Training-free Truthfulness Detection via Value Vectors in LLMs

• URL: http://arxiv.org/abs/2509.17932v1
• Date: Mon, 22 Sep 2025 15:54:29 GMT
• Title: Training-free Truthfulness Detection via Value Vectors in LLMs
• Abstract summary: Large language models often generate factually incorrect outputs, motivating efforts to detect the truthfulness of their content.<n>A recent training-free method, NoVo, addresses this challenge by exploiting statistical patterns from the model itself.<n>We show that certain value vectors within modules exhibit truthfulness-free statistical patterns.<n>We propose TruthV, a simple and interpretable training method that detects content truthfulness by leveraging these value vectors.
• Score: 37.5974102248718
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• Unlearning Isn't Invisible: Detecting Unlearning Traces in LLMs from Model Outputs [19.08691637612329]
  Machine unlearning (MU) for large language models (LLMs) seeks to remove specific undesirable data or knowledge from a trained model.<n>We identify a new vulnerability post-unlearning: unlearning trace detection.<n>We show that forget-relevant prompts enable over 90% accuracy in detecting unlearning traces across all model sizes.
  arXiv  Detail & Related papers  (2025-06-16T21:03:51Z)
• Factual Self-Awareness in Language Models: Representation, Robustness, and Scaling [56.26834106704781]
  Factual incorrectness in generated content is one of the primary concerns in ubiquitous deployment of large language models (LLMs)<n>We provide evidence supporting the presence of LLMs' internal compass that dictate the correctness of factual recall at the time of generation.<n>Scaling experiments across model sizes and training dynamics highlight that self-awareness emerges rapidly during training and peaks in intermediate layers.
  arXiv  Detail & Related papers  (2025-05-27T16:24:02Z)
• Memorization or Interpolation ? Detecting LLM Memorization through Input Perturbation Analysis [8.725781605542675]
  Large Language Models (LLMs) achieve remarkable performance through training on massive datasets.<n>LLMs can exhibit concerning behaviors such as verbatim reproduction of training data rather than true generalization.<n>This paper introduces PEARL, a novel approach for detecting memorization in LLMs.
  arXiv  Detail & Related papers  (2025-05-05T20:42:34Z)
• Model Utility Law: Evaluating LLMs beyond Performance through Mechanism Interpretable Metric [99.56567010306807]
  Large Language Models (LLMs) have become indispensable across academia, industry, and daily applications.<n>One core challenge of evaluation in the large language model (LLM) era is the generalization issue.<n>We propose Model Utilization Index (MUI), a mechanism interpretability enhanced metric that complements traditional performance scores.
  arXiv  Detail & Related papers  (2025-04-10T04:09:47Z)
• How Post-Training Reshapes LLMs: A Mechanistic View on Knowledge, Truthfulness, Refusal, and Confidence [52.9442657690445]
  Post-training is essential for the success of large language models (LLMs)<n>We compare base and post-trained LLMs from four perspectives to better understand post-training effects.
  arXiv  Detail & Related papers  (2025-04-03T06:30:55Z)
• Self-training Large Language Models through Knowledge Detection [26.831873737733737]
  Large language models (LLMs) often necessitate extensive labeled datasets and training compute to achieve impressive performance across downstream tasks. This paper explores a self-training paradigm, where the LLM autonomously curates its own labels and selectively trains on unknown data samples. Empirical evaluations demonstrate significant improvements in reducing hallucination in generation across multiple subjects.
  arXiv  Detail & Related papers  (2024-06-17T07:25:09Z)
• Characterizing Truthfulness in Large Language Model Generations with Local Intrinsic Dimension [63.330262740414646]
  We study how to characterize and predict the truthfulness of texts generated from large language models (LLMs) We suggest investigating internal activations and quantifying LLM's truthfulness using the local intrinsic dimension (LID) of model activations.
  arXiv  Detail & Related papers  (2024-02-28T04:56:21Z)
• Self-Checker: Plug-and-Play Modules for Fact-Checking with Large Language Models [75.75038268227554]
  Self-Checker is a framework comprising a set of plug-and-play modules that facilitate fact-checking. This framework provides a fast and efficient way to construct fact-checking systems in low-resource environments.
  arXiv  Detail & Related papers  (2023-05-24T01:46:07Z)
• The Internal State of an LLM Knows When It's Lying [18.886091925252174]
  Large Language Models (LLMs) have shown exceptional performance in various tasks. One of their most prominent drawbacks is generating inaccurate or false information with a confident tone. We provide evidence that the LLM's internal state can be used to reveal the truthfulness of statements.
  arXiv  Detail & Related papers  (2023-04-26T02:49:38Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.