Cosine Similarity as Logits?: A Scalable Knowledge Probe Using Embedding Vectors from Generative Language Models

Tomoyuki Jinno, Kazuki Hayashi, Yusuke Sakai, Hidetaka Kamigaito, Taro Watanabe


Anthology ID:
2026.eacl-long.382
Volume:
Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)
Month:
March
Year:
2026
Address:
Rabat, Morocco
Editors:
Vera Demberg, Kentaro Inui, Lluís Marquez
Venue:
EACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
8188–8200
Language:
URL:
https://preview.aclanthology.org/ingest-eacl/2026.eacl-long.382/
DOI:
Bibkey:
Cite (ACL):
Tomoyuki Jinno, Kazuki Hayashi, Yusuke Sakai, Hidetaka Kamigaito, and Taro Watanabe. 2026. Cosine Similarity as Logits?: A Scalable Knowledge Probe Using Embedding Vectors from Generative Language Models. In Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers), pages 8188–8200, Rabat, Morocco. Association for Computational Linguistics.
Cite (Informal):
Cosine Similarity as Logits?: A Scalable Knowledge Probe Using Embedding Vectors from Generative Language Models (Jinno et al., EACL 2026)
Copy Citation:
PDF:
https://preview.aclanthology.org/ingest-eacl/2026.eacl-long.382.pdf