Truth Forest: Toward Multi-Scale Truthfulness in Large Language Models through Intervention without Tuning
Zhongzhi Chen, Xingwu Sun, Xianfeng Jiao, Fengzong Lian, Zhanhui Kang, Di Wang, Chengzhong Xu
Abstract
Despite the great success of large language models (LLMs) in various tasks, they suffer from generating hallucinations. We introduce Truth Forest, a method that enhances truthfulness in LLMs by uncovering hidden truth representations using multi-dimensional orthogonal probes. Specifically, it creates multiple orthogonal bases for modeling truth by incorporating orthogonal constraints into the probes. Moreover, we introduce Random Peek, a systematic technique considering an extended range of positions within the sequence, reducing the gap between discerning and generating truth features in LLMs. By employing this approach, we improved the truthfulness of Llama-2-7B from 40.8% to 74.5% on TruthfulQA. Likewise, significant improvements are observed in fine-tuned models. We conducted a thorough analysis of truth features using probes. Our visualization results show that orthogonal probes capture complementary truth-related features, forming well-defined clusters that reveal the inherent structure of the dataset.
BibTeX
@article{Chen_Sun_Jiao_Lian_Kang_Wang_Xu_2024, title={Truth Forest: Toward Multi-Scale Truthfulness in Large Language Models through Intervention without Tuning}, volume={38}, url={https://ojs.aaai.org/index.php/AAAI/article/view/30087}, DOI={10.1609/aaai.v38i19.30087}, abstractNote={Despite the great success of large language models (LLMs) in various tasks, they suffer from generating hallucinations. We introduce Truth Forest, a method that enhances truthfulness in LLMs by uncovering hidden truth representations using multi-dimensional orthogonal probes. Specifically, it creates multiple orthogonal bases for modeling truth by incorporating orthogonal constraints into the probes. Moreover, we introduce Random Peek, a systematic technique considering an extended range of positions within the sequence, reducing the gap between discerning and generating truth features in LLMs. By employing this approach, we improved the truthfulness of Llama-2-7B from 40.8% to 74.5% on TruthfulQA. Likewise, significant improvements are observed in fine-tuned models. We conducted a thorough analysis of truth features using probes. Our visualization results show that orthogonal probes capture complementary truth-related features, forming well-defined clusters that reveal the inherent structure of the dataset.}, number={19}, journal={Proceedings of the AAAI Conference on Artificial Intelligence}, author={Chen, Zhongzhi and Sun, Xingwu and Jiao, Xianfeng and Lian, Fengzong and Kang, Zhanhui and Wang, Di and Xu, Chengzhong}, year={2024}, month={Mar.}, pages={20967-20974} }