English

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

Computation and Language 2026-04-30 v1 Artificial Intelligence

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 of ten linguistic features changes Llama-3.2-1B's preference for pro-animal-welfare reasoning when used as fine-tuning data. Eight of the ten features produce statistically significant shifts. Seven move the model toward stronger pro-animal-welfare reasoning: assertive certainty, explicit moral vocabulary, emotion words, evaluative claims, narrative structure, depicted harm severity, and immediate temporal framing. Two move it the other way: hedged language and concrete sensory description both dilute the pro-animal-welfare stance. First-person perspective has no statistically significant effect. The practical recommendation for anyone writing animal-welfare text that may end up in LLM training corpora: assert a position rather than describe a scene neutrally. The features that shift the model are the ones that make the writer's position explicit; the features that dilute it hold animal-welfare content but withhold stance.

Keywords

Cite

@article{arxiv.2606.26104,
  title  = {Assert, don't describe: Linguistic features that shift LLM reasoning about animal welfare},
  author = {Jasmine Brazilek and Harper Dunn},
  journal= {arXiv preprint arXiv:2606.26104},
  year   = {2026}
}