{"total":1741,"rows":[{"id":"2303.17760","title":"CAMEL: Communicative Agents for \"Mind\" Exploration of Large Language Model Society","created":"2023-03-31","cited_by_count":1395,"area":"agents"},{"id":"2304.14108","title":"DataComp: In search of the next generation of multimodal datasets","created":"2023-04-27","cited_by_count":644,"area":"diffusion"},{"id":"2107.07075","title":"Deep Learning on a Data Diet: Finding Important Examples Early in Training","created":"2021-07-15","cited_by_count":533,"area":null},{"id":"2402.04333","title":"LESS: Selecting Influential Data for Targeted Instruction Tuning","created":"2024-02-06","cited_by_count":532,"area":null},{"id":"2404.05868","title":"Negative Preference Optimization: From Catastrophic Collapse to Effective Unlearning","created":"2024-04-08","cited_by_count":504,"area":"alignment"},{"id":"2108.13624","title":"Towards Out-Of-Distribution Generalization: A Survey","created":"2021-08-31","cited_by_count":436,"area":null},{"id":"2310.12508","title":"SalUn: Empowering Machine Unlearning via Gradient-based Weight Saliency in Both Image Classification and Generation","created":"2023-10-19","cited_by_count":386,"area":"diffusion"},{"id":"2407.12772","title":"LMMs-Eval: Reality Check on the Evaluation of Large Multimodal Models","created":"2024-07-17","cited_by_count":353,"area":"mllm"},{"id":"2309.01029","title":"Explainability for Large Language Models: A Survey","created":"2023-09-02","cited_by_count":333,"area":null},{"id":"2209.02299","title":"A Survey of Machine Unlearning","created":"2022-09-06","cited_by_count":312,"area":"safety"},{"id":"2310.10683","title":"Large Language Model Unlearning","created":"2023-10-14","cited_by_count":302,"area":"safety"},{"id":"2110.08420","title":"Understanding Dataset Difficulty with $\\mathcal{V}$-Usable Information","created":"2021-10-16","cited_by_count":291,"area":null},{"id":"2303.14186","title":"TRAK: Attributing Model Behavior at Scale","created":"2023-03-24","cited_by_count":283,"area":null},{"id":"2402.08787","title":"Rethinking Machine Unlearning for Large Language Models","created":"2024-02-13","cited_by_count":257,"area":"lr"},{"id":"2110.14430","title":"Adversarial Neuron Pruning Purifies Backdoored Deep Models","created":"2021-10-27","cited_by_count":235,"area":null},{"id":"2108.11577","title":"Machine Unlearning of Features and Labels","created":"2021-08-26","cited_by_count":229,"area":"safety"},{"id":"2111.08947","title":"Fast Yet Effective Machine Unlearning","created":"2021-11-17","cited_by_count":217,"area":"safety"},{"id":"2304.04934","title":"Model Sparsity Can Simplify Machine Unlearning","created":"2023-04-11","cited_by_count":214,"area":"safety"},{"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,"area":"diffusion"},{"id":"2110.01167","title":"Trustworthy AI: From Principles to Practices","created":"2021-10-04","cited_by_count":207,"area":null},{"id":"2101.04898","title":"Unlearnable Examples: Making Personal Data Unexploitable","created":"2021-01-13","cited_by_count":193,"area":null},{"id":"2202.00622","title":"Datamodels: Predicting Predictions from Training Data","created":"2022-02-01","cited_by_count":189,"area":null},{"id":"2407.01492","title":"RegMix: Data Mixture as Regression for Language Model Pre-training","created":"2024-07-01","cited_by_count":177,"area":null},{"id":"2110.11891","title":"On the Necessity of Auditable Algorithmic Definitions for Machine Unlearning","created":"2021-10-22","cited_by_count":171,"area":"safety"},{"id":"2110.03735","title":"Adversarial Unlearning of Backdoors via Implicit Hypergradient","created":"2021-10-07","cited_by_count":166,"area":null},{"id":"2110.14049","title":"Beta Shapley: a Unified and Noise-reduced Data Valuation Framework