Multimodal alignment error in Prometheus after model update
Problem After upgrading the CLIP‑like vision‑language model to the version shipped with Prometheus v2.4.1, evaluation runs on multimodal benchmarks (e.g., COCO caption, Flickr30k) began producing divergent scores between the text and image modalities. Typical symptoms include: Cross‑modal retrieval MAP dropped ~15 % while text‑only metrics stayed flat (Production run on the COCO caption benchmark). ~3 % of … Read more