{"list":"other","total":110,"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":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"id":"2210.03629","title":"ReAct: Synergizing Reasoning and Acting in Language Models","created":"2022-10-06","cited_by_count":8695},{"id":"2305.18290","title":"Direct Preference Optimization: Your Language Model is Secretly a Reward Model","created":"2023-05-29","cited_by_count":8065},{"id":"1412.6572","title":"Explaining and Harnessing Adversarial Examples","created":"2014-12-20","cited_by_count":7364},{"id":"2001.08361","title":"Scaling Laws for Neural Language Models","created":"2020-01-23","cited_by_count":6586},{"id":"1706.06083","title":"Towards Deep Learning Models Resistant to Adversarial Attacks","created":"2017-06-19","cited_by_count":6415},{"id":"1312.6199","title":"Intriguing properties of neural networks","created":"2013-12-21","cited_by_count":5155},{"id":"2205.11916","title":"Large Language Models are Zero-Shot Reasoners","created":"2022-05-24","cited_by_count":4374},{"id":"2108.07258","title":"On the Opportunities and Risks of Foundation Models","created":"2021-08-16","cited_by_count":4033},{"id":"1706.03741","title":"Deep reinforcement learning from human preferences","created":"2017-06-12","cited_by_count":3912},{"id":"1312.5602","title":"Playing Atari with Deep Reinforcement Learning","created":"2013-12-19","cited_by_count":3274},{"id":"2307.15043","title":"Universal and Transferable Adversarial Attacks on Aligned Language Models","created":"2023-07-27","cited_by_count":3104},{"id":"2212.08073","title":"Constitutional AI: Harmlessness from AI Feedback","created":"2022-12-15","cited_by_count":3050},{"id":"2203.15556","title":"Training Compute-Optimal Large Language Models","created":"2022-03-29","cited_by_count":3019},{"id":"1608.04644","title":"Towards Evaluating the Robustness of Neural Networks","created":"2016-08-16","cited_by_count":2998},{"id":"2202.05262","title":"Locating and Editing Factual Associations in GPT","created":"2022-02-10","cited_by_count":2691},{"id":"2408.00118","title":"Gemma 2: Improving Open Language Models at a Practical Size","created":"2024-07-31","cited_by_count":1998},{"id":"2309.08600","title":"Sparse Autoencoders Find Highly Interpretable Features in Language Models","created":"2023-09-15","cited_by_count":1420},{"id":"2501.19393","title":"s1: Simple test-time scaling","created":"2025-01-31","cited_by_count":1341},{"id":"2310.01405","title":"Representation Engineering: A Top-Down Approach to AI Transparency","created":"2023-10-02","cited_by_count":1336},{"id":"2306.03341","title":"Inference-Time Intervention: Eliciting Truthful Answers from a Language Model","created":"2023-06-06","cited_by_count":1302},{"id":"1802.00420","title":"Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examples","created":"2018-02-01","cited_by_count":1268},{"id":"2312.06674","title":"Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversations","created":"2023-12-07","cited_by_count":1207},{"id":"2406.17557","title":"The FineWeb Datasets: Decanting the Web for the Finest Text Data at Scale","created":"2024-06-25","cited_by_count":1160},{"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":"1912.06680","title":"Dota 2 with Large Scale Deep Reinforcement Learning","created":"2019-12-13","cited_by_count":1103},{"id":"1912.03817","title":"Machine Unlearning","created":"2019-12-09","cited_by_count":1061},{"id":"2112.00861","title":"A General Language Assistant as a Laboratory for Alignment","created":"2021-12-01","cited_by_count":1055},{"id":"2406.11717","title":"Refusal in Language Models Is Mediated by a Single Direction","created":"2024-06-17","cited_by_count":1032},{"id":"1604.07316","title":"End to End Learning for Self-Driving Cars","created":"2016-04-25","cited_by_count":1009},{"id":"2210.07229","title":"Mass-Editing Memory in a Transformer","created":"2022-10-13","cited_by_count":1001},{"id":"2308.10248","title":"Steering Language Models With Activation Engineering","created":"2023-08-20","cited_by_count":922},{"id":"2506.13131","title":"AlphaEvolve: A coding agent for scientific and algorithmic discovery","created":"2025-06-16","cited_by_count":867},{"id":"2202.11214","title":"FourCastNet: A Global Data-driven High-resolution Weather Model using Adaptive Fourier Neural Operators","created":"2022-02-22","cited_by_count":776},{"id":"2301.13688","title":"The Flan Collection: Designing Data and Methods for Effective Instruction Tuning","created":"2023-01-31","cited_by_count":739},{"id":"2306.05499","title":"Prompt Injection attack against LLM-integrated Applications","created":"2023-06-08","cited_by_count":605},{"id":"2406.04093","title":"Scaling and evaluating sparse autoencoders","created":"2024-06-06","cited_by_count":553},{"id":"2403.03218","title":"The WMDP Benchmark: Measuring and Reducing Malicious Use With Unlearning","created":"2024-03-05","cited_by_count":509},{"id":"2404.05868","title":"Negative Preference Optimization: From Catastrophic Collapse to Effective Unlearning","created":"2024-04-08","cited_by_count":504},{"id":"2406.18495","title":"WildGuard: Open One-Stop Moderation Tools for Safety Risks, Jailbreaks, and Refusals of LLMs","created":"2024-06-26","cited_by_count":496},{"id":"2404.13208","title":"The Instruction Hierarchy: Training LLMs to Prioritize Privileged Instructions","created":"2024-04-19","cited_by_count":493},{"id":"2305.07759","title":"TinyStories: How Small Can Language Models Be and Still Speak Coherent English?","created":"2023-05-12","cited_by_count":449},{"id":"2505.05410","title":"Reasoning Models Don't Always Say What They Think","created":"2025-05-08","cited_by_count":415},{"id":"2310.06452","title":"Understanding the Effects of RLHF on LLM Generalisation and Diversity","created":"2023-10-10","cited_by_count":396},{"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},{"id":"2412.14093","title":"Alignment faking in large language models","created":"2024-12-18","cited_by_count":360},{"id":"2502.02737","title":"SmolLM2: When Smol Goes Big -- Data-Centric Training of a Small Language Model","created":"2025-02-04","cited_by_count":335},{"id":"2308.03296","title":"Studying Large Language Model Generalization with Influence Functions","created":"2023-08-07","cited_by_count":326},{"id":"2406.04313","title":"Improving Alignment and Robustness with Circuit Breakers","created":"2024-06-06","cited_by_count":322},{"id":"1811.06521","title":"Reward learning from human preferences and demonstrations in Atari","created":"2018-11-15","cited_by_count":316},{"id":"2310.10683","title":"Large Language Model Unlearning","created":"2023-10-14","cited_by_count":302},{"id":"2302.09880","title":"Towards Unbounded Machine Unlearning","created":"2023-02-20","cited_by_count":268},{"id":"2110.11571","title":"Anti-Backdoor Learning: Training Clean Models on Poisoned Data","created":"2021-10-22","cited_by_count":263},{"id":"2209.00626","title":"The Alignment Problem from a Deep Learning Perspective","created":"2022-08-30","cited_by_count":258},{"id":"2507.11473","title":"Chain of Thought Monitorability: A New and Fragile Opportunity for AI Safety","created":"2025-07-15","cited_by_count":249},{"id":"2302.08582","title":"Pretraining Language Models with Human Preferences","created":"2023-02-16","cited_by_count":247},{"id":"2405.20947","title":"OR-Bench: An Over-Refusal Benchmark for Large Language Models","created":"2024-05-31","cited_by_count":244},{"id":"2310.07579","title":"In-Context Unlearning: Language Models as Few Shot Unlearners","created":"2023-10-11","cited_by_count":224},{"id":"2501.17148","title":"AxBench: Steering LLMs? Even Simple Baselines Outperform Sparse Autoencoders","created":"2025-01-28","cited_by_count":218},{"id":"2205.08096","title":"Can Bad Teaching Induce Forgetting? Unlearning in Deep Networks using an Incompetent Teacher","created":"2022-05-17","cited_by_count":194},{"id":"2310.16218","title":"Knowledge Editing for Large Language Models: A Survey","created":"2023-10-24","cited_by_count":194},{"id":"2309.06256","title":"Mitigating the Alignment Tax of RLHF","created":"2023-09-12","cited_by_count":183},{"id":"2308.07707","title":"Fast Machine Unlearning Without Retraining Through Selective Synaptic Dampening","created":"2023-08-15","cited_by_count":181},{"id":"2501.18837","title":"Constitutional Classifiers: Defending against Universal Jailbreaks across Thousands of Hours of Red Teaming","created":"2025-01-31","cited_by_count":181},{"id":"2401.01286","title":"A Comprehensive Study of Knowledge Editing for Large Language Models","created":"2024-01-02","cited_by_count":163},{"id":"1811.11553","title":"Strike (with) a Pose: Neural Networks Are Easily Fooled by Strange Poses of Familiar Objects","created":"2018-11-28","cited_by_count":143},{"id":"2408.00761","title":"Tamper-Resistant