{"list":"other","total":83,"rows":[{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"1908.10084","title":"Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks","created":"2019-08-27","cited_by_count":9170},{"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":"1909.08593","title":"Fine-Tuning Language Models from Human Preferences","created":"2019-09-18","cited_by_count":2150},{"id":"1907.02893","title":"Invariant Risk Minimization","created":"2019-07-05","cited_by_count":1854},{"id":"1912.01603","title":"Dream to Control: Learning Behaviors by Latent Imagination","created":"2019-12-03","cited_by_count":1653},{"id":"2404.16130","title":"From Local to Global: A Graph RAG Approach to Query-Focused Summarization","created":"2024-04-24","cited_by_count":1453},{"id":"1907.07174","title":"Natural Adversarial Examples","created":"2019-07-16","cited_by_count":1408},{"id":"1606.04671","title":"Progressive Neural Networks","created":"2016-06-15","cited_by_count":1361},{"id":"2009.11462","title":"RealToxicityPrompts: Evaluating Neural Toxic Degeneration in Language Models","created":"2020-09-24","cited_by_count":1255},{"id":"2210.07229","title":"Mass-Editing Memory in a Transformer","created":"2022-10-13","cited_by_count":1001},{"id":"1810.12894","title":"Exploration by Random Network Distillation","created":"2018-10-30","cited_by_count":993},{"id":"2504.13837","title":"Does Reinforcement Learning Really Incentivize Reasoning Capacity in LLMs Beyond the Base Model?","created":"2025-04-18","cited_by_count":982},{"id":"2306.01708","title":"TIES-Merging: Resolving Interference When Merging Models","created":"2023-06-02","cited_by_count":818},{"id":"1511.06335","title":"Unsupervised Deep Embedding for Clustering Analysis","created":"2015-11-19","cited_by_count":767},{"id":"2003.00688","title":"Out-of-Distribution Generalization via Risk Extrapolation (REx)","created":"2020-03-02","cited_by_count":742},{"id":"1707.07328","title":"Adversarial Examples for Evaluating Reading Comprehension Systems","created":"2017-07-23","cited_by_count":571},{"id":"2210.13382","title":"Emergent World Representations: Exploring a Sequence Model Trained on a Synthetic Task","created":"2022-10-24","cited_by_count":431},{"id":"2206.11795","title":"Video PreTraining (VPT): Learning to Act by Watching Unlabeled Online Videos","created":"2022-06-23","cited_by_count":345},{"id":"2201.03544","title":"The Effects of Reward Misspecification: Mapping and Mitigating Misaligned Models","created":"2022-01-10","cited_by_count":328},{"id":"1606.03137","title":"Cooperative Inverse Reinforcement Learning","created":"2016-06-09","cited_by_count":300},{"id":"2011.00620","title":"Social Chemistry 101: Learning to Reason about Social and Moral Norms","created":"2020-11-01","cited_by_count":255},{"id":"1511.05641","title":"Net2Net: Accelerating Learning via Knowledge Transfer","created":"2015-11-18","cited_by_count":250},{"id":"2410.02355","title":"AlphaEdit: Null-Space Constrained Knowledge Editing for Language Models","created":"2024-10-03","cited_by_count":236},{"id":"2303.04381","title":"Automatically Auditing Large Language Models via Discrete Optimization","created":"2023-03-08","cited_by_count":191},{"id":"1610.03425","title":"Statistics of Robust Optimization: A Generalized Empirical Likelihood Approach","created":"2016-10-11","cited_by_count":183},{"id":"2209.07526","title":"OmniVL:One Foundation Model for Image-Language and Video-Language Tasks","created":"2022-09-15","cited_by_count":143},{"id":"2511.18397","title":"Natural Emergent Misalignment from Reward Hacking in Production RL","created":"2025-11-23","cited_by_count":136},{"id":"1805.07894","title":"Constructing Unrestricted Adversarial Examples with Generative Models","created":"2018-05-21","cited_by_count":135},{"id":"1609.02200","title":"Discrete