arXiv:2601. 06599v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) often encode whether a statement is true as a vector in their residual stream activations.
Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.
arXiv:2607. 16741v1 Announce Type: new Abstract: B\"urger et al.
The paper investigates how truth representations in small language models are structured. Using a training‑free axis derived from the dominant singular vector of hidden‑state differences between true and false minimal pairs, the authors evaluate 14 models across six architectural families, including Mixture‑of‑Experts. The study examines whether a single direction captures truth, which components contribute, and how this applies to categories with computed truth values.
arXiv:2606. 15821v1 Announce Type: cross Abstract: Recent advances in large language models (LLMs) have produced many specialized multimodal LLMs (MLLMs) that share common foundational LLMs, forming distinct model lineages.
arXiv:2604.03754v2 Announce Type: replace-cross Abstract: Large language models (LLMs) have been shown to encode truth of statements in their activation space along a linear truth direction. Previous...
arXiv:2608. 06417v1 Announce Type: new Abstract: The proliferation of misinformation online has driven demand for scalable detection systems.
arXiv:2610.00910v1 Announce Type: cross Abstract: Human reasoning depends on how objects are related within propositions. \textit{How do relations organize the language representations of contextual...