Metraipolis › archive › dc_cc33876c3ba8
Latent Fact-Checking: Detecting Misinformation through Activation Engineering — arXiv:2608.06417
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.06417
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-19T09:47:04.381Z
- SHA-256 of the archived text
99695cb5be4b8842c30e08c5402ce54b36d6c8378b9fc506a0d85129970e5a09- Stable URL of this page
https://metraipolis.com/documento/dc_cc33876c3ba8
How to cite
Latent Fact-Checking: Detecting Misinformation through Activation Engineering — arXiv:2608.06417 — arXiv (en), https://arxiv.org/abs/2608.06417 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_cc33876c3ba8 (Metraipolis archive dc_cc33876c3ba8, sha256 99695cb5be4b8842c30e08c5402ce54b36d6c8378b9fc506a0d85129970e5a09)
BibTeX
@misc{dccc33876c3ba8,
title = {Latent Fact-Checking: Detecting Misinformation through Activation Engineering — arXiv:2608.06417},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.06417},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_cc33876c3ba8; sha256 99695cb5be4b8842c30e08c5402ce54b36d6c8378b9fc506a0d85129970e5a09},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.06417. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
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 this https URL . Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-10 in cs.CL). Categorie arXiv: Machine Learning (cs.LG) ; Computation and Language (cs.CL). Pagina del lavoro: https://arxiv.org/abs/2608.06417 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-19T09:46:37.253Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-08-10?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).