{"list":"other","total":98,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"2006.11239","title":"Denoising Diffusion Probabilistic Models","created":"2020-06-19","cited_by_count":21076},{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"1910.10683","title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","created":"2019-10-23","cited_by_count":14599},{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"2306.05685","title":"Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena","created":"2023-06-09","cited_by_count":8626},{"id":"2009.03300","title":"Measuring Massive Multitask Language Understanding","created":"2020-09-07","cited_by_count":7963},{"id":"1804.07461","title":"GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding","created":"2018-04-20","cited_by_count":4899},{"id":"1612.00796","title":"Overcoming catastrophic forgetting in neural networks","created":"2016-12-02","cited_by_count":4787},{"id":"2310.03744","title":"Improved Baselines with Visual Instruction Tuning","created":"2023-10-05","cited_by_count":4418},{"id":"1902.00751","title":"Parameter-Efficient Transfer Learning for NLP","created":"2019-02-02","cited_by_count":4236},{"id":"2210.08402","title":"LAION-5B: An open large-scale dataset for training next generation image-text models","created":"2022-10-16","cited_by_count":4152},{"id":"1905.07830","title":"HellaSwag: Can a Machine Really Finish Your Sentence?","created":"2019-05-19","cited_by_count":4100},{"id":"2104.08691","title":"The Power of Scale for Parameter-Efficient Prompt Tuning","created":"2021-04-18","cited_by_count":3795},{"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":"2208.12242","title":"DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generation","created":"2022-08-25","cited_by_count":3300},{"id":"1710.10196","title":"Progressive Growing of GANs for Improved Quality, Stability, and Variation","created":"2017-10-27","cited_by_count":2988},{"id":"2109.07958","title":"TruthfulQA: Measuring How Models Mimic Human Falsehoods","created":"2021-09-08","cited_by_count":2975},{"id":"1911.11641","title":"PIQA: Reasoning about Physical Commonsense in Natural Language","created":"2019-11-26","cited_by_count":2883},{"id":"2202.05262","title":"Locating and Editing Factual Associations in GPT","created":"2022-02-10","cited_by_count":2691},{"id":"2101.00027","title":"The Pile: An 800GB Dataset of Diverse Text for Language Modeling","created":"2020-12-31","cited_by_count":2411},{"id":"1803.03635","title":"The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks","created":"2018-03-09","cited_by_count":2262},{"id":"2208.01618","title":"An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversion","created":"2022-08-02","cited_by_count":2245},{"id":"1411.1784","title":"Conditional Generative Adversarial Nets","created":"2014-11-06","cited_by_count":2162},{"id":"1703.04730","title":"Understanding Black-box Predictions via Influence Functions","created":"2017-03-14","cited_by_count":1741},{"id":"2307.02483","title":"Jailbroken: How Does LLM Safety Training Fail?","created":"2023-07-05","cited_by_count":1651},{"id":"2203.05482","title":"Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time","created":"2022-03-10","cited_by_count":1396},{"id":"1705.08690","title":"Continual Learning with Deep Generative Replay","created":"2017-05-24","cited_by_count":1158},{"id":"2310.03693","title":"Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To!","created":"2023-10-05","cited_by_count":1154},{"id":"1912.03817","title":"Machine Unlearning","created":"2019-12-09","cited_by_count":1061},{"id":"1506.06724","title":"Aligning Books and Movies: Towards Story-like Visual Explanations by Watching Movies and Reading Books","created":"2015-06-22","cited_by_count":1043},{"id":"2305.13301","title":"Training Diffusion Models with Reinforcement Learning","created":"2023-05-22","cited_by_count":982},{"id":"2004.09456","title":"StereoSet: Measuring stereotypical bias in pretrained language models","created":"2020-04-20","cited_by_count":924},{"id":"2205.05638","title":"Few-Shot