for Machine Learning","created":"2021-10-26","cited_by_count":165,"area":null},{"id":"2104.03413","title":"Rethinking the Backdoor Attacks' Triggers: A Frequency Perspective","created":"2021-04-07","cited_by_count":161,"area":"safety"},{"id":"2204.06031","title":"A Review on Language Models as Knowledge Bases","created":"2022-04-12","cited_by_count":157,"area":null},{"id":"2108.04840","title":"Post-hoc Interpretability for Neural NLP: A Survey","created":"2021-08-10","cited_by_count":156,"area":null},{"id":"2112.12938","title":"Counterfactual Memorization in Neural Language Models","created":"2021-12-24","cited_by_count":156,"area":null},{"id":"2106.09667","title":"Poisoning and Backdooring Contrastive Learning","created":"2021-06-17","cited_by_count":151,"area":null},{"id":"2107.10912","title":"Explainable artificial intelligence (XAI) in deep learning-based medical image analysis","created":"2021-07-22","cited_by_count":147,"area":null},{"id":"2406.04244","title":"Benchmark Data Contamination of Large Language Models: A Survey","created":"2024-06-06","cited_by_count":147,"area":null},{"id":"2209.05364","title":"If Influence Functions are the Answer, Then What is the Question?","created":"2022-09-12","cited_by_count":144,"area":null},{"id":"2408.00761","title":"Tamper-Resistant Safeguards for Open-Weight LLMs","created":"2024-08-01","cited_by_count":138,"area":"safety"},{"id":"2102.13076","title":"Benchmarking and Survey of Explanation Methods for Black Box Models","created":"2021-02-25","cited_by_count":136,"area":null},{"id":"2212.04612","title":"Training Data Influence Analysis and Estimation: A Survey","created":"2022-12-09","cited_by_count":135,"area":null},{"id":"2205.09329","title":"Dataset Pruning: Reducing Training Data by Examining Generalization Influence","created":"2022-05-19","cited_by_count":133,"area":null},{"id":"2112.03052","title":"Scaling Up Influence Functions","created":"2021-12-06","cited_by_count":132,"area":null},{"id":"2205.15466","title":"Data Banzhaf: A Robust Data Valuation Framework for Machine Learning","created":"2022-05-30","cited_by_count":132,"area":null},{"id":"2209.11326","title":"Towards Faithful Model Explanation in NLP: A Survey","created":"2022-09-22","cited_by_count":130,"area":null},{"id":"2210.06726","title":"Explanations from Large Language Models Make Small Reasoners Better","created":"2022-10-13","cited_by_count":124,"area":"lr"},{"id":"2306.01941","title":"AI Transparency in the Age of LLMs: A Human-Centered Research Roadmap","created":"2023-06-02","cited_by_count":123,"area":null},{"id":"2310.00902","title":"DataInf: Efficiently Estimating Data Influence in LoRA-tuned LLMs and Diffusion Models","created":"2023-10-02","cited_by_count":123,"area":"diffusion"},{"id":"2307.14430","title":"Skill-it! A Data-Driven Skills Framework for Understanding and Training Language Models","created":"2023-07-26","cited_by_count":121,"area":null},{"id":"2106.10807","title":"Adversarial Examples Make Strong Poisons","created":"2021-06-21","cited_by_count":119,"area":null},{"id":"2402.10376","title":"Interpreting CLIP with Sparse Linear Concept Embeddings (SpLiCE)","created":"2024-02-16","cited_by_count":119,"area":null},{"id":"2103.10689","title":"Interpretable Deep Learning: Interpretation, Interpretability, Trustworthiness, and Beyond","created":"2021-03-19","cited_by_count":118,"area":null},{"id":"2203.07320","title":"The Right to be Forgotten in Federated Learning: An Efficient Realization with Rapid Retraining","created":"2022-03-14","cited_by_count":118,"area":"safety"},{"id":"2303.15715","title":"Foundation Models and Fair Use","created":"2023-03-28","cited_by_count":116,"area":null},{"id":"2110.11794","title":"Federated Unlearning via Class-Discriminative