arXiv:2602. 08159v2 Announce Type: replace Abstract: When a language model asserts that "the capital of Australia is Sydney," does it know this is wrong?
arXiv:2608. 06417v1 Announce Type: new Abstract: The proliferation of misinformation online has driven demand for scalable detection systems.
arXiv:2606. 01060v1 Announce Type: cross Abstract: Preference alignment has substantially improved the observable behavior of large language models, yet it remains unclear what alignment changes internally.
arXiv:2606. 07537v1 Announce Type: cross Abstract: Large language models hallucinate--producing fluent, confident, factually wrong outputs--with a consistency that persists across generations and scales.
arXiv:2607. 16741v1 Announce Type: new Abstract: B\"urger et al.
arXiv:2607. 04222v1 Announce Type: new Abstract: Interpretability methods aim to reveal the features represented inside large language models (LLMs).
Warning: This paper studies stereotypes and biases, and contains potentially disturbing examples, used for illustration purposes only. Our findings should not be interpreted as an argument against alignment.
arXiv:2607. 18305v1 Announce Type: cross Abstract: Some limits on what language models know are not gaps in data coverage but structural properties of learning from text.
arXiv:2605. 05686v3 Announce Type: replace Abstract: Language models draw on two knowledge sources: facts baked into weights (parametric memory, PM) and information in context (working memory, WM).
arXiv:2606. 17389v1 Announce Type: cross Abstract: Multimodal Foundation Models are increasingly used as reasoning agents, making reliability, knowing when a model may hallucinate, critical.
arXiv:2606. 02907v1 Announce Type: cross Abstract: Linear probing of large language model (LLM) hidden states is widely used to claim that models learn distinct representations for different reasoning types.
arXiv:2607. 19355v1 Announce Type: new Abstract: LLMs are increasingly used with external knowledge sources like the internet.
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.