Parameter-Efficient Fine-Tuning is Better and Cheaper than In-Context Learning","created":"2022-05-11","cited_by_count":896},{"id":"2307.04657","title":"BeaverTails: Towards Improved Safety Alignment of LLM via a Human-Preference Dataset","created":"2023-07-10","cited_by_count":860},{"id":"2212.09251","title":"Discovering Language Model Behaviors with Model-Written Evaluations","created":"2022-12-19","cited_by_count":836},{"id":"1801.07243","title":"Personalizing Dialogue Agents: I have a dog, do you have pets too?","created":"2018-01-22","cited_by_count":828},{"id":"2109.01903","title":"Robust fine-tuning of zero-shot models","created":"2021-09-04","cited_by_count":797},{"id":"2107.06499","title":"Deduplicating Training Data Makes Language Models Better","created":"2021-07-14","cited_by_count":714},{"id":"2309.14525","title":"Aligning Large Multimodal Models with Factually Augmented RLHF","created":"2023-09-25","cited_by_count":712},{"id":"2010.00133","title":"CrowS-Pairs: A Challenge Dataset for Measuring Social Biases in Masked Language Models","created":"2020-09-30","cited_by_count":710},{"id":"1809.02156","title":"Object Hallucination in Image Captioning","created":"2018-09-06","cited_by_count":669},{"id":"1905.13319","title":"MathQA: Towards Interpretable Math Word Problem Solving with Operation-Based Formalisms","created":"2019-05-30","cited_by_count":662},{"id":"1912.05671","title":"Linear Mode Connectivity and the Lottery Ticket Hypothesis","created":"2019-12-11","cited_by_count":637},{"id":"2111.09832","title":"Merging Models with Fisher-Weighted Averaging","created":"2021-11-18","cited_by_count":621},{"id":"1911.04933","title":"Eternal Sunshine of the Spotless Net: Selective Forgetting in Deep Networks","created":"2019-11-12","cited_by_count":618},{"id":"1911.03030","title":"Certified Data Removal from Machine Learning Models","created":"2019-11-08","cited_by_count":535},{"id":"1911.12237","title":"SAMSum Corpus: A Human-annotated Dialogue Dataset for Abstractive Summarization","created":"2019-11-27","cited_by_count":535},{"id":"2203.14680","title":"Transformer Feed-Forward Layers Build Predictions by Promoting Concepts in the Vocabulary Space","created":"2022-03-28","cited_by_count":532},{"id":"2211.05105","title":"Safe Latent Diffusion: Mitigating Inappropriate Degeneration in Diffusion Models","created":"2022-11-09","cited_by_count":513},{"id":"2403.03218","title":"The WMDP Benchmark: Measuring and Reducing Malicious Use With Unlearning","created":"2024-03-05","cited_by_count":509},{"id":"2404.02151","title":"Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attacks","created":"2024-04-02","cited_by_count":486},{"id":"2209.04836","title":"Git Re-Basin: Merging Models modulo Permutation Symmetries","created":"2022-09-11","cited_by_count":471},{"id":"1907.05012","title":"Making AI Forget You: Data Deletion in Machine Learning","created":"2019-07-11","cited_by_count":465},{"id":"2310.06987","title":"Catastrophic Jailbreak of Open-source LLMs via Exploiting Generation","created":"2023-10-10","cited_by_count":451},{"id":"2206.06520","title":"Memory-Based Model Editing at Scale","created":"2022-06-13","cited_by_count":447},{"id":"2306.14565","title":"Mitigating Hallucination in Large Multi-Modal Models via Robust Instruction Tuning","created":"2023-06-26","cited_by_count":445},{"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":"2012.10289","title":"HateXplain: A Benchmark Dataset for Explainable Hate Speech Detection","created":"2020-12-18","cited_by_count":407},{"id":"1903.04561","title":"Nuanced Metrics for Measuring Unintended Bias with Real Data for Text Classification","created":"2019-03-11","cited_by_count":404},{"id":"2308.14761","title":"Unified Concept Editing in Diffusion Models","created":"2023-08-25","cited_by_count":388},{"id":"2212.09849","title":"Dataless Knowledge Fusion by Merging Weights of Language Models","created":"2022-12-19","cited_by_count":387},{"id":"2109.01247","title":"Do Prompt-Based Models Really Understand the Meaning of their