Metraipolis › archive › dc_2b32a50d41f2
Structuring Semantic Embeddings for Principle Evaluation: A Prototype-Guided Contrastive Learning Approach — arXiv:2608.15224
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.15224
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-18T19:40:09.102Z
- SHA-256 of the archived text
255391e1046065f1943dc5dc6db60f1275ea19071b053f236f01158067b65f2c- Stable URL of this page
https://metraipolis.com/documento/dc_2b32a50d41f2
How to cite
Structuring Semantic Embeddings for Principle Evaluation: A Prototype-Guided Contrastive Learning Approach — arXiv:2608.15224 — arXiv (en), https://arxiv.org/abs/2608.15224 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_2b32a50d41f2 (Metraipolis archive dc_2b32a50d41f2, sha256 255391e1046065f1943dc5dc6db60f1275ea19071b053f236f01158067b65f2c)
BibTeX
@misc{dc2b32a50d41f2,
title = {Structuring Semantic Embeddings for Principle Evaluation: A Prototype-Guided Contrastive Learning Approach — arXiv:2608.15224},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.15224},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_2b32a50d41f2; sha256 255391e1046065f1943dc5dc6db60f1275ea19071b053f236f01158067b65f2c},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.15224. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Reliable post-hoc evaluation asks whether already generated text satisfies a target criterion after generation. In this paper we study a focused frozen-embedding setting using principle-evaluation proxy tasks: toxicity detection, fine-grained emotion categorization, and ordinal review rating. General-purpose text embeddings are widely deployed for such tasks, but broad semantic similarity can place semantically similar yet task-distinct examples in overlapping regions of the representation space. We introduce Prototype-Guided Contrastive Learning (PGCL), a prototype-guided geometric regularization module built on top of frozen text embeddings. The module combines a semantic stream, a prototype-anchor attention stream, supervised contrastive learning, offset-based prototype-margin regularization, and stream regularization to produce a compact task-adapted representation without updating the base encoder. Controlled experiments show that PGCL improves over raw frozen embeddings on all three datasets and gives the clearest direct-baseline margin on AmazonReviews, while remaining competitive with strong direct frozen metric-learning baselines on GoEmotions and ToxicComment. We also add supervised residual-adapter, encoder-LoRA, full fine-tuning, objective ablation, sensitivity, and fully logged few-shot LLM protocol diagnostics to define the boundary of the claim. The theoretical analysis is revised as a sufficient-condition account for prototype-margin behavior under explicit assumptions in the prototype-mapping space, rather than as an unconditional training or final-embedding separation guarantee. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-18 in cs.LG). Categorie arXiv: Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2608.15224 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-18T19:02:44.080Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-08-18?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).