{"list":"other","total":59,"rows":[{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"id":"2305.18290","title":"Direct Preference Optimization: Your Language Model is Secretly a Reward Model","created":"2023-05-29","cited_by_count":8065},{"id":"2501.12948","title":"DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning","created":"2025-01-22","cited_by_count":6330},{"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":"2212.08073","title":"Constitutional AI: Harmlessness from AI Feedback","created":"2022-12-15","cited_by_count":3050},{"id":"1607.00133","title":"Deep Learning with Differential Privacy","created":"2016-07-01","cited_by_count":2728},{"id":"2004.07780","title":"Shortcut Learning in Deep Neural Networks","created":"2020-04-16","cited_by_count":1969},{"id":"1907.02893","title":"Invariant Risk Minimization","created":"2019-07-05","cited_by_count":1854},{"id":"2305.11206","title":"LIMA: Less Is More for Alignment","created":"2023-05-18","cited_by_count":1100},{"id":"2112.00861","title":"A General Language Assistant as a Laboratory for Alignment","created":"2021-12-01","cited_by_count":1055},{"id":"2007.01434","title":"In Search of Lost Domain Generalization","created":"2020-07-02","cited_by_count":1054},{"id":"2107.09044","title":"Just Train Twice: Improving Group Robustness without Training Group Information","created":"2021-07-19","cited_by_count":523},{"id":"2310.06987","title":"Catastrophic Jailbreak of Open-source LLMs via Exploiting Generation","created":"2023-10-10","cited_by_count":451},{"id":"2204.02937","title":"Last Layer Re-Training is Sufficient for Robustness to Spurious Correlations","created":"2022-04-06","cited_by_count":381},{"id":"2311.03191","title":"DeepInception: Hypnotize Large Language Model to Be Jailbreaker","created":"2023-11-06","cited_by_count":367},{"id":"2006.07710","title":"The Pitfalls of Simplicity Bias in Neural Networks","created":"2020-06-13","cited_by_count":351},{"id":"2302.08582","title":"Pretraining Language Models with Human Preferences","created":"2023-02-16","cited_by_count":247},{"id":"2310.16028","title":"What Algorithms can Transformers Learn? A Study in Length Generalization","created":"2023-10-24","cited_by_count":199},{"id":"1909.10594","title":"MemGuard: Defending against Black-Box Membership Inference Attacks via Adversarial Examples","created":"2019-09-23","cited_by_count":197},{"id":"2310.05916","title":"Interpreting CLIP's Image Representation via Text-Based Decomposition","created":"2023-10-09","cited_by_count":196},{"id":"1807.05852","title":"Machine Learning with Membership Privacy using Adversarial Regularization","created":"2018-07-16","cited_by_count":186},{"id":"2203.01517","title":"Correct-N-Contrast: A Contrastive Approach for Improving Robustness to Spurious Correlations","created":"2022-03-03","cited_by_count":172},{"id":"2206.10469","title":"The Privacy Onion Effect: Memorization is Relative","created":"2022-06-21","cited_by_count":136},{"id":"2307.03381","title":"Teaching Arithmetic to Small Transformers","created":"2023-07-07","cited_by_count":123},{"id":"2206.00240","title":"Privacy for Free: How does Dataset Condensation Help Privacy?","created":"2022-06-01","cited_by_count":120},{"id":"2011.07018","title":"Synthetic Data -- Anonymisation Groundhog Day","created":"2020-11-13","cited_by_count":108},{"id":"2308.01320","title":"DeepSpeed-Chat: Easy, Fast and Affordable RLHF Training of ChatGPT-like Models at All Scales","created":"2023-08-02","cited_by_count":108},{"id":"2410.21272","title":"Arithmetic Without Algorithms: Language Models Solve Math With a Bag of Heuristics","created":"2024-10-28","cited_by_count":97},{"id":"2205.11502","title":"On the Paradox of