On the Universal Truthfulness Hyperplane Inside LLMs
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.
Code (1)
Tasks
DiversityDomain GeneralizationHallucinationSimilar Papers 제목 키워드 기반
Truth Knows No Language: Evaluating Truthfulness Beyond English
We introduce a professionally translated extension of the TruthfulQA benchmark designed to evaluate truthfulness in Basque, Catalan, Galician, and Spanish. Truthfulness evaluations of large language models (LLMs) have pr…
InformativenessMachine TranslationMultiple-choiceTranslation+1Probing the Geometry of Truth: Consistency and Generalization of Truth Directions in LLMs Across Logical Transformations and Question Answering Tasks
Large language models (LLMs) are trained on extensive datasets that encapsulate substantial world knowledge. However, their outputs often include confidently stated inaccuracies. Earlier works suggest that LLMs encode tr…
In-Context LearningNegationQuestion AnsweringWorld KnowledgeLLMs Know More Than They Show: On the Intrinsic Representation of LLM Hallucinations
Large language models (LLMs) often produce errors, including factual inaccuracies, biases, and reasoning failures, collectively referred to as "hallucinations". Recent studies have demonstrated that LLMs' internal states…
Hyperplane Clustering Via Dual Principal Component Pursuit
We extend the theoretical analysis of a recently proposed single subspace learning algorithm, called Dual Principal Component Pursuit (DPCP), to the case where the data are drawn from of a union of hyperplanes. To gain i…
ClusteringPurging the Gray Zone: Latent-Geometric Denoising for Precise Knowledge Boundary Awareness
Large language models (LLMs) often exhibit hallucinations due to their inability to accurately perceive their own knowledge boundaries. Existing abstention fine-tuning methods typically partition datasets directly based …