Author

Tatiana Gaintseva

View on Semantic Scholar

1 paper indexed here

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.

Preprint Jul 2026

When Activation Oracles Learn Not to Read: Concept-Specific Blind Spots in Fine-Tuned Oracles

It is found that fine-tuned AOs can become concept-specific anti-readers: they selectively fail to recover the concept persistently present during their own training, raising a reliability concern for learned interpretability interfaces.

Tobias Bersia, Tatiana Gaintseva · 1 citation