Value steering should change an LLM's normative priorities while preserving the scenario, facts, and task constraints underlying its answer. Conventional activation edits often change both. We introduce an editable semantic-value interface on frozen residual states, with a one-way semantic-to-value pathway that grounds...
Jia-Le Dai, Hong-Can Deng, Liu-Xian Ma et al.· 0 citations
VITA (Value-Informed Semantic Trust Arbitration), a learned seven-field appraisal interface that conditions modality arbitration on concerns, event relations, and expression conditions while retaining a joint-evidence residual, is introduced.
Jia-Le Dai, Liu-Xian Ma, Xiao-Ke Niu et al.· 0 citations
This work introduces Harness-Zero, which enables harness distillation through agent-as-harness, and shows that for frontier LLMs using the same evolved harness, agent-as-harness outperforms code-as-harness.
Hao-Ran Ye, Yuxing Lu, Hao-Nan Dong et al.· 5 citations· ⚡1
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.