{"total":326,"rows":[{"id":"2309.12288","title":"The Reversal Curse: LLMs trained on \"A is B\" fail to learn \"B is A\"","created":"2023-09-21","cited_by_count":407,"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":"2309.01029","title":"Explainability for Large Language Models: A Survey","created":"2023-09-02","cited_by_count":333,"area":null},{"id":"2403.08319","title":"Knowledge Conflicts for LLMs: A Survey","created":"2024-03-13","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":"2411.18279","title":"Large Language Model-Brained GUI Agents: A Survey","created":"2024-11-27","cited_by_count":162,"area":"agents"},{"id":"2309.00667","title":"Taken out of context: On measuring situational awareness in LLMs","created":"2023-09-01","cited_by_count":143,"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":"2402.01761","title":"Rethinking Interpretability in the Era of Large Language Models","created":"2024-01-30","cited_by_count":111,"area":"lr"},{"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":"2404.11457","title":"Bias and Unfairness in Information Retrieval Systems: New Challenges in the LLM Era","created":"2024-04-17","cited_by_count":98,"area":null},{"id":"2409.00729","title":"ContextCite: Attributing Model Generation to Context","created":"2024-09-01","cited_by_count":98,"area":null},{"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":"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":"2406.11011","title":"Data Shapley in One Training Run","created":"2024-06-16","cited_by_count":81,"area":null},{"id":"2403.03187","title":"Reliable, Adaptable, and Attributable Language Models with Retrieval","created":"2024-03-05","cited_by_count":73,"area":"rag"},{"id":"2403.10949","title":"SelfIE: Self-Interpretation of Large Language Model Embeddings","created":"2024-03-16","cited_by_count":67,"area":null},{"id":"2402.11260","title":"MoRAL: MoE Augmented LoRA for LLMs' Lifelong Learning","created":"2024-02-17","cited_by_count":63,"area":"moe"},{"id":"2311.00636","title":"Kronecker-Factored Approximate Curvature for Modern Neural Network Architectures","created":"2023-11-01","cited_by_count":49,"area":null},{"id":"2311.00500","title":"Intriguing Properties of Data Attribution on Diffusion Models","created":"2023-11-01","cited_by_count":47,"area":"diffusion"},{"id":"2403.08946","title":"Usable XAI: 10 Strategies Towards Exploiting Explainability in the LLM Era","created":"2024-03-13","cited_by_count":46,"area":null},{"id":"2505.24119","title":"The State of Multilingual LLM Safety Research: From Measuring the Language Gap to Mitigating It","created":"2025-05-30","cited_by_count":45,"area":"safety"},{"id":"2402.14433","title":"A Language Model's Guide Through Latent Space","created":"2024-02-22","cited_by_count":43,"area":null},{"id":"2402.07321","title":"Summing Up the Facts: Additive Mechanisms Behind Factual Recall in LLMs","created":"2024-02-11","cited_by_count":42,"area":null},{"id":"2410.17413","title":"Scalable Influence and Fact Tracing for Large Language Model Pretraining","created":"2024-10-22","cited_by_count":42,"area":null},{"id":"2411.12580","title":"Procedural Knowledge in Pretraining Drives Reasoning in Large Language Models","created":"2024-11-19","cited_by_count":41,"area":"lr"},{"id":"2502.07218","title":"LLM Unlearning via Neural Activation Redirection","created":"2025-02-11","cited_by_count":41,"area":"safety"},{"id":"2507.16795","title":"Steering Out-of-Distribution Generalization with Concept Ablation Fine-Tuning","created":"2025-07-22","cited_by_count":39,"area":null},{"id":"2410.07064","title":"Data Selection via Optimal Control for Language Models","created":"2024-10-09","cited_by_count":38,"area":null},{"id":"2312.04339","title":"Merging by Matching Models in Task Parameter