GRATH: Gradual Self-Truthifying for Large Language Models

no code implementations • 22 Jan 2024 • Weixin Chen, Dawn Song, Bo Li

GRATH iteratively refines truthfulness data and updates the model, leading to a gradual improvement in model truthfulness in a self-supervised manner.

FMMRec: Fairness-aware Multimodal Recommendation

no code implementations • 26 Oct 2023 • Weixin Chen, Li Chen, Yongxin Ni, Yuhan Zhao, Fajie Yuan, Yongfeng Zhang

Recently, multimodal recommendations have gained increasing attention for effectively addressing the data sparsity problem by incorporating modality-based representations.

Attribute counterfactual +3

DecodingTrust: A Comprehensive Assessment of Trustworthiness in GPT Models

no code implementations • NeurIPS 2023 • Boxin Wang, Weixin Chen, Hengzhi Pei, Chulin Xie, Mintong Kang, Chenhui Zhang, Chejian Xu, Zidi Xiong, Ritik Dutta, Rylan Schaeffer, Sang T. Truong, Simran Arora, Mantas Mazeika, Dan Hendrycks, Zinan Lin, Yu Cheng, Sanmi Koyejo, Dawn Song, Bo Li

Yet, while the literature on the trustworthiness of GPT models remains limited, practitioners have proposed employing capable GPT models for sensitive applications such as healthcare and finance -- where mistakes can be costly.

Adversarial Robustness Ethics +1

TrojDiff: Trojan Attacks on Diffusion Models with Diverse Targets

3 code implementations • CVPR 2023 • Weixin Chen, Dawn Song, Bo Li

To answer these questions, we propose an effective Trojan attack against diffusion models, TrojDiff, which optimizes the Trojan diffusion and generative processes during training.

Image Generation

Enabling the Network to Surf the Internet

no code implementations • 24 Feb 2021 • Zhuoling Li, Haohan Wang, Tymoteusz Swistek, Weixin Chen, Yuanzheng Li, Haoqian Wang

Few-shot learning is challenging due to the limited data and labels.

Few-Shot Learning Self-Supervised Learning