{"total":54,"rows":[{"id":"2407.15017","title":"Knowledge Mechanisms in Large Language Models: A Survey and Perspective","created":"2024-07-22","cited_by_count":51,"area":null},{"id":"2502.01563","title":"Massive Values in Self-Attention Modules are the Key to Contextual Knowledge Understanding","created":"2025-02-03","cited_by_count":47,"area":null},{"id":"2503.05788","title":"Emergent Abilities in Large Language Models: A Survey","created":"2025-02-28","cited_by_count":37,"area":null},{"id":"2509.23024","title":"Tracing the Representation Geometry of Language Models from Pretraining to Post-training","created":"2025-09-27","cited_by_count":35,"area":null},{"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":"2504.12459","title":"On Linear Representations and Pretraining Data Frequency in Language Models","created":"2025-04-16","cited_by_count":23,"area":null},{"id":"2412.07684","title":"The Pitfalls of Memorization: When Memorization Hurts Generalization","created":"2024-12-10","cited_by_count":19,"area":null},{"id":"2410.01769","title":"Quantifying Generalization Complexity for Large Language Models","created":"2024-10-02","cited_by_count":18,"area":null},{"id":"2511.04418","title":"The Illusion of Certainty: Uncertainty Quantification for LLMs Fails under Ambiguity","created":"2025-11-06","cited_by_count":17,"area":null},{"id":"2509.21519","title":"Provable Scaling Laws of Feature Emergence from Learning Dynamics of Grokking","created":"2025-09-25","cited_by_count":15,"area":null},{"id":"2412.15291","title":"A Large-Scale Simulation on Large Language Models for Decision-Making in Political Science","created":"2024-12-19","cited_by_count":10,"area":null},{"id":"2501.12619","title":"Quantification of Large Language Model Distillation","created":"2025-01-22","cited_by_count":9,"area":null},{"id":"2412.20760","title":"Attributing Culture-Conditioned Generations to Pretraining Corpora","created":"2024-12-30","cited_by_count":8,"area":null},{"id":"2510.18554","title":"Extracting alignment data in open models","created":"2025-10-21","cited_by_count":8,"area":null},{"id":"2512.01970","title":"Atomic Skills are the Prerequisite: When Reinforcement Learning Synthesizes Compositional Reasoning, and When It Only Amplifies","created":"2025-12-01","cited_by_count":8,"area":null},{"id":"2410.10870","title":"PortLLM: Personalizing Evolving Large Language Models with Training-Free and Portable Model Patches","created":"2024-10-08","cited_by_count":7,"area":null},{"id":"2509.23383","title":"Train Once, Answer All: Many Pretraining Experiments for the Cost of One","created":"2025-09-27","cited_by_count":6,"area":null},{"id":"2510.09259","title":"Detecting Data Contamination from Reinforcement Learning Post-training for Large Language Models","created":"2025-10-10","cited_by_count":6,"area":null},{"id":"2506.01675","title":"Cross-Lingual Transfer of Cultural Knowledge: An Asymmetric Phenomenon","created":"2025-06-02","cited_by_count":5,"area":null},{"id":"2507.07186","title":"Planted in Pretraining, Swayed by Finetuning: A Case Study on the Origins of Cognitive Biases in LLMs","created":"2025-07-09","cited_by_count":5,"area":null},{"id":"2507.21914","title":"Rote Learning Considered Useful: Generalizing over Memorized Data in LLMs","created":"2025-07-29","cited_by_count":5,"area":null},{"id":"2510.08608","title":"MMA-ASIA: A Multilingual and Multimodal Alignment Framework for Culturally-Grounded Evaluation","created":"2025-10-07","cited_by_count":5,"area":null},{"id":"2511.04715","title":"First is Not Really Better Than Last: Evaluating Layer Choice and Aggregation Strategies in Language Model Data Influence Estimation","created":"2025-11-06","cited_by_count":5,"area":null},{"id":"2502.07830","title":"Captured by Captions: On Memorization and its Mitigation in CLIP Models","created":"2025-02-11","cited_by_count":4,"area":null},{"id":"2603.03415","title":"Farther the Shift, Sparser the Representation: Analyzing OOD Mechanisms in LLMs","created":"2026-03-03","cited_by_count":4,"area":null},{"id":"2411.11266","title":"VersaTune: An Efficient Data Composition Framework for Training Multi-Capability LLMs","created":"2024-11-18","cited_by_count":3,"area":null},{"id":"2506.09591","title":"Memorization in Language Models through the Lens of Intrinsic Dimension","created":"2025-06-11","cited_by_count":3,"area":null},{"id":"2603.10846","title":"Towards Cold-Start Drafting and Continual Refining: A