{"total":36,"rows":[{"id":"2101.00190","title":"Prefix-Tuning: Optimizing Continuous Prompts for Generation","created":"2021-01-01","cited_by_count":3915,"area":null},{"id":"2111.01243","title":"Recent Advances in Natural Language Processing via Large Pre-Trained Language Models: A Survey","created":"2021-11-01","cited_by_count":463,"area":null},{"id":"2211.15583","title":"On the Effectiveness of Parameter-Efficient Fine-Tuning","created":"2022-11-28","cited_by_count":141,"area":null},{"id":"2409.05746","title":"LLMs Will Always Hallucinate, and We Need to Live With This","created":"2024-09-09","cited_by_count":78,"area":null},{"id":"2301.01821","title":"Parameter-Efficient Fine-Tuning Design Spaces","created":"2023-01-04","cited_by_count":67,"area":null},{"id":"2104.03514","title":"Low-Complexity Probing via Finding Subnetworks","created":"2021-04-08","cited_by_count":64,"area":null},{"id":"2504.02922","title":"Overcoming Sparsity Artifacts in Crosscoders to Interpret Chat-Tuning","created":"2025-04-03","cited_by_count":34,"area":null},{"id":"2106.02205","title":"Enabling Lightweight Fine-tuning for Pre-trained Language Model Compression based on Matrix Product Operators","created":"2021-06-04","cited_by_count":29,"area":null},{"id":"2303.10464","title":"SPDF: Sparse Pre-training and Dense Fine-tuning for Large Language Models","created":"2023-03-18","cited_by_count":28,"area":null},{"id":"2510.13900","title":"Narrow Finetuning Leaves Clearly Readable Traces in Activation Differences","created":"2025-10-14","cited_by_count":28,"area":null},{"id":"2110.08329","title":"Control Prefixes for Parameter-Efficient Text Generation","created":"2021-10-15","cited_by_count":24,"area":null},{"id":"2109.04740","title":"How Does Fine-tuning Affect the Geometry of Embedding Space: A Case Study on Isotropy","created":"2021-09-10","cited_by_count":23,"area":null},{"id":"2404.18466","title":"HFT: Half Fine-Tuning for Large Language Models","created":"2024-04-29","cited_by_count":18,"area":null},{"id":"2302.06354","title":"Less is More: Selective Layer Finetuning with SubTuning","created":"2023-02-13","cited_by_count":14,"area":null},{"id":"2108.06277","title":"Towards Structured Dynamic Sparse Pre-Training of BERT","created":"2021-08-13","cited_by_count":12,"area":null},{"id":"2204.11218","title":"Learning to Win Lottery Tickets in BERT Transfer via Task-agnostic Mask Training","created":"2022-04-24","cited_by_count":10,"area":null},{"id":"2205.11833","title":"Diverse Lottery Tickets Boost Ensemble from a Single Pretrained Model","created":"2022-05-24","cited_by_count":7,"area":null},{"id":"2210.05211","title":"A Win-win Deal: Towards Sparse and Robust Pre-trained Language Models","created":"2022-10-11","cited_by_count":7,"area":null},{"id":"2406.05360","title":"Flexible and Adaptable Summarization via Expertise Separation","created":"2024-06-08","cited_by_count":7,"area":null},{"id":"2110.14943","title":"Semi-Siamese Bi-encoder Neural Ranking Model Using Lightweight Fine-Tuning","created":"2021-10-28","cited_by_count":6,"area":null},{"id":"2403.20284","title":"LayerNorm: A key component in parameter-efficient fine-tuning","created":"2024-03-29","cited_by_count":4,"area":null},{"id":"2602.12601","title":"HyperMLP: An Integrated Perspective for Sequence Modeling","created":"2026-02-13","cited_by_count":3,"area":null},{"id":"2109.02572","title":"Enhancing Natural Language Representation with Large-Scale Out-of-Domain Commonsense","created":"2021-09-06","cited_by_count":2,"area":null},{"id":"2207.10858","title":"Two-Stage Fine-Tuning: A Novel Strategy for Learning Class-Imbalanced Data","created":"2022-07-22","cited_by_count":2,"area":null},{"id":"2505.23117","title":"Decom-Renorm-Merge: Model Merging on the Right Space Improves Multitasking","created":"2025-05-29","cited_by_count":2,"area":null},{"id":"2602.15897","title":"Mitigating Gradient Inversion Risks in Language Models via Token Obfuscation","created":"2026-02-11","cited_by_count":2,"area":null},{"id":"2205.12186","title":"Continual Learning with Global Alignment","created":"2022-05-24","cited_by_count":1,"area":null},{"id":"2301.09820","title":"A Stability Analysis of Fine-Tuning a Pre-Trained Model","created":"2023-01-24","cited_by_count":1,"area":null},{"id":"2405.11040","title":"From Generalist to Specialist: Improving Large Language Models for Medical Physics Using ARCoT","created":"2024-05-17","cited_by_count":1,"area":null},{"id":"2408.13482","title":"MPruner: Optimizing Neural Network Size with CKA-Based Mutual Information Pruning","created":"2024-08-24","cited_by_count":1,"area":null},{"id":"2506.18221","title":"These Are Not All the Features You Are Looking For: A Fundamental Bottleneck in Supervised Pretraining","created":"2025-06-23","cited_by_count":1,"area":null},{"id":"2401.04051","title":"Empirical Analysis of Efficient Fine-Tuning Methods for Large Pre-Trained Language Models","created":"2024-01-08","cited_by_count":0,"area":null},{"id":"2409.07407","title":"CLNX: Bridging Code and Natural Language for C/C++ Vulnerability-Contributing Commits Identification","created":"2024-09-11","cited_by_count":0,"area":null},{"id":"2506.03674","title":"Out-of-Distribution Graph Models Merging","created":"2025-06-04","cited_by_count":0,"area":null},{"id":"2510.09160","title":"Efficient Resource-Constrained Training of Transformers via Subspace Optimization","created":"2025-10-10","cited_by_count":0,"area":null},{"id":"2609.22146","title":"GRRR: The Geometry of Reshaping, Rotation, and Routing in Decoder LLM post-training","created":"2026-08-26","cited_by_count":0,"area":null}],"next_cursor":null}