Subspaces","created":"2023-12-07","cited_by_count":36,"area":null},{"id":"2412.09538","title":"Capturing the Temporal Dependence of Training Data Influence","created":"2024-12-12","cited_by_count":35,"area":null},{"id":"2310.10322","title":"Evaluating the Reversal Curse in Model Editing","created":"2023-10-16","cited_by_count":34,"area":null},{"id":"2409.16986","title":"Harnessing Diversity for Important Data Selection in Pretraining Large Language Models","created":"2024-09-25","cited_by_count":34,"area":null},{"id":"2410.13850","title":"Influence Functions for Scalable Data Attribution in Diffusion Models","created":"2024-10-17","cited_by_count":33,"area":"diffusion"},{"id":"2408.06223","title":"On Effects of Steering Latent Representation for Large Language Model Unlearning","created":"2024-08-12","cited_by_count":32,"area":"safety"},{"id":"2409.18153","title":"Most Influential Subset Selection: Challenges, Promises, and Beyond","created":"2024-09-25","cited_by_count":32,"area":null},{"id":"2404.01019","title":"Source-Aware Training Enables Knowledge Attribution in Language Models","created":"2024-04-01","cited_by_count":30,"area":null},{"id":"2410.01748","title":"Not All LLM Reasoners Are Created Equal","created":"2024-10-02","cited_by_count":30,"area":"lr"},{"id":"2402.14015","title":"Corrective Machine Unlearning","created":"2024-02-21","cited_by_count":29,"area":"safety"},{"id":"2408.02085","title":"Unleashing the Power of Data Tsunami: A Comprehensive Survey on Data Assessment and Selection for Instruction Tuning of Language Models","created":"2024-08-04","cited_by_count":29,"area":"alignment"},{"id":"2410.03659","title":"Unraveling Cross-Modality Knowledge Conflicts in Large Vision-Language Models","created":"2024-10-04","cited_by_count":28,"area":"mllm"},{"id":"2410.17509","title":"WAGLE: Strategic Weight Attribution for Effective and Modular Unlearning in Large Language Models","created":"2024-10-23","cited_by_count":26,"area":"safety"},{"id":"2407.06488","title":"Towards Understanding Multi-Task Learning (Generalization) of LLMs via Detecting and Exploring Task-Specific Neurons","created":"2024-07-09","cited_by_count":25,"area":null},{"id":"2409.04481","title":"Large Language Models in Drug Discovery and Development: From Disease Mechanisms to Clinical Trials","created":"2024-09-06","cited_by_count":24,"area":null},{"id":"2411.07681","title":"What Do Learning Dynamics Reveal About Generalization in LLM Reasoning?","created":"2024-11-12","cited_by_count":23,"area":"lr"},{"id":"2411.15102","title":"AttriBoT: A Bag of Tricks for Efficiently Approximating Leave-One-Out Context Attribution","created":"2024-11-22","cited_by_count":23,"area":null},{"id":"2506.19121","title":"CUPID: Curating Data your Robot Loves with Influence Functions","created":"2025-06-23","cited_by_count":23,"area":"offlinerl"},{"id":"2509.11452","title":"Learning to Optimize Multi-Objective Alignment Through Dynamic Reward Weighting","created":"2025-09-14","cited_by_count":23,"area":"alignment"},{"id":"2311.08576","title":"Towards Evaluating AI Systems for Moral Status Using Self-Reports","created":"2023-11-14","cited_by_count":22,"area":null},{"id":"2404.09554","title":"Explainable Generative AI (GenXAI): A Survey, Conceptualization, and Research Agenda","created":"2024-04-15","cited_by_count":22,"area":null},{"id":"2406.09408","title":"Data Attribution for Text-to-Image Models by Unlearning Synthesized Images","created":"2024-06-13","cited_by_count":22,"area":"safety"},{"id":"2504.16430","title":"MAGIC: Near-Optimal Data Attribution for Deep Learning","created":"2025-04-23","cited_by_count":22,"area":null},{"id":"2401.15866","title":"Stochastic Amortization: A Unified Approach to Accelerate Feature and Data