{"total":23,"rows":[{"id":"2302.05319","title":"Large Language Models for Code: Security Hardening and Adversarial Testing","created":"2023-02-10","cited_by_count":155,"area":null},{"id":"2406.16838","title":"From Decoding to Meta-Generation: Inference-time Algorithms for Large Language Models","created":"2024-06-24","cited_by_count":137,"area":null},{"id":"2205.11275","title":"RL with KL penalties is better viewed as Bayesian inference","created":"2022-05-23","cited_by_count":135,"area":null},{"id":"2208.11663","title":"PEER: A Collaborative Language Model","created":"2022-08-24","cited_by_count":86,"area":null},{"id":"2206.00761","title":"On Reinforcement Learning and Distribution Matching for Fine-Tuning Language Models with no Catastrophic Forgetting","created":"2022-06-01","cited_by_count":82,"area":null},{"id":"2308.11131","title":"ReLLa: Retrieval-enhanced Large Language Models for Lifelong Sequential Behavior Comprehension in Recommendation","created":"2023-08-22","cited_by_count":77,"area":null},{"id":"2205.12558","title":"Gradient-Based Constrained Sampling from Language Models","created":"2022-05-25","cited_by_count":64,"area":null},{"id":"2406.06391","title":"Towards Lifelong Learning of Large Language Models: A Survey","created":"2024-06-10","cited_by_count":64,"area":null},{"id":"2205.14219","title":"Controllable Text Generation with Neurally-Decomposed Oracle","created":"2022-05-27","cited_by_count":41,"area":null},{"id":"2312.06185","title":"KnowGPT: Knowledge Graph based Prompting for Large Language Models","created":"2023-12-11","cited_by_count":31,"area":null},{"id":"2404.13506","title":"Parameter Efficient Fine Tuning: A Comprehensive Analysis Across Applications","created":"2024-04-21","cited_by_count":25,"area":null},{"id":"2402.19371","title":"OpenMedLM: Prompt engineering can out-perform fine-tuning in medical question-answering with open-source large language models","created":"2024-02-29","cited_by_count":20,"area":null},{"id":"2310.02527","title":"CITING: Large Language Models Create Curriculum for Instruction Tuning","created":"2023-10-04","cited_by_count":14,"area":null},{"id":"2407.20999","title":"MoFO: Momentum-Filtered Optimizer for Mitigating Forgetting in LLM Fine-Tuning","created":"2024-07-30","cited_by_count":14,"area":null},{"id":"2302.14401","title":"GLM-Dialog: Noise-tolerant Pre-training for Knowledge-grounded Dialogue Generation","created":"2023-02-28","cited_by_count":9,"area":null},{"id":"2410.09982","title":"Self-Data Distillation for Recovering Quality in Pruned Large Language Models","created":"2024-10-13","cited_by_count":8,"area":null},{"id":"2410.06716","title":"Guaranteed Generation from Large Language Models","created":"2024-10-09","cited_by_count":7,"area":null},{"id":"2303.05431","title":"disco: a toolkit for Distributional Control of Generative Models","created":"2023-03-08","cited_by_count":3,"area":null},{"id":"2601.21577","title":"Collaborative Parameter Learning: Mitigating Forgetting via Parameter-Level Gradient Analysis","created":"2026-01-29","cited_by_count":2,"area":null},{"id":"2406.13660","title":"Towards Minimal Targeted Updates of Language Models with Targeted Negative Training","created":"2024-06-19","cited_by_count":1,"area":null},{"id":"2602.02767","title":"Provable Effects of Data Replay in Continual Learning: A Feature Learning Perspective","created":"2026-02-02","cited_by_count":1,"area":null},{"id":"2509.26242","title":"Finetune Once: Decoupling General & Domain Learning with Dynamic Boosted Annealing","created":"2025-09-30","cited_by_count":0,"area":null},{"id":"2510.12029","title":"CPR: Mitigating Large Language Model Hallucinations with Curative Prompt Refinement","created":"2025-10-14","cited_by_count":0,"area":null}],"next_cursor":null}