Learning to Reason from Data","created":"2022-05-23","cited_by_count":93},{"id":"2305.16960","title":"Training Socially Aligned Language Models on Simulated Social Interactions","created":"2023-05-26","cited_by_count":78},{"id":"2407.09121","title":"Refuse Whenever You Feel Unsafe: Improving Safety in LLMs via Decoupled Refusal Training","created":"2024-07-12","cited_by_count":69},{"id":"2110.08324","title":"Mitigating Membership Inference Attacks by Self-Distillation Through a Novel Ensemble Architecture","created":"2021-10-15","cited_by_count":67},{"id":"2202.03335","title":"Membership Inference Attacks and Defenses in Neural Network Pruning","created":"2022-02-07","cited_by_count":45},{"id":"2305.18761","title":"Identifying Spurious Biases Early in Training through the Lens of Simplicity Bias","created":"2023-05-30","cited_by_count":44},{"id":"2306.04949","title":"Robust Learning with Progressive Data Expansion Against Spurious Correlation","created":"2023-06-08","cited_by_count":39},{"id":"2207.05801","title":"RelaxLoss: Defending Membership Inference Attacks without Losing Utility","created":"2022-07-12","cited_by_count":37},{"id":"2210.08196","title":"Deep Regression Unlearning","created":"2022-10-15","cited_by_count":32},{"id":"2307.01610","title":"Overconfidence is a Dangerous Thing: Mitigating Membership Inference Attacks by Enforcing Less Confident Prediction","created":"2023-07-04","cited_by_count":29},{"id":"2202.05189","title":"Understanding Rare Spurious Correlations in Neural Networks","created":"2022-02-10","cited_by_count":27},{"id":"2309.16748","title":"Discovering environments with XRM","created":"2023-09-28","cited_by_count":26},{"id":"2006.05336","title":"On the Effectiveness of Regularization Against Membership Inference Attacks","created":"2020-06-09","cited_by_count":24},{"id":"2309.17310","title":"Leave-one-out Distinguishability in Machine Learning","created":"2023-09-29","cited_by_count":20},{"id":"2205.14055","title":"A Blessing of Dimensionality in Membership Inference through Regularization","created":"2022-05-27","cited_by_count":18},{"id":"2405.19524","title":"AI Risk Management Should Incorporate Both Safety and Security","created":"2024-05-29","cited_by_count":17},{"id":"2212.00612","title":"Purifier: Defending Data Inference Attacks via Transforming Confidence Scores","created":"2022-12-01","cited_by_count":15},{"id":"2202.01243","title":"Parameters or Privacy: A Provable Tradeoff Between Overparameterization and Membership Inference","created":"2022-02-02","cited_by_count":14},{"id":"2212.02648","title":"Spuriosity Rankings: Sorting Data to Measure and Mitigate Biases","created":"2022-12-05","cited_by_count":13},{"id":"2311.00919","title":"MIST: Defending Against Membership Inference Attacks Through Membership-Invariant Subspace Training","created":"2023-11-02","cited_by_count":12},{"id":"2409.19069","title":"Localizing Memorization in SSL Vision Encoders","created":"2024-09-27","cited_by_count":9},{"id":"2402.05453","title":"Mitigating Privacy Risk in Membership Inference by Convex-Concave Loss","created":"2024-02-08","cited_by_count":6},{"id":"2411.15796","title":"Data Lineage Inference: Uncovering Privacy Vulnerabilities of Dataset Pruning","created":"2024-11-24","cited_by_count":5},{"id":"2404.17674","title":"Center-Based Relaxed Learning Against Membership Inference Attacks","created":"2024-04-26","cited_by_count":4},{"id":"2410.06814","title":"Defending Membership Inference Attacks via Privacy-aware Sparsity Tuning","created":"2024-10-09","cited_by_count":4},{"id":"2407.16164","title":"Representation Magnitude has a Liability to Privacy Vulnerability","created":"2024-07-23","cited_by_count":3}],"next_cursor":null}