Variational Autoencoders","created":"2016-09-07","cited_by_count":125},{"id":"2406.15479","title":"Twin-Merging: Dynamic Integration of Modular Expertise in Model Merging","created":"2024-06-17","cited_by_count":116},{"id":"1908.04734","title":"Reward Tampering Problems and Solutions in Reinforcement Learning: A Causal Influence Diagram Perspective","created":"2019-08-13","cited_by_count":108},{"id":"2007.15646","title":"Rewriting a Deep Generative Model","created":"2020-07-30","cited_by_count":107},{"id":"1803.01128","title":"Seq2Sick: Evaluating the Robustness of Sequence-to-Sequence Models with Adversarial Examples","created":"2018-03-03","cited_by_count":94},{"id":"1911.10891","title":"ColorFool: Semantic Adversarial Colorization","created":"2019-11-25","cited_by_count":89},{"id":"2406.01257","title":"What makes unlearning hard and what to do about it","created":"2024-06-03","cited_by_count":89},{"id":"2308.04265","title":"FLIRT: Feedback Loop In-context Red Teaming","created":"2023-08-08","cited_by_count":83},{"id":"2402.09345","title":"InfoRM: Mitigating Reward Hacking in RLHF via Information-Theoretic Reward Modeling","created":"2024-02-14","cited_by_count":79},{"id":"2401.12244","title":"Large-scale Reinforcement Learning for Diffusion Models","created":"2024-01-20","cited_by_count":78},{"id":"1902.07742","title":"From Language to Goals: Inverse Reinforcement Learning for Vision-Based Instruction Following","created":"2019-02-20","cited_by_count":67},{"id":"2301.11578","title":"Learning to Unlearn: Instance-wise Unlearning for Pre-trained Classifiers","created":"2023-01-27","cited_by_count":67},{"id":"2407.21792","title":"Safetywashing: Do AI Safety Benchmarks Actually Measure Safety Progress?","created":"2024-07-31","cited_by_count":61},{"id":"1609.09408","title":"Cooperative Training of Descriptor and Generator Networks","created":"2016-09-29","cited_by_count":60},{"id":"2205.01663","title":"Adversarial Training for High-Stakes Reliability","created":"2022-05-03","cited_by_count":60},{"id":"2305.17008","title":"NormBank: A Knowledge Bank of Situational Social Norms","created":"2023-05-26","cited_by_count":60},{"id":"2403.14236","title":"A Unified Framework for Model Editing","created":"2024-03-21","cited_by_count":57},{"id":"1712.03847","title":"On Quadratic Penalties in Elastic Weight Consolidation","created":"2017-12-11","cited_by_count":55},{"id":"2402.09656","title":"The Butterfly Effect of Model Editing: Few Edits Can Trigger Large Language Models Collapse","created":"2024-02-15","cited_by_count":54},{"id":"1911.08114","title":"Neural Network Pruning with Residual-Connections and Limited-Data","created":"2019-11-19","cited_by_count":52},{"id":"2403.07175","title":"Rebuilding ROME : Resolving Model Collapse during Sequential Model Editing","created":"2024-03-11","cited_by_count":50},{"id":"2210.08604","title":"NormSAGE: Multi-Lingual Multi-Cultural Norm Discovery from Conversations On-the-Fly","created":"2022-10-16","cited_by_count":48},{"id":"1406.3332","title":"Convolutional Kernel Networks","created":"2014-06-12","cited_by_count":47},{"id":"2302.05209","title":"A Survey on Causal Reinforcement Learning","created":"2023-02-10","cited_by_count":45},{"id":"2009.14715","title":"Learning Rewards from Linguistic Feedback","created":"2020-09-30","cited_by_count":41},{"id":"2004.09395","title":"Energy-Based Imitation Learning","created":"2020-04-20","cited_by_count":40},{"id":"2405.03279","title":"Lifelong Knowledge Editing for LLMs with Retrieval-Augmented Continuous Prompt Learning","created":"2024-05-06","cited_by_count":40},{"id":"2301.12832","title":"Deep networks for system identification: a Survey","created":"2023-01-30","cited_by_count":37},{"id":"2410.20971","title":"BlueSuffix: