paper-with-me

홈 › Papers

On the Universal Truthfulness Hyperplane Inside LLMs

2024-07-11 · Junteng Liu, Shiqi Chen, Yu Cheng, Junxian He

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.

📄 PDF Abstract BibTeX arXiv:2407.08582

Code (1)

hkust-nlp/universal_truthfulness_hyperplane 공식 구현 pytorch

Tasks

DiversityDomain GeneralizationHallucination

Similar Papers 제목 키워드 기반

Truth Knows No Language: Evaluating Truthfulness Beyond English

2025-02-13 · Blanca Calvo Figueras, Eneko Sagarzazu, Julen Etxaniz, Jeremy Barnes 외

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+1

Probing the Geometry of Truth: Consistency and Generalization of Truth Directions in LLMs Across Logical Transformations and Question Answering Tasks

2025-06-01 · Yuntai Bao, Xuhong Zhang, Tianyu Du, Xinkui Zhao 외

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 Knowledge

LLMs Know More Than They Show: On the Intrinsic Representation of LLM Hallucinations

2024-10-03 · Hadas Orgad, Michael Toker, Zorik Gekhman, Roi Reichart 외

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

2017-06-06 · ICML 2017 8 · Manolis C. Tsakiris, Rene Vidal

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…

Clustering

Purging the Gray Zone: Latent-Geometric Denoising for Precise Knowledge Boundary Awareness

2026-04-15 · Hao An, Yibin Lou, Jiayi Guo, Yang Xu arxiv

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 …