10 papers
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…
Small-Margin Preferences Still Matter-If You Train Them Right
Jinlong Pang, Zhaowei Zhu, Na Di +4
Preference optimization methods such as DPO align large language models (LLMs) using paired comparisons, but their effectiveness can be highly sensitive to the quality and difficul…
Observations and Remedies for Large Language Model Bias in Self-Consuming Performative Loop
Yaxuan Wang, Zhongteng Cai, Yujia Bao +2
The rapid advancement of large language models (LLMs) has led to growing interest in using synthetic data to train future models. However, this creates a self-consuming retraining…
PromptBridge: Cross-Model Prompt Transfer for Large Language Models
Yaxuan Wang, Quan Liu, Zhenting Wang +4
Large language models (LLMs) underpin applications in code generation, mathematical reasoning, and agent-based workflows. In practice, systems access LLMs via commercial APIs or op…
Stabilizing Self-Consuming Diffusion Models with Latent Space Filtering
Zhongteng Cai, Yaxuan Wang, Yang Liu +1
As synthetic data proliferates across the Internet, it is often reused to train successive generations of generative models. This creates a ``self-consuming loop" that can lead to…
DRAGON: Guard LLM Unlearning in Context via Negative Detection and Reasoning
Yaxuan Wang, Chris Yuhao Liu, Quan Liu +4
Unlearning in Large Language Models (LLMs) is crucial for protecting private data and removing harmful knowledge. Most existing approaches rely on fine-tuning to balance unlearning…