Attribution","created":"2024-01-29","cited_by_count":21,"area":null},{"id":"2405.15603","title":"Kronecker-Factored Approximate Curvature for Physics-Informed Neural Networks","created":"2024-05-24","cited_by_count":21,"area":null},{"id":"2410.05180","title":"Mitigating the Risk of Health Inequity Exacerbated by Large Language Models","created":"2024-10-07","cited_by_count":21,"area":null},{"id":"2405.11724","title":"Token-wise Influential Training Data Retrieval for Large Language Models","created":"2024-05-20","cited_by_count":20,"area":null},{"id":"2409.19998","title":"Do Influence Functions Work on Large Language Models?","created":"2024-09-30","cited_by_count":20,"area":null},{"id":"2506.10387","title":"Mirage-1: Augmenting and Updating GUI Agent with Hierarchical Multimodal Skills","created":"2025-06-12","cited_by_count":19,"area":"mllm"},{"id":"2401.15241","title":"Unlearning Traces the Influential Training Data of Language Models","created":"2024-01-26","cited_by_count":18,"area":"safety"},{"id":"2410.23232","title":"Attribute-to-Delete: Machine Unlearning via Datamodel Matching","created":"2024-10-30","cited_by_count":18,"area":"safety"},{"id":"2412.10047","title":"Large Action Models: From Inception to Implementation","created":"2024-12-13","cited_by_count":18,"area":null},{"id":"2411.16353","title":"Lessons from Studying Two-Hop Latent Reasoning","created":"2024-11-25","cited_by_count":17,"area":"lr"},{"id":"2402.08922","title":"The Mirrored Influence Hypothesis: Efficient Data Influence Estimation by Harnessing Forward Passes","created":"2024-02-14","cited_by_count":16,"area":null},{"id":"2506.12152","title":"Because we have LLMs, we Can and Should Pursue Agentic Interpretability","created":"2025-06-13","cited_by_count":16,"area":"agents"},{"id":"2404.16621","title":"Hippocrates: An Open-Source Framework for Advancing Large Language Models in Healthcare","created":"2024-04-25","cited_by_count":15,"area":null},{"id":"2507.05261","title":"TokenShapley: Token Level Context Attribution with Shapley Value","created":"2025-06-18","cited_by_count":15,"area":null},{"id":"2406.04606","title":"Helpful or Harmful Data? Fine-tuning-free Shapley Attribution for Explaining Language Model Predictions","created":"2024-06-07","cited_by_count":14,"area":null},{"id":"2410.03249","title":"How Much Can We Forget about Data Contamination?","created":"2024-10-04","cited_by_count":14,"area":null},{"id":"2412.04614","title":"Extractive Structures Learned in Pretraining Enable Generalization on Finetuned Facts","created":"2024-12-05","cited_by_count":14,"area":null},{"id":"2509.26544","title":"Bayesian Influence Functions for Hessian-Free Data Attribution","created":"2025-09-30","cited_by_count":14,"area":null},{"id":"2504.01928","title":"Is the Reversal Curse a Binding Problem? Uncovering Limitations of Transformers from a Basic Generalization Failure","created":"2025-04-02","cited_by_count":13,"area":null},{"id":"2601.14249","title":"Which Reasoning Trajectories Teach Students to Reason Better? A Simple Metric of Informative Alignment","created":"2026-01-20","cited_by_count":13,"area":"lr"},{"id":"2601.21571","title":"Shaping capabilities with token-level data filtering","created":"2026-01-29","cited_by_count":13,"area":null},{"id":"2505.23811","title":"LayerIF: Estimating Layer Quality for Large Language Models using Influence Functions","created":"2025-05-27","cited_by_count":12,"area":null},{"id":"2510.20956","title":"Self-Jailbreaking: Language Models Can Reason Themselves Out of Safety Alignment After Benign Reasoning Training","created":"2025-10-23","cited_by_count":12,"area":"lr"},{"id":"2510.26491","title":"Data-Efficient RLVR via Off-Policy Influence Guidance","created":"2025-10-30","cited_by_count":12,"area":"lr"},{"id":"2602.21492","title":"GradAlign: Gradient-Aligned Data Selection for LLM Reinforcement Learning","created":"2026-02-25","cited_by_count":12,"area":null},{"id":"2312.12747","title":"ALMANACS: A Simulatability Benchmark for Language Model Explainability","created":"2023-12-20","cited_by_count":11,"area":null},{"id":"2402.11750","title":"In-Context Learning Demonstration Selection via Influence Analysis","created":"2024-02-19","cited_by_count":11,"area":null},{"id":"2403.00758","title":"Mitigating Reversal Curse in Large Language Models via Semantic-aware Permutation Training","created":"2024-03-01","cited_by_count":11,"area":null},{"id":"2410.18808","title":"Delving into the Reversal Curse: How Far Can Large Language Models Generalize?","created":"2024-10-24","cited_by_count":11,"area":null},{"id":"2501.05790","title":"Understanding Impact of Human Feedback via Influence Functions","created":"2025-01-10","cited_by_count":11,"area":"alignment"},{"id":"2505.19281","title":"A Snapshot of Influence: A Local Data Attribution Framework for Online Reinforcement Learning","created":"2025-05-25","cited_by_count":11,"area":"deeprl"},{"id":"2310.15047","title":"Implicit meta-learning may lead language models to trust more reliable sources","created":"2023-10-23","cited_by_count":10,"area":null},{"id":"2311.12233","title":"Unifying Corroborative and Contributive Attributions in Large Language Models","created":"2023-11-20","cited_by_count":10,"area":null},{"id":"2405.03869","title":"Outlier Gradient Analysis: Efficiently Identifying Detrimental Training Samples for Deep Learning Models","created":"2024-05-06","cited_by_count":10,"area":null},{"id":"2405.20456","title":"Scaling Laws for the Value of Individual Data Points in Machine Learning","created":"2024-05-30","cited_by_count":10,"area":null},{"id":"2409.17357","title":"Revisiting inverse Hessian vector products for calculating influence functions","created":"2024-09-25","cited_by_count":10,"area":null},{"id":"2410.08102","title":"Efficient Pretraining Data Selection for Language Models via Multi-Actor Collaboration","created":"2024-10-10","cited_by_count":10,"area":null},{"id":"2506.05451","title":"Interpretation Meets Safety: A Survey on Interpretation Methods and Tools for Improving LLM Safety","created":"2025-06-05","cited_by_count":10,"area":"safety"},{"id":"2506.20702","title":"The Singapore Consensus on Global AI Safety Research Priorities","created":"2025-06-25","cited_by_count":10,"area":null},{"id":"2507.14740","title":"Better Training Data Attribution via Better Inverse Hessian-Vector Products","created":"2025-07-19","cited_by_count":10,"area":null},{"id":"2510.06108","title":"Influence Functions for Efficient Data Selection in Reasoning","created":"2025-10-07","cited_by_count":10,"area":"lr"},{"id":"2601.21996","title":"Mechanistic Data Attribution: Tracing the Training Origins of Interpretable LLM Units","created":"2026-01-29","cited_by_count":10,"area":"mechinterp"},{"id":"2602.17835","title":"Influence-Preserving Proxies for Gradient-Based Data Selection in LLM Fine-tuning","created":"2026-02-19","cited_by_count":10,"area":null},{"id":"2312.05705","title":"Structured Inverse-Free Natural Gradient: Memory-Efficient & Numerically-Stable KFAC","created":"2023-12-09","cited_by_count":9,"area":null},{"id":"2312.07779","title":"Tell, don't show: Declarative facts influence how LLMs generalize","created":"2023-12-12","cited_by_count":9,"area":null},{"id":"2401.04374","title":"Towards Explainable Artificial Intelligence (XAI): A Data Mining Perspective","created":"2024-01-09","cited_by_count":9,"area":null},{"id":"2406.16135","title":"Crosslingual Capabilities and Knowledge Barriers in Multilingual Large Language Models","created":"2024-06-23","cited_by_count":9,"area":null}],"next_cursor":"100"}