Latent Fact-Checking: Detecting Misinformation through Activation Engineering

• URL: http://arxiv.org/abs/2608.06417v3
• Date: Wed, 12 Aug 2026 19:11:59 GMT
• Title: Latent Fact-Checking: Detecting Misinformation through Activation Engineering
• Abstract summary: We introduce a misinformation detection framework grounded in activation engineering.<n>Our approach elicits a misinformation direction in the residual stream by contrasting activations from paired truthful and false statements.<n>We evaluate the method across 11 models on three fact-checking benchmarks: AVeriTeC, LIAR, and FACTors.
• Score: 1.3299946892361476
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The proliferation of misinformation online has driven demand for scalable detection systems. While most existing approaches rely on surface-level linguistic features or external knowledge retrieval, we examine truthfulness as a geometric property of a language model's representation space. We introduce a misinformation detection framework grounded in activation engineering, which leverages the latent geometry of transformer models. Our approach elicits a misinformation direction in the residual stream by contrasting activations from paired truthful and false statements, following the difference-in-means principle of Contrastive Activation Addition (CAA). At inference time, the last-token activation of an unseen claim is projected onto this direction, and the projected representation is fed to an Multilayer Perceptron (MLP) for classification. The procedure requires no fine-tuning of the backbone model, no external evidence retrieval, and no task-specific supervision beyond the contrastive pairs used to estimate the direction. We evaluate the method across 11 models from the Gemma, Llama, and Qwen families, ranging from 270M to 12B parameters, on three fact-checking benchmarks: AVeriTeC, LIAR, and FACTors. The falsehood direction is recoverable across model scales and architectural families, and last-token projection matches or surpasses zero-shot and few-shot prompting baselines on LIAR and FACTors, with the largest gains observed for smaller models. Performance on AVeriTeC is more limited, which we attribute to its evidence-grounded labeling scheme. These findings provide evidence that truthfulness is a structured, linearly separable concept in the latent space of pretrained language models, and point toward interpretability-driven misinformation detection as a practical complement to retrieval-based pipelines. The code is available on https://github.com/Malta-Lab/LaFaCt.

Related papers

• AnE: Pushing the Reasoning Frontier of Multimodal LLMs via Anchor Evolution [61.593935260052795]
  Post-training viaSupervised Fine-Tuning (SFT) and Reinforcement Learning (RL) is crucial for enhancing reasoning in Multimodal Large Language Models (MLLMs)<n>Existing paradigms often reach a performance bottleneck due to the limitations of static data.<n>We propose Anchor Evolution (AnE), a new paradigm that integrates truth-anchored data curation and model evolution.
  arXiv  Detail & Related papers  (2026-05-25T08:26:34Z)
• LiveFMBench: Unveiling the Power and Limits of Agentic Workflows in Specification Generation [75.05397479715576]
  Large language models (LLMs) and agents have shown promising progress, but their true capabilities and failure modes remain unclear.<n>We present the first systematic and contamination-aware study of LLM- and agent-based formal specification generation for C programs.
  arXiv  Detail & Related papers  (2026-05-02T11:31:33Z)
• LogitDynamics: Reliable ViT Error Detection from Layerwise Logit Trajectories [1.4610038284393168]
  We study error prediction in Vision Transformers (ViTs)<n>Motivated by internal-signal hallucination detection in large language models, we investigate whether similar depth-wise signals exist inViTs.<n>By attaching lightweight linear heads to intermediate layers, we extract features from the last L layers that capture both the logits of the predicted class and its top-K competitors.<n>A linear probe trained on these features predicts the error indicator.
  arXiv  Detail & Related papers  (2026-04-12T13:43:40Z)
• Watch the Weights: Unsupervised monitoring and control of fine-tuned LLMs [27.544312683007234]
  We introduce a new method for understanding, monitoring and controlling fine-tuned large language models (LLMs)<n>We demonstrate that the top singular of the weight difference between a fine-tuned model and its base model correspond to newly acquired behaviors.<n>For backdoored models that bypasses safety mechanisms when a secret trigger is present, our method stops up to 100% of attacks with a false positive rate below 1.2%.
  arXiv  Detail & Related papers  (2025-07-31T21:04:12Z)
• Improving Out-of-Distribution Detection via Dynamic Covariance Calibration [12.001290283557466]
  Out-of-Distribution (OOD) detection is essential for the trustworthiness of AI systems.<n>We argue that the influence of ill-distributed samples can be corrected by dynamically adjusting the prior geometry.<n>Our approach significantly enhances OOD detection across various models.
  arXiv  Detail & Related papers  (2025-06-11T05:05:26Z)
• Open-Set Deepfake Detection: A Parameter-Efficient Adaptation Method with Forgery Style Mixture [81.93945602120453]
  We introduce an approach that is both general and parameter-efficient for face forgery detection.<n>We design a forgery-style mixture formulation that augments the diversity of forgery source domains.<n>We show that the designed model achieves state-of-the-art generalizability with significantly reduced trainable parameters.
  arXiv  Detail & Related papers  (2024-08-23T01:53:36Z)
• SINDER: Repairing the Singular Defects of DINOv2 [61.98878352956125]
  Vision Transformer models trained on large-scale datasets often exhibit artifacts in the patch token they extract. We propose a novel fine-tuning smooth regularization that rectifies structural deficiencies using only a small dataset.
  arXiv  Detail & Related papers  (2024-07-23T20:34:23Z)
• Downstream-Pretext Domain Knowledge Traceback for Active Learning [138.02530777915362]
  We propose a downstream-pretext domain knowledge traceback (DOKT) method that traces the data interactions of downstream knowledge and pre-training guidance. DOKT consists of a traceback diversity indicator and a domain-based uncertainty estimator. Experiments conducted on ten datasets show that our model outperforms other state-of-the-art methods.
  arXiv  Detail & Related papers  (2024-07-20T01:34:13Z)
• ProtoVAE: Prototypical Networks for Unsupervised Disentanglement [1.6114012813668934]
  We introduce a novel deep generative VAE-based model, ProtoVAE, that leverages a deep metric learning Prototypical network trained using self-supervision. Our model is completely unsupervised and requires no priori knowledge of the dataset, including the number of factors. We evaluate our proposed model on the benchmark dSprites, 3DShapes, and MPI3D disentanglement datasets.
  arXiv  Detail & Related papers  (2023-05-16T01:29:26Z)
• ALSO: Automotive Lidar Self-supervision by Occupancy estimation [70.70557577874155]
  We propose a new self-supervised method for pre-training the backbone of deep perception models operating on point clouds. The core idea is to train the model on a pretext task which is the reconstruction of the surface on which the 3D points are sampled. The intuition is that if the network is able to reconstruct the scene surface, given only sparse input points, then it probably also captures some fragments of semantic information.
  arXiv  Detail & Related papers  (2022-12-12T13:10:19Z)
• Layer-wise Analysis of a Self-supervised Speech Representation Model [26.727775920272205]
  Self-supervised learning approaches have been successful for pre-training speech representation models. Not much has been studied about the type or extent of information encoded in the pre-trained representations themselves.
  arXiv  Detail & Related papers  (2021-07-10T02:13:25Z)

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.