ENTITY SFT retention

SFT retention

PulseAugur coverage of SFT retention — every cluster mentioning SFT retention across labs, papers, and developer communities, ranked by signal.

Total · 30d

1

1 over 90d

Releases · 30d

0

0 over 90d

Papers · 30d

1

1 over 90d

TIER MIX · 90D

TOPICS

SENTIMENT · 30D

1 day(s) with sentiment data

RECENT · PAGE 1/1 · 1 TOTAL

TOOL · CL_349623 · Nov 4 · 13:18

Qwen3.5-4B model shows task-selective capability loss with increased reward margin

A study on the Qwen3.5-4B model, using Direct Preference Optimization with SFT retention, found that increasing the reward margin led to a graded and task-selective loss of capabilities. Specifically, the model's abilit…