SpeciesCAI: Constitutional AI Specificity in Animal Welfare Fine-Tuning

Abstract

A constitution can endorse a value without ever stating what that value implies a model should do differently: the commitment stays unoperationalized. We present SpeciesCAI, a preliminary ablation that isolates making an existing commitment explicit from adding genuinely new value content, using animal welfare as the test domain. We build three constitutions: Base (unmodified), Meso (eight sentence-level edits operationalizing an existing welfare commitment), and Macro (Meso plus a new, inherently welfare-focused subsection). We fine-tune Llama 3.1 8B Instruct at each level on SL-CAI critique-revision data, evaluating on ANIMA for moral reasoning and MMLU/IFEval for capability retention. Base→Meso transmits: a dose-ordered rise in welfare-substantive reasoning traceable from constitution to training data to model output, alongside a calibration cost resembling the documented helpful-harmless tradeoff and a partial, edit-specific capability cost. Macro's effect is uneven rather than a clean extension of Meso's, with Epistemic Humility taking the largest hit of any comparison in the study. This is a preliminary draft, single-model ablation, and we flag limitations throughout.