Semantically Anchored Geometric Coverage (SAGC), a framework for reshaping representation geometry using LLM-generated macro-intent labels as semantic anchors for dense micro-context representations, is proposed, using macro-intent anchors to constrain dense-space exploration toward high-level algorithmic structure.
Ke Zhang, Zixian Huang, Gong Cheng· Proceedings of the 35th ACM...· 0 citations
Diversity-driven data selection offers a scalable way to reduce code instruction-tuning costs, yet it relies on a fragile assumption: geometric spread in representation space should correspond to training-useful semantic coverage. In code data selection, our diagnosis reveals a geometric bias behind this assumption: de...
Ke Zhang, Zixian Huang, Gong Cheng· Proceedings of the 35th ACM...· 0 citations
Teacher takeover in on-policy distillation (OPD) can produce incorrect responses even when the student and teacher independently answer the same problem correctly, a failure we quantify using Collaboration Failure Rate (CFR