trustworthy MLLMs via Behavior Alignment from Fine-grained Correctional Human Feedback","created":"2023-12-01","cited_by_count":412},{"id":"2305.10425","title":"SLiC-HF: Sequence Likelihood Calibration with Human Feedback","created":"2023-05-17","cited_by_count":401},{"id":"2309.06657","title":"Statistical Rejection Sampling Improves Preference Optimization","created":"2023-09-13","cited_by_count":323},{"id":"2311.07397","title":"AMBER: An LLM-free Multi-dimensional Benchmark for MLLMs Hallucination Evaluation","created":"2023-11-13","cited_by_count":300},{"id":"2006.04315","title":"Counterfactual VQA: A Cause-Effect Look at Language Bias","created":"2020-06-08","cited_by_count":266},{"id":"2405.00675","title":"Self-Play Preference Optimization for Language Model Alignment","created":"2024-05-01","cited_by_count":232},{"id":"2311.16839","title":"Beyond Hallucinations: Enhancing LVLMs through Hallucination-Aware Direct Preference Optimization","created":"2023-11-28","cited_by_count":225},{"id":"2402.13446","title":"Large Language Models for Data Annotation and Synthesis: A Survey","created":"2024-02-21","cited_by_count":205},{"id":"2402.11411","title":"Aligning Modalities in Vision Large Language Models via Preference Fine-tuning","created":"2024-02-18","cited_by_count":198},{"id":"2302.00070","title":"Debiasing Vision-Language Models via Biased Prompts","created":"2023-01-31","cited_by_count":149},{"id":"2403.00409","title":"Provably Robust DPO: Aligning Language Models with Noisy Feedback","created":"2024-03-01","cited_by_count":135},{"id":"2210.03329","title":"Calibrating Factual Knowledge in Pretrained Language Models","created":"2022-10-07","cited_by_count":92},{"id":"2109.05433","title":"Are Gender-Neutral Queries Really Gender-Neutral? Mitigating Gender Bias in Image Search","created":"2021-09-12","cited_by_count":90},{"id":"2407.08639","title":"$\\beta$-DPO: Direct Preference Optimization with Dynamic $\\beta$","created":"2024-07-11","cited_by_count":90},{"id":"2402.05369","title":"Noise Contrastive Alignment of Language Models with Explicit Rewards","created":"2024-02-08","cited_by_count":85},{"id":"2404.14233","title":"Detecting and Mitigating Hallucination in Large Vision Language Models via Fine-Grained AI Feedback","created":"2024-04-22","cited_by_count":80},{"id":"2303.10431","title":"DeAR: Debiasing Vision-Language Models with Additive Residuals","created":"2023-03-18","cited_by_count":70},{"id":"2009.08566","title":"MUTANT: A Training Paradigm for Out-of-Distribution Generalization in Visual Question Answering","created":"2020-09-18","cited_by_count":63},{"id":"1403.3610","title":"Making Risk Minimization Tolerant to Label Noise","created":"2014-03-14","cited_by_count":54},{"id":"2406.08702","title":"VLind-Bench: Measuring Language Priors in Large Vision-Language Models","created":"2024-06-13","cited_by_count":45},{"id":"2012.11528","title":"Overcoming Language Priors with Self-supervised Learning for Visual Question Answering","created":"2020-12-17","cited_by_count":43},{"id":"2204.02285","title":"SwapMix: Diagnosing and Regularizing the Over-Reliance on Visual Context in Visual Question Answering","created":"2022-04-05","cited_by_count":38},{"id":"2406.01252","title":"Towards Scalable Automated Alignment of LLMs: A Survey","created":"2024-06-03","cited_by_count":35},{"id":"2210.04692","title":"Language Prior Is Not the Only Shortcut: A Benchmark for Shortcut Learning in VQA","created":"2022-10-10","cited_by_count":30},{"id":"2406.14194","title":"VLBiasBench: A Comprehensive Benchmark for Evaluating Bias in Large Vision-Language Model","created":"2024-06-20","cited_by_count":26},{"id":"2202.12690","title":"On Modality Bias Recognition and Reduction","created":"2022-02-25","cited_by_count":20},{"id":"2112.15324","title":"Deconfounded Visual Grounding","created":"2021-12-31","cited_by_count":16},{"id":"2409.11726","title":"Revealing and Mitigating the Challenge of Detecting Character Knowledge Errors in LLM Role-Playing","created":"2024-09-18","cited_by_count":9},{"id":"2406.01934","title":"Optimal Transport Guided Correlation Assignment for Multimodal Entity Linking","created":"2024-06-04","cited_by_count":5},{"id":"2311.16941","title":"Debiasing Multimodal Models via Causal Information Minimization","created":"2023-11-28","cited_by_count":4},{"id":"2502.05924","title":"Multi-Branch Collaborative Learning Network for Video Quality Assessment in Industrial Video Search","created":"2025-02-09","cited_by_count":2}],"next_cursor":null}