Data filtering barely curbs LLM misbehaviors beyond refusal
Neel Nanda’s MATS 10.0 team discovered that standard data‑filtering methods barely change LLM fine‑tuning behaviors like liberal framing or “your feelings are valid” statements. Only refusal rates respond noticeably. This suggests many undesirable traits are entrenched in pre‑trained personas, limiting the effectiveness of post‑hoc data curation.