finding
active
finding:reward-shaping-most-consistently-raises-harmful-refusals-while-retaining-dpo-accuracy-across-7-70b-models-e-g-tulu-70b-safety-0-957-harm-0-3

Reward shaping most consistently raises harmful refusals while retaining DPO accuracy across 7-70B models (e.g. Tulu 70B safety 0.957, harm 0.3%)

Fig. 10, Table 10.

Source paper

extracted_from
Anatomy of Post-Training: Using Interpretability to Characterize Data and Shape the Learning Signal
(2026) · Leon Bergen · Usha Bhalla · Sidharth Baskaran · Max Loeffler +13

Neighborhood — ranked by edge-count

Related by similarity (8)

cosine ≥ 0.65 · no typed edge

Entities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.