Skip to content

Author

Fabio James Fehr

2 papers 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.

#artificial intelligence Preprint Sep 2026

Building Legal Reward Models for Grounding and Abstention

Across general and legal contextual evaluation, it is found that contextual DPO improves grounded evaluation, but performance is sensitive to preference-data construction, which provides a reproducible foundation for constructing and evaluating grounded legal reward models in retrieval-augmented settings.

Rilton Franzone, Valentin Noël, Pu-Yu Wang et al. · 1 citation
#artificial intelligence Preprint Sep 2026

When Rubrics Fail: Hallucinations Reveal Blind Spots in Medical AI Evaluation

A taxonomy of medical hallucination types and a clinician-validated error-injection pipeline that creates matched correct and error-injected responses are developed, finding that more specific rubrics better distinguish correct from hallucinated responses.

Griffin Farrow, Lily Sijia Li, Jack Johnson et al. · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.