Pruning","created":"2021-10-22","cited_by_count":115,"area":"safety"},{"id":"2110.04301","title":"Salient ImageNet: How to discover spurious features in Deep Learning?","created":"2021-10-08","cited_by_count":114,"area":null},{"id":"2108.13888","title":"Backdoor Attacks on Pre-trained Models by Layerwise Weight Poisoning","created":"2021-08-31","cited_by_count":113,"area":null},{"id":"2107.03158","title":"A Survey on Data Augmentation for Text Classification","created":"2021-07-07","cited_by_count":111,"area":null},{"id":"2210.12067","title":"Efficient Dataset Distillation Using Random Feature Approximation","created":"2022-10-21","cited_by_count":111,"area":null},{"id":"2112.03184","title":"HIVE: Evaluating the Human Interpretability of Visual Explanations","created":"2021-12-06","cited_by_count":105,"area":null},{"id":"2401.12926","title":"DsDm: Model-Aware Dataset Selection with Datamodels","created":"2024-01-23","cited_by_count":105,"area":null},{"id":"2404.18239","title":"SOUL: Unlocking the Power of Second-Order Optimization for LLM Unlearning","created":"2024-04-28","cited_by_count":104,"area":"safety"},{"id":"2406.06046","title":"MATES: Model-Aware Data Selection for Efficient Pretraining with Data Influence Models","created":"2024-06-10","cited_by_count":100,"area":null},{"id":"2305.06535","title":"KGA: A General Machine Unlearning Framework Based on Knowledge Gap Alignment","created":"2023-05-11","cited_by_count":99,"area":"safety"},{"id":"2202.05594","title":"The Shapley Value in Machine Learning","created":"2022-02-11","cited_by_count":98,"area":null},{"id":"2206.04041","title":"Neural Collapse: A Review on Modelling Principles and Generalization","created":"2022-06-08","cited_by_count":95,"area":null},{"id":"2205.01992","title":"Wild Patterns Reloaded: A Survey of Machine Learning Security against Training Data Poisoning","created":"2022-05-04","cited_by_count":94,"area":"safety"},{"id":"2405.13954","title":"What is Your Data Worth to GPT? LLM-Scale Data Valuation with Influence Functions","created":"2024-05-22","cited_by_count":94,"area":null},{"id":"2308.07061","title":"Machine Unlearning: Solutions and Challenges","created":"2023-08-14","cited_by_count":93,"area":"safety"},{"id":"2105.07190","title":"A Comprehensive Taxonomy for Explainable Artificial Intelligence: A Systematic Survey of Surveys on Methods and Concepts","created":"2021-05-15","cited_by_count":91,"area":null},{"id":"2110.02444","title":"Influence-Balanced Loss for Imbalanced Visual Classification","created":"2021-10-06","cited_by_count":91,"area":null},{"id":"2207.10062","title":"DataPerf: Benchmarks for Data-Centric AI Development","created":"2022-07-20","cited_by_count":90,"area":null},{"id":"2303.04947","title":"InfoBatch: Lossless Training Speed Up by Unbiased Dynamic Data Pruning","created":"2023-03-08","cited_by_count":90,"area":null},{"id":"2406.01257","title":"What makes unlearning hard and what to do about it","created":"2024-06-03","cited_by_count":89,"area":"safety"},{"id":"2112.11471","title":"Towards a Science of Human-AI Decision Making: A Survey of Empirical Studies","created":"2021-12-21","cited_by_count":86,"area":null},{"id":"2210.00875","title":"Untargeted Backdoor Watermark: Towards Harmless and Stealthy Dataset Copyright Protection","created":"2022-09-27","cited_by_count":86,"area":null},{"id":"2210.11584","title":"Towards Human-centered Explainable AI: A Survey of User Studies for Model Explanations","created":"2022-10-20","cited_by_count":85,"area":null},{"id":"2405.00208","title":"A Primer on the Inner Workings of Transformer-based Language Models","created":"2024-04-30","cited_by_count":85,"area":null},{"id":"2108.09331","title":"Influence Selection for Active