Truth Forest: Toward Multi-Scale Truthfulness in Large Language Models through Intervention without Tuning

1 code implementation • 29 Dec 2023 • Zhongzhi Chen, Xingwu Sun, Xianfeng Jiao, Fengzong Lian, Zhanhui Kang, Di Wang, Cheng-Zhong Xu

We introduce Truth Forest, a method that enhances truthfulness in LLMs by uncovering hidden truth representations using multi-dimensional orthogonal probes.

AltCLIP: Altering the Language Encoder in CLIP for Extended Language Capabilities

1 code implementation • 12 Nov 2022 • Zhongzhi Chen, Guang Liu, Bo-Wen Zhang, Fulong Ye, Qinghong Yang, Ledell Wu

In this work, we present a conceptually simple and effective method to train a strong bilingual/multilingual multimodal representation model.

Contrastive Learning Cross-Modal Retrieval +10

Exploiting Global and Local Hierarchies for Hierarchical Text Classification

1 code implementation • 5 May 2022 • Ting Jiang, Deqing Wang, Leilei Sun, Zhongzhi Chen, Fuzhen Zhuang, Qinghong Yang

Existing methods encode label hierarchy in a global view, where label hierarchy is treated as the static hierarchical structure containing all labels.

Multi Label Text Classification Multi-Label Text Classification +1