EmpathRAG / eval /run_adversarial.py

Commit History

Start v2 safety hardening
81deeef

MukulRay commited on

eval: save adversarial results at both t=0.50 and t=0.85, reset production threshold to 0.50 (Day 14)
9f77f5f

Mukul Rayana commited on

fix: threshold sweep — calibrate DeBERTa guardrail threshold, patch eval imports (Day 14)
d5f8958

Mukul Rayana commited on

feat: eval scripts — BM25 baseline, adversarial probes, BERTScore, RAGAS, Wilcoxon (Day 14)
78fc1e6

Mukul Rayana commited on