Learning","created":"2021-08-20","cited_by_count":84,"area":null},{"id":"2105.04857","title":"Leveraging Sparse Linear Layers for Debuggable Deep Networks","created":"2021-05-11","cited_by_count":82,"area":null},{"id":"2206.14754","title":"Distilling Model Failures as Directions in Latent Space","created":"2022-06-29","cited_by_count":82,"area":null},{"id":"2209.08040","title":"Exploring the Whole Rashomon Set of Sparse Decision Trees","created":"2022-09-16","cited_by_count":81,"area":null},{"id":"2406.11011","title":"Data Shapley in One Training Run","created":"2024-06-16","cited_by_count":81,"area":null},{"id":"2210.07700","title":"Language Generation Models Can Cause Harm: So What Can We Do About It? An Actionable Survey","created":"2022-10-14","cited_by_count":80,"area":null},{"id":"2102.05262","title":"Input Similarity from the Neural Network Perspective","created":"2021-02-10","cited_by_count":79,"area":null},{"id":"2104.08678","title":"Improving Question Answering Model Robustness with Synthetic Adversarial Data Generation","created":"2021-04-18","cited_by_count":79,"area":null},{"id":"2302.13942","title":"Inseq: An Interpretability Toolkit for Sequence Generation Models","created":"2023-02-27","cited_by_count":78,"area":null},{"id":"2310.12808","title":"Model Merging by Uncertainty-Based Gradient Matching","created":"2023-10-19","cited_by_count":77,"area":null},{"id":"2103.01378","title":"Contrastive Explanations for Model Interpretability","created":"2021-03-02","cited_by_count":75,"area":null},{"id":"2108.12055","title":"Towards Self-Explainable Graph Neural Network","created":"2021-08-26","cited_by_count":75,"area":null},{"id":"2305.11733","title":"Long-tailed Visual Recognition via Gaussian Clouded Logit Adjustment","created":"2023-05-19","cited_by_count":75,"area":null},{"id":"2301.07255","title":"Understanding the Role of Human Intuition on Reliance in Human-AI Decision-Making with Explanations","created":"2023-01-18","cited_by_count":73,"area":null},{"id":"2310.12560","title":"Fast Model Debias with Machine Unlearning","created":"2023-10-19","cited_by_count":72,"area":"safety"},{"id":"2308.04430","title":"SILO Language Models: Isolating Legal Risk In a Nonparametric Datastore","created":"2023-08-08","cited_by_count":71,"area":null},{"id":"2305.00054","title":"LAVA: Data Valuation without Pre-Specified Learning Algorithms","created":"2023-04-28","cited_by_count":69,"area":null},{"id":"2210.12329","title":"ProGen: Progressive Zero-shot Dataset Generation via In-context Feedback","created":"2022-10-22","cited_by_count":67,"area":null},{"id":"2310.14664","title":"Data Pruning via Moving-one-Sample-out","created":"2023-10-23","cited_by_count":67,"area":null},{"id":"2402.17641","title":"Variational Learning is Effective for Large Deep Networks","created":"2024-02-27","cited_by_count":65,"area":null},{"id":"2210.03735","title":"\"Help Me Help the AI\": Understanding How Explainability Can Support Human-AI Interaction","created":"2022-10-02","cited_by_count":63,"area":null},{"id":"2306.05175","title":"Large-scale Dataset Pruning with Dynamic Uncertainty","created":"2023-06-08","cited_by_count":63,"area":null},{"id":"2302.11042","title":"In-context Example Selection with Influences","created":"2023-02-21","cited_by_count":61,"area":null},{"id":"2502.19301","title":"Rethinking LLM Unlearning Objectives: A Gradient Perspective and Go Beyond","created":"2025-02-26","cited_by_count":61,"area":"lr"},{"id":"2106.03216","title":"On Memorization in Probabilistic Deep Generative Models","created":"2021-06-06","cited_by_count":60,"area":null},{"id":"2304.02835","title":"GIF: A General Graph Unlearning Strategy via Influence Function","created":"2023-04-06","cited_by_count":60,"area":"safety"}],"next_cursor":"100"}