{"total":20,"rows":[{"id":"2402.08787","title":"Rethinking Machine Unlearning for Large Language Models","created":"2024-02-13","cited_by_count":257,"area":"lr"},{"id":"2402.01761","title":"Rethinking Interpretability in the Era of Large Language Models","created":"2024-01-30","cited_by_count":111,"area":"lr"},{"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":"2410.01748","title":"Not All LLM Reasoners Are Created Equal","created":"2024-10-02","cited_by_count":30,"area":"lr"},{"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":"2411.16353","title":"Lessons from Studying Two-Hop Latent Reasoning","created":"2024-11-25","cited_by_count":17,"area":"lr"},{"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":"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":"2510.06108","title":"Influence Functions for Efficient Data Selection in Reasoning","created":"2025-10-07","cited_by_count":10,"area":"lr"},{"id":"2505.19949","title":"Which Data Attributes Stimulate Math and Code Reasoning? An Investigation via Influence Functions","created":"2025-05-26","cited_by_count":7,"area":"lr"},{"id":"2312.03633","title":"Exploring the Reversal Curse and Other Deductive Logical Reasoning in BERT and GPT-Based Large Language Models","created":"2023-12-06","cited_by_count":5,"area":"lr"},{"id":"2602.03783","title":"Efficient Estimation of Kernel Surrogate Models for Task Attribution","created":"2026-02-03","cited_by_count":4,"area":"lr"},{"id":"2509.00072","title":"Test of Time: Rethinking Temporal Signal of Benchmark Contamination","created":"2025-08-26","cited_by_count":3,"area":"lr"},{"id":"2512.15663","title":"Explaining the Reasoning of Large Language Models Using Attribution Graphs","created":"2025-12-17","cited_by_count":3,"area":"lr"},{"id":"2604.08423","title":"Synthetic Data for any Differentiable Target","created":"2026-04-09","cited_by_count":2,"area":"lr"},{"id":"2508.18672","title":"Optimal Sparsity of Mixture-of-Experts Language Models for Reasoning Tasks","created":"2025-08-26","cited_by_count":1,"area":"lr"},{"id":"2605.24331","title":"CurveRL: Principled Distribution-Aware Context Reweighting for LLM Reasoning","created":"2026-05-23","cited_by_count":0,"area":"lr"},{"id":"2608.29252","title":"Dynamic Important Example Mining for Reinforcement Finetuning","created":"2026-08-29","cited_by_count":0,"area":"lr"},{"id":"2610.06851","title":"Base Models Can Reason By Taking a Cue From Training Data","created":"2026-10-05","cited_by_count":0,"area":"lr"}],"next_cursor":null}