Skip to content
arXiv cs.CL · Papers

Assert, don't describe: Linguistic features that shift LLM reasoning about animal welfare

arXiv:2606.26104v1 Announce Type: new Abstract: Animal-welfare advocates produce a lot of writing, and increasingly that writing trains the language models that millions of people then ask about animal welfare. Using vocabulary-matched stance-contrast probes on a held-out animal-welfare benchmark, we measure how each o