Safeguards for Open-Weight LLMs","created":"2024-08-01","cited_by_count":138},{"id":"2505.23643","title":"Securing AI Agents with Information-Flow Control","created":"2025-05-29","cited_by_count":121},{"id":"2309.01809","title":"Are Emergent Abilities in Large Language Models just In-Context Learning?","created":"2023-09-04","cited_by_count":109},{"id":"2503.05379","title":"R1-Omni: Explainable Omni-Multimodal Emotion Recognition with Reinforcement Learning","created":"2025-03-07","cited_by_count":100},{"id":"2403.03329","title":"Guardrail Baselines for Unlearning in LLMs","created":"2024-03-05","cited_by_count":96},{"id":"2409.19091","title":"System-Level Defense against Indirect Prompt Injection Attacks: An Information Flow Control Perspective","created":"2024-09-27","cited_by_count":96},{"id":"2507.05246","title":"When Chain of Thought is Necessary, Language Models Struggle to Evade Monitors","created":"2025-07-07","cited_by_count":88},{"id":"2403.01218","title":"Inexact Unlearning Needs More Careful Evaluations to Avoid a False Sense of Privacy","created":"2024-03-02","cited_by_count":82},{"id":"2407.11969","title":"Does Refusal Training in LLMs Generalize to the Past Tense?","created":"2024-07-16","cited_by_count":79},{"id":"2410.08827","title":"Do Unlearning Methods Remove Information from Language Model Weights?","created":"2024-10-11","cited_by_count":73},{"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":"2112.01008","title":"Editing a classifier by rewriting its prediction rules","created":"2021-12-02","cited_by_count":65},{"id":"2407.00106","title":"UnUnlearning: Unlearning is not sufficient for content regulation in advanced generative AI","created":"2024-06-27","cited_by_count":51},{"id":"2501.04952","title":"Open Problems in Machine Unlearning for AI Safety","created":"2025-01-09","cited_by_count":51},{"id":"2406.09073","title":"Are we making progress in unlearning? Findings from the first NeurIPS unlearning competition","created":"2024-06-13","cited_by_count":50},{"id":"2406.12038","title":"Soft Prompting for Unlearning in Large Language Models","created":"2024-06-17","cited_by_count":46},{"id":"2504.16980","title":"Safety Pretraining: Toward the Next Generation of Safe AI","created":"2025-04-23","cited_by_count":43},{"id":"2508.06601","title":"Deep Ignorance: Filtering Pretraining Data Builds Tamper-Resistant Safeguards into Open-Weight LLMs","created":"2025-08-08","cited_by_count":42},{"id":"2601.04603","title":"Constitutional Classifiers++: Efficient Production-Grade Defenses against Universal Jailbreaks","created":"2026-01-08","cited_by_count":41},{"id":"2502.05209","title":"Model Tampering Attacks Enable More Rigorous Evaluations of LLM Capabilities","created":"2025-02-03","cited_by_count":39},{"id":"2410.04332","title":"Gradient Routing: Masking Gradients to Localize Computation in Neural Networks","created":"2024-10-06","cited_by_count":34},{"id":"2502.12197","title":"A Closer Look at System Prompt Robustness","created":"2025-02-15","cited_by_count":32},{"id":"2502.18695","title":"Policy-as-Prompt: Rethinking Content Moderation in the Age of Large Language Models","created":"2025-02-25","cited_by_count":31},{"id":"2506.04245","title":"Contextual Integrity in LLMs via Reasoning and Reinforcement Learning","created":"2025-05-29","cited_by_count":31},{"id":"2402.14015","title":"Corrective Machine Unlearning","created":"2024-02-21","cited_by_count":29},{"id":"2408.10682","title":"Towards Robust Knowledge Unlearning: An Adversarial Framework for Assessing and Improving Unlearning Robustness in Large Language Models","created":"2024-08-20","cited_by_count":27},{"id":"2209.10015","title":"Metadata Archaeology: Unearthing Data Subsets by Leveraging Training Dynamics","created":"2022-09-20","cited_by_count":26},{"id":"2404.11534","title":"Decomposing and Editing Predictions by Modeling Model Computation","created":"2024-04-17","cited_by_count":19},{"id":"2404.16841","title":"Machine Unlearning in Large Language Models","created":"2024-02-03","cited_by_count":17},{"id":"2311.15792","title":"Rethinking Privacy in Machine Learning Pipelines from an Information Flow Control Perspective","created":"2023-11-27","cited_by_count":16},{"id":"2406.01436","title":"Editing the Mind of Giants: An In-Depth Exploration of Pitfalls of Knowledge Editing in Large Language Models","created":"2024-06-03","cited_by_count":12}],"next_cursor":"100"}