Story

arxiv_cs_cl ยท Nov 3, 2026 ยท paper

Source brief

Suppressing Misaligned Behaviors in Language Models, Durably

arxiv.orgNov 3, 2026
original source linked

In brief

Undesired model behaviors can emerge or re-emerge at any stage of training. Once observed, how effectively can we suppress them? To study this question, we first construct two model organisms--language models delibera...

Feed lens
eval

Continue reading

Read the original at arxiv.org โ†’Open in live feedRead that dayโ€™s brief

Earlier in this thread 1 item