Author

C. Camassa

h-index 3 View on Semantic Scholar

We have 2 of 11 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

BankGPT: the use of large language models in official communications 1

No overall preference is indicated between human and machine-generated summaries; however, experts with greater familiarity with the Bulletin and higher educational attainment showed a marked preference for the official summaries.

Claudia Biancotti, C. Camassa, Marco Fruzzetti et al. · 0 citations

#artificial intelligence May 2026

Do as I Say, Not as I Do: Instruction-Induction Conflict in LLMs

It is suggested that instruction-following remains brittle under induction pressure even for otherwise capable models, and that output diversity, rather than semantic engagement with the input, is the primary factor predicting robustness.

C. Camassa, Derek Shiller · arXiv.org · 0 citations