What do a language model's hidden states say about the organization of a single text? From one forward pass, without training, we score every token position on two properties.
Summary generated by The Flow from the publisher's feed. The full article lives at Hugging Face Trending Papers.
arXiv:2510. 04120v2 Announce Type: replace-cross Abstract: Large language models (LLMs) achieve strong performance on metaphor detection and interpretation tasks, yet it remains unclear what such behavioral success reveals about metaphor processing.
arXiv:2607. 16741v1 Announce Type: new Abstract: B\"urger et al.
arXiv:2607. 10248v1 Announce Type: cross Abstract: Language builds discourse contexts other than the actual: a painting, a belief, a memory, a hypothetical.
arXiv:2608. 04021v1 Announce Type: cross Abstract: Cloze-style probes that vary how often a target token appears implicitly assume that more copies of a target affect prediction the same way regardless of where the readout slot sits.
arXiv:2607. 03598v1 Announce Type: cross Abstract: When a person shares something with a language model, the model often answers the surface of the message rather than what the sender was doing by sending it: share a finished project and it critiques the code; share a raw late-night line and it runs a wellness check.
arXiv:2606. 07555v1 Announce Type: cross Abstract: Glossaries, technical specifications, and system prompts routinely ask language models to use familiar words in unfamiliar ways.