Reinforced Blue Teaming for Vision-Language Models Against Jailbreak Attacks","created":"2024-10-28","cited_by_count":28},{"id":"2308.01589","title":"Holy Grail 2.0: From Natural Language to Constraint Models","created":"2023-08-03","cited_by_count":26},{"id":"2409.16783","title":"Holistic Automated Red Teaming for Large Language Models through Top-Down Test Case Generation and Multi-turn Interaction","created":"2024-09-25","cited_by_count":25},{"id":"2408.00657","title":"Disentangling Dense Embeddings with Sparse Autoencoders","created":"2024-08-01","cited_by_count":23},{"id":"2206.08575","title":"Query-Efficient and Scalable Black-Box Adversarial Attacks on Discrete Sequential Data via Bayesian Optimization","created":"2022-06-17","cited_by_count":22},{"id":"2109.02765","title":"Robustness and Generalization via Generative Adversarial Training","created":"2021-09-06","cited_by_count":20},{"id":"2409.09778","title":"Rewind-to-Delete: Certified Machine Unlearning for Nonconvex Functions","created":"2024-09-15","cited_by_count":19},{"id":"2503.06339","title":"Learning to Unlearn while Retaining: Combating Gradient Conflicts in Machine Unlearning","created":"2025-03-08","cited_by_count":19},{"id":"1712.04172","title":"A Low-Cost Ethics Shaping Approach for Designing Reinforcement Learning Agents","created":"2017-12-12","cited_by_count":18},{"id":"2503.05212","title":"Knowledge Updating? No More Model Editing! Just Selective Contextual Reasoning","created":"2025-03-07","cited_by_count":16},{"id":"2003.10388","title":"Generating Natural Language Adversarial Examples on a Large Scale with Generative Models","created":"2020-03-10","cited_by_count":15},{"id":"2406.11757","title":"STAR: SocioTechnical Approach to Red Teaming Language Models","created":"2024-06-17","cited_by_count":13},{"id":"2410.20957","title":"Neuro-symbolic Learning Yielding Logical Constraints","created":"2024-10-28","cited_by_count":12},{"id":"2103.17232","title":"Neuro-Symbolic Constraint Programming for Structured Prediction","created":"2021-03-31","cited_by_count":11},{"id":"2409.07569","title":"A Comprehensive Survey on Inverse Constrained Reinforcement Learning: Definitions, Progress and Challenges","created":"2024-09-11","cited_by_count":10},{"id":"2506.07899","title":"MEMOIR: Lifelong Model Editing with Minimal Overwrite and Informed Retention for LLMs","created":"2025-06-09","cited_by_count":10},{"id":"2205.12532","title":"Skill Machines: Temporal Logic Skill Composition in Reinforcement Learning","created":"2022-05-25","cited_by_count":9},{"id":"2502.04354","title":"Reviving The Classics: Active Reward Modeling in Large Language Model Alignment","created":"2025-02-04","cited_by_count":8},{"id":"2512.16814","title":"Grammar-Forced Translation of Natural Language to Temporal Logic using LLMs","created":"2025-12-18","cited_by_count":8},{"id":"2510.13851","title":"EvoEdit: Evolving Null-space Alignment for Robust and Efficient Knowledge Editing","created":"2025-10-11","cited_by_count":7},{"id":"2402.00723","title":"Improving Semantic Control in Discrete Latent Spaces with Transformer Quantized Variational Autoencoders","created":"2024-02-01","cited_by_count":6},{"id":"2410.07525","title":"Offline Inverse Constrained Reinforcement Learning for Safe-Critical Decision Making in Healthcare","created":"2024-10-10","cited_by_count":4},{"id":"2412.10096","title":"Reward Machine Inference for Robotic Manipulation","created":"2024-12-13","cited_by_count":4},{"id":"2409.07091","title":"Learning Task Specifications from Demonstrations as Probabilistic Automata","created":"2024-09-11","cited_by_count":2},{"id":"2410.03049","title":"Scalable Frame-based Construction of Sociocultural NormBases for Socially-Aware Dialogues","created":"2024-10-04","cited_by_count":1}],"next_cursor":null}