Papers
arxiv:2509.17932

Training-free Truthfulness Detection via Value Vectors in LLMs

Published on Sep 22
Authors:
,
,
,

Abstract

TruthV, a training-free method, detects truthfulness in large language models by analyzing value vectors in MLP modules, outperforming existing approaches like NoVo.

AI-generated summary

Large language models often generate factually incorrect outputs, motivating efforts to detect the truthfulness of their content. Most existing approaches rely on training probes over internal activations, but these methods suffer from scalability and generalization issues. A recent training-free method, NoVo, addresses this challenge by exploiting statistical patterns from the model itself. However, it focuses exclusively on attention mechanisms, potentially overlooking the MLP module-a core component of Transformer models known to support factual recall. In this paper, we show that certain value vectors within MLP modules exhibit truthfulness-related statistical patterns. Building on this insight, we propose TruthV, a simple and interpretable training-free method that detects content truthfulness by leveraging these value vectors. On the NoVo benchmark, TruthV significantly outperforms both NoVo and log-likelihood baselines, demonstrating that MLP modules-despite being neglected in prior training-free efforts-encode rich and useful signals for truthfulness detection. These findings offer new insights into how truthfulness is internally represented in LLMs and motivate further research on scalable and interpretable truthfulness detection.

Community

Sign up or log in to comment

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2509.17932 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2509.17932 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2509.17932 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.