paper-with-me

Papers

Exploring Memorization in Fine-tuned Language Models

2023-10-10 · Shenglai Zeng, Yaxin Li, Jie Ren, Yiding Liu, Han Xu, Pengfei He, Yue Xing, Shuaiqiang Wang, Jiliang Tang, Dawei Yin

Large language models (LLMs) have shown great capabilities in various tasks but also exhibited memorization of training data, raising tremendous privacy and copyright concerns. While prior works have studied memorization during pre-training, the exploration of memorization during fine-tuning is rather limited. Compared to pre-training, fine-tuning typically involves more sensitive data and diverse objectives, thus may bring distinct privacy risks and unique memorization behaviors. In this work, we conduct the first comprehensive analysis to explore language models' (LMs) memorization during fine-tuning across tasks. Our studies with open-sourced and our own fine-tuned LMs across various tasks indicate that memorization presents a strong disparity among different fine-tuning tasks. We provide an intuitive explanation of this task disparity via sparse coding theory and unveil a strong correlation between memorization and attention score distribution.

📄 PDF Abstract BibTeX arXiv:2310.06714

Code (0)

등록된 구현이 없습니다.

Tasks

Memorization

Similar Papers 제목 키워드 기반

Memorization in Fine-Tuned Large Language Models

2025-07-28 · Danil Savine arxiv

This study investigates the mechanisms and factors influencing memorization in fine-tuned large language models (LLMs), with a focus on the medical domain due to its privacy-sensitive nature. We examine how different asp…

Quantifying Memorization and Retriever Performance in Retrieval-Augmented Vision-Language Models

2025-02-19 · Peter Carragher, Abhinand Jha, R Raghav, Kathleen M. Carley

Large Language Models (LLMs) demonstrate remarkable capabilities in question answering (QA), but metrics for assessing their reliance on memorization versus retrieval remain underdeveloped. Moreover, while finetuned mode…

MemorizationQuestion AnsweringRetrieval

Unintended Memorization of Sensitive Information in Fine-Tuned Language Models

2026-01-24 · Marton Szep, Jorge Marin Ruiz, Georgios Kaissis, Paulina Seidl 외 arxiv

Fine-tuning Large Language Models (LLMs) on sensitive datasets carries a substantial risk of unintended memorization and leakage of Personally Identifiable Information (PII), which can violate privacy regulations and com…

Exploring Cross-Client Memorization of Training Data in Large Language Models for Federated Learning

2025-10-09 · Tinnakit Udsa, Can Udomcharoenchaikit, Patomporn Payoungkhamdee, Sarana Nutanong 외 arxiv

Federated learning (FL) enables collaborative training without raw data sharing, but still risks training data memorization. Existing FL memorization detection techniques focus on one sample at a time, underestimating mo…

Federated Learning

Unveiling Over-Memorization in Finetuning LLMs for Reasoning Tasks

2025-08-06 · Zhiwen Ruan, Yun Chen, Yutao Hou, Peng Li 외 arxiv

The pretrained large language models (LLMs) are finetuned with labeled data for better instruction following ability and alignment with human values. In this paper, we study the learning dynamics of LLM finetuning on rea…

Instruction Following