Prompts?","created":"2021-09-02","cited_by_count":326},{"id":"2202.04053","title":"DALL-Eval: Probing the Reasoning Skills and Social Biases of Text-to-Image Generation Models","created":"2022-02-08","cited_by_count":230},{"id":"2310.11868","title":"To Generate or Not? Safety-Driven Unlearned Diffusion Models Are Still Easy To Generate Unsafe Images ... For Now","created":"2023-10-18","cited_by_count":210},{"id":"2208.05592","title":"Patching open-vocabulary models by interpolating weights","created":"2022-08-10","cited_by_count":190},{"id":"1909.07083","title":"Controllable Text-to-Image Generation","created":"2019-09-16","cited_by_count":187},{"id":"2003.02960","title":"Forgetting Outside the Box: Scrubbing Deep Networks of Information Accessible from Input-Output Observations","created":"2020-03-05","cited_by_count":180},{"id":"2305.15324","title":"Model evaluation for extreme risks","created":"2023-05-24","cited_by_count":177},{"id":"2308.08742","title":"PMET: Precise Model Editing in a Transformer","created":"2023-08-17","cited_by_count":173},{"id":"2402.08567","title":"Agent Smith: A Single Image Can Jailbreak One Million Multimodal LLM Agents Exponentially Fast","created":"2024-02-13","cited_by_count":153},{"id":"2311.03287","title":"Holistic Analysis of Hallucination in GPT-4V(ision): Bias and Interference Challenges","created":"2023-11-06","cited_by_count":131},{"id":"2312.03689","title":"Evaluating and Mitigating Discrimination in Language Model Decisions","created":"2023-12-06","cited_by_count":124},{"id":"2201.05273","title":"Pretrained Language Models for Text Generation: A Survey","created":"2022-01-14","cited_by_count":122},{"id":"2311.17717","title":"Receler: Reliable Concept Erasing of Text-to-Image Diffusion Models via Lightweight Erasers","created":"2023-11-29","cited_by_count":120},{"id":"2010.12883","title":"Variational Bayesian Unlearning","created":"2020-10-24","cited_by_count":117},{"id":"2402.04401","title":"Democratizing Large Language Models via Personalized Parameter-Efficient Fine-tuning","created":"2024-02-06","cited_by_count":90},{"id":"2311.09127","title":"Jailbreaking GPT-4V via Self-Adversarial Attacks with System Prompts","created":"2023-11-15","cited_by_count":65},{"id":"2401.05779","title":"Erasing Undesirable Influence in Diffusion Models","created":"2024-01-11","cited_by_count":57},{"id":"2305.12434","title":"BiasAsker: Measuring the Bias in Conversational AI System","created":"2023-05-21","cited_by_count":53},{"id":"2403.11901","title":"Larimar: Large Language Models with Episodic Memory Control","created":"2024-03-18","cited_by_count":53},{"id":"2404.05880","title":"Eraser: Jailbreaking Defense in Large Language Models via Unlearning Harmful Knowledge","created":"2024-04-08","cited_by_count":51},{"id":"2402.00351","title":"Machine Unlearning for Image-to-Image Generative Models","created":"2024-02-01","cited_by_count":47},{"id":"2402.02333","title":"Copyright Protection in Generative AI: A Technical Perspective","created":"2024-02-04","cited_by_count":38},{"id":"2402.08113","title":"Addressing cognitive bias in medical language models","created":"2024-02-12","cited_by_count":36},{"id":"2211.03216","title":"Unlearning Graph Classifiers with Limited Data Resources","created":"2022-11-06","cited_by_count":31},{"id":"2403.16257","title":"Unlearning Backdoor Threats: Enhancing Backdoor Defense in Multimodal Contrastive Learning via Local Token Unlearning","created":"2024-03-24","cited_by_count":31},{"id":"2306.02174","title":"Training Data Attribution for Diffusion Models","created":"2023-06-03","cited_by_count":24},{"id":"2303.05699","title":"Feature Unlearning for Pre-trained GANs and VAEs","created":"2023-03-10","cited_by_count":16},{"id":"2309.16082","title":"Forgetting Private Textual Sequences in Language Models via Leave-One-Out Ensemble","created":"2023-09-28","cited_by_count":6},{"id":"2312.14895","title":"FAST: Feature Aware Similarity Thresholding for Weak Unlearning in Black-Box Generative Models","created":"2023-12-22","cited_by_count":5}],"next_cursor":null}