Skip to content

Author

Kasra Mazaheri

We have 1 of 3 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.

Preprint Aug 2026

Prior Audit-Repair Context Shifts LLM Verifier Thresholds Toward Leniency

Measuring false alarms on human-verified-correct ProcessBench traces with the present task held byte-identical, it is found that a completed audit ->repair episode already in the model's context lowers false alarms in 15 of 15 model x wording combinations.

Parsa Mazaheri, Kasra Mazaheri · 0 citations