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

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.

Authors

• Zhongzhi Chen Beihang University Tencent Inc.
• Xingwu Sun Tencent University of Macau
• Xianfeng Jiao Tencent Inc.
• Fengzong Lian Tencent Inc.
• Zhanhui Kang Tencent
• Di Wang King Abdullah University of Science and Technology
• Chengzhong Xu University of Macau

Keywords

• General