finding
active
finding:mildly-poisoning-5-of-sft-and-dpo-data-induces-each-target-trait-interventions-substantially-reduce-trait-expression

Mildly poisoning 5% of SFT and DPO data induces each target trait; interventions substantially reduce trait expression

Fig. 3 on Llama-3.1-8B.

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.