On the Universal Truthfulness Hyperplane Inside LLMs

Junteng Liu, Shiqi Chen, Yu Cheng, Junxian He


Abstract
While large language models (LLMs) have demonstrated remarkable abilities across various fields, hallucination remains a significant challenge. Recent studies have explored hallucinations through the lens of internal representations, proposing mechanisms to decipher LLMs’ adherence to facts. However, these approaches often fail to generalize to out-of-distribution data, leading to concerns about whether internal representation patterns reflect fundamental factual awareness, or only overfit spurious correlations on the specific datasets. In this work, we investigate whether a universal truthfulness hyperplane that distinguishes the model’s factually correct and incorrect outputs exists within the model. To this end, we scale up the number of training datasets and conduct an extensive evaluation – we train the truthfulness hyperplane on a diverse collection of over 40 datasets and examine its cross-task, cross-domain, and in-domain generalization. Our results indicate that increasing the diversity of the training datasets significantly enhances the performance in all scenarios, while the volume of data samples plays a less critical role. This finding supports the optimistic hypothesis that a universal truthfulness hyperplane may indeed exist within the model, offering promising directions for future research.
Anthology ID:
2024.emnlp-main.1012
Volume:
Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing
Month:
November
Year:
2024
Address:
Miami, Florida, USA
Editors:
Yaser Al-Onaizan, Mohit Bansal, Yun-Nung Chen
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
18199–18224
Language:
URL:
https://aclanthology.org/2024.emnlp-main.1012
DOI:
10.18653/v1/2024.emnlp-main.1012
Bibkey:
Cite (ACL):
Junteng Liu, Shiqi Chen, Yu Cheng, and Junxian He. 2024. On the Universal Truthfulness Hyperplane Inside LLMs. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 18199–18224, Miami, Florida, USA. Association for Computational Linguistics.
Cite (Informal):
On the Universal Truthfulness Hyperplane Inside LLMs (Liu et al., EMNLP 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.emnlp-main.1012.pdf