3 citations · 7 across the 16 of their papers we have counts for
17 papers
Do LLMs Really Forget? Hidden-State Leakage in Model Unlearning and How to Fix it
Hadi Reisizadeh, Jiajun Ruan, Sijia Liu +1
Unlearning in large language models (LLMs) is typically evaluated at the output level, where a model appears to suppress sensitive or undesirable content. In this work, we show tha…
Multimodal Unlearning Across Vision, Language, Video, and Audio: Survey of Methods, Datasets, and Benchmarks
Nobin Sarwar, Shubhashis Roy Dipta, Zheyuan Liu +1
With the growing adoption of VLMs, DMs, LLMs, and AFMs, these multimodal foundation models can inadvertently encode sensitive, copyrighted, biased, or unsafe cross-modal associatio…
See What I See, Know What I Think: Dense Latent Communication Across Heterogeneous Agents
Siyi Chen, Xiaoyan Zhang, Meng Wu +7
Language-model agents build internal representations of the information they observe and the reasoning they perform. Sharing these representations offers a way to communicate both…
PrivUn: Unveiling Latent Ripple Effects and Shallow Forgetting in Privacy Unlearning
Xiaoyi Chen, Haoyuan Wang, Siyuan Tang +4
Large language models (LLMs) often memorize private information during training, raising serious privacy concerns. While machine unlearning has emerged as a promising solution, its…
Attention Smoothing Is All You Need For Unlearning
Saleh Zare Zade, Xiangyu Zhou, Sijia Liu +1
Large Language Models are prone to memorizing sensitive, copyrighted, or hazardous content, posing significant privacy and legal concerns. Retraining from scratch is computationall…
Powering Up Zeroth-Order Training via Subspace Gradient Orthogonalization
Yicheng Lang, Changsheng Wang, Yihua Zhang +4
Zeroth-order (ZO) optimization provides a gradient-free alternative to first-order (FO) methods by estimating gradients via finite differences of function evaluations, and has rece…
Leak@: Unlearning Does Not Make LLMs Forget Under Probabilistic Decoding
Hadi Reisizadeh, Jiajun Ruan, Yiwei Chen +3
Unlearning in large language models (LLMs) is critical for regulatory compliance and for building ethical generative AI systems that avoid producing private, toxic, illegal, or cop…
Breaking Memorization Barriers in LLM Code Fine-Tuning via Information Bottleneck for Improved Generalization
Changsheng Wang, Xin Chen, Sijia Liu +1
Adapting pretrained large language models (LLMs) to code domains via supervised fine-tuning (FT) has been commonly used for code generation. However, we identify a previously under…
LLM Unlearning on Noisy Forget Sets: A Study of Incomplete, Rewritten, and Watermarked Data
Changsheng Wang, Yihua Zhang, Dennis Wei +3
Large language models (LLMs) exhibit remarkable generative capabilities but raise ethical and security concerns by memorizing sensitive data, reinforcing biases, and producing harm…
LLM Unlearning Under the Microscope: A Full-Stack View on Methods and Metrics
Chongyu Fan, Changsheng Wang, Yancheng Huang +2
Machine unlearning for large language models (LLMs) aims to remove undesired data, knowledge, and behaviors (e.g., for safety, privacy, or copyright) while preserving useful model…
Humanline: Online Alignment as Perceptual Loss
Sijia Liu, Niklas Muennighoff, Kawin Ethayarajh
Online alignment (e.g., GRPO) is generally more performant than offline alignment (e.g., DPO) -- but why? Drawing on prospect theory from behavioral economics, we propose a human-c…
Unlearning Isn't Invisible: Detecting Unlearning Traces in LLMs from Model Outputs
Yiwei Chen, Soumyadeep Pal, Yimeng Zhang +2
Machine unlearning (MU) for large language models (LLMs), commonly referred to as LLM unlearning, seeks to remove specific undesirable data or knowledge from a trained model, while…
Invariance Makes LLM Unlearning Resilient Even to Unanticipated Downstream Fine-Tuning
Changsheng Wang, Yihua Zhang, Jinghan Jia +6
Machine unlearning offers a promising solution to privacy and safety concerns in large language models (LLMs) by selectively removing targeted knowledge while preserving utility. H…
LLM Unlearning Reveals a Stronger-Than-Expected Coreset Effect in Current Benchmarks
Soumyadeep Pal, Changsheng Wang, James Diffenderfer +2
Large language model unlearning has become a critical challenge in ensuring safety and controlled model behavior by removing undesired data-model influences from the pretrained mod…
FROG: Fair Removal on Graphs
Ziheng Chen, Jiali Cheng, Hadi Amiri +5
With growing emphasis on privacy regulations, machine unlearning has become increasingly critical in real-world applications such as social networks and recommender systems, many o…
LLM Self-Correction with DeCRIM: Decompose, Critique, and Refine for Enhanced Following of Instructions with Multiple Constraints
Thomas Palmeira Ferraz, Kartik Mehta, Yu-Hsiang Lin +7
Instruction following is a key capability for LLMs. However, recent studies have shown that LLMs often struggle with instructions containing multiple constraints (e.g. a request to…
More Samples or More Prompts? Exploring Effective In-Context Sampling for LLM Few-Shot Prompt Engineering
Bingsheng Yao, Guiming Chen, Ruishi Zou +7
While most existing works on LLM prompting techniques focus only on how to select a better set of data samples inside one single prompt input (In-Context Learning or ICL), why can…