8 papers
Train Locally, Learn Together: Distributed Multi-Agent Training via ADMM
Yiwei Chen, Changsheng Wang, Yicheng Lang +3
Multi-agent systems (MAS) can outperform individual language-model agents by combining specialized roles, diverse reasoning processes, and collaborative decision-making. However, c…
Who Built This Model? Tracing LLM Lineage via Spectral Fingerprints in Weight Space
Yiwei Chen, Bingqi Shang, Sijia Liu
Open-weight large language models (LLMs) are increasingly developed through complex, multi-stage pipelines, leading to intricate lineage relationships that reflect model origin, ow…
Data-Centric Benchmarking of Exploit Generation in LLMs: Understanding the Impact of Fine-Tuning
Yiwei Chen, Lichi Li, Kai Cheung +2
We study the task of CVE-conditioned exploit generation, where a model drafts proof-of-concept (PoC) exploits given software vulnerability context. We adopt a data-centric approach…
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…
Forgetting to Forget: Attention Sink as A Gateway for Backdooring LLM Unlearning
Bingqi Shang, Yiwei Chen, Yihua Zhang +2
Large language model (LLM) unlearning is a key approach for removing undesired data, knowledge, or behaviors from pretrained models while retaining their general utility. Yet, with…
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…
Safety Mirage: How Spurious Correlations Undermine VLM Safety Fine-Tuning and Can Be Mitigated by Machine Unlearning
Yiwei Chen, Yuguang Yao, Yihua Zhang +3
Recent vision language models (VLMs) have made remarkable strides in generative modeling with multimodal inputs, particularly text and images. However, their susceptibility to gene…
Diffusion Guided Language Modeling
Justin Lovelace, Varsha Kishore, Yiwei Chen +1
Current language models demonstrate remarkable proficiency in text generation. However, for many applications it is desirable to control attributes, such as sentiment, or toxicity,…