SOURCE-LINKED INTELLIGENCE
When Do Language-Grounded Explanations Help? A Graph-Bottleneck for Farm Monitoring Interpretable Sheep Facial Pain
Automated pain recognition from facial expression could make continuous welfare assessment practical in sheep, but adoption depends on trust: a stockperson cannot act on a score that arrives without justification. We ground a model in the Sheep Pain Facial Expression Scale (SPFES) by letting each detected facial region attend over text embeddings of the clinical descriptors and then test whether the resulting explanations mean anything. They do not. Ablating an entire descriptor changes the predicted logit by about $10^{-4}$, and the most-attended cue agrees with the predicted pain level in on
Read original source ↗ Open in workspace
- recordType
- paper
- region
- Global
Evidence & attribution
- arXiv · AI, language, vision and robotics · 2026-09-17T14:08:16.000Z
- arXiv · Artificial Intelligence · 2026-09-17T14:08:16.000Z
First collected: 2026-09-19T20:26:32.566Z. This is not the publication date.