Value-Driven Memory Approach with Application to NPU Kernel Synthesis","created":"2026-03-11","cited_by_count":3,"area":null},{"id":"2504.04083","title":"A Benchmark for End-to-End Zero-Shot Biomedical Relation Extraction with LLMs: Experiments with OpenAI Models","created":"2025-04-05","cited_by_count":2,"area":null},{"id":"2506.17585","title":"Cite Pretrain: Retrieval-Free Knowledge Attribution for Large Language Models","created":"2025-06-21","cited_by_count":2,"area":null},{"id":"2509.15356","title":"Predicting Language Models' Success at Zero-Shot Probabilistic Prediction","created":"2025-09-18","cited_by_count":2,"area":null},{"id":"2510.00034","title":"Review of Hallucination Understanding in Large Language and Vision Models","created":"2025-09-26","cited_by_count":2,"area":null},{"id":"2601.04301","title":"Quantifying the Effect of Test Set Contamination on Generative Evaluations","created":"2026-01-07","cited_by_count":2,"area":null},{"id":"2602.18733","title":"A Prior-Aware Metric for Efficiently Distinguishing Memorization from Generalization in Large Language Models","created":"2026-02-21","cited_by_count":2,"area":null},{"id":"2609.02526","title":"When Persona Attributes Improve Population Alignment in Large Language Models","created":"2026-09-02","cited_by_count":2,"area":null},{"id":"2503.05491","title":"Statistical Deficiency for Task Inclusion Estimation","created":"2025-03-07","cited_by_count":1,"area":null},{"id":"2505.15501","title":"Protoknowledge Shapes Behaviour of LLMs in Downstream Tasks: Memorization and Generalization with Knowledge Graphs","created":"2025-05-21","cited_by_count":1,"area":null},{"id":"2507.06056","title":"Data Compressibility Quantifies LLM Memorization","created":"2025-07-08","cited_by_count":1,"area":null},{"id":"2509.00303","title":"Access Paths for Efficient Ordering with Large Language Models","created":"2025-08-30","cited_by_count":1,"area":null},{"id":"2509.04866","title":"Memorization $\\neq$ Understanding: Do Large Language Models Have the Ability of Scenario Cognition?","created":"2025-09-05","cited_by_count":1,"area":null},{"id":"2509.26347","title":"Uncovering Zero-Shot Generalization Gaps in Time-Series Foundation Models Using Real-World Videos","created":"2025-09-30","cited_by_count":1,"area":null},{"id":"2510.19036","title":"From Memorization to Generalization: Fine-Tuning Large Language Models for Biomedical Term-to-Identifier Normalization","created":"2025-10-21","cited_by_count":1,"area":null},{"id":"2604.21211","title":"Subject-level Inference for Realistic Text Anonymization Evaluation","created":"2026-04-23","cited_by_count":1,"area":null},{"id":"2606.28479","title":"Decomposing Memorization Reduction in Privacy-Preserving Fine-Tuning of SLMs for CSIRTs","created":"2026-06-26","cited_by_count":1,"area":null},{"id":"2607.04969","title":"Train Smarter, Not Longer: Memorization-Guided Data Reuse for Efficient LLM Training","created":"2026-07-06","cited_by_count":1,"area":null},{"id":"2608.30372","title":"Auditing MCQA Benchmarks through Probability Landscapes","created":"2026-08-31","cited_by_count":1,"area":null},{"id":"2503.00992","title":"Evidence of conceptual mastery in the application of rules by Large Language Models","created":"2025-03-02","cited_by_count":0,"area":null},{"id":"2506.20481","title":"Counterfactual Influence as a Distributional Quantity","created":"2025-06-25","cited_by_count":0,"area":null},{"id":"2510.14261","title":"Rewriting History: A Recipe for Interventional Analyses to Study Data Effects on Model Behavior","created":"2025-10-16","cited_by_count":0,"area":null},{"id":"2510.27313","title":"LLM generation novelty through the lens of semantic similarity","created":"2025-10-31","cited_by_count":0,"area":null},{"id":"2511.00476","title":"Remembering Unequally: Global and Disciplinary Bias in LLM Reconstruction of Scholarly Coauthor Lists","created":"2025-11-01","cited_by_count":0,"area":null},{"id":"2511.21006","title":"TrackList: Tracing Back Query Linguistic Diversity for Head and Tail Knowledge in Open Large Language Models","created":"2025-11-26","cited_by_count":0,"area":null},{"id":"2608.05157","title":"Large Language Models Threaten Double-blind Review","created":"2026-05-23","cited_by_count":0,"area":null},{"id":"2609.21888","title":"Detecting Pretraining Data in Large Language Models from a Free-Energy Perspective","created":"2026-09-18","cited_by_count":0,"area":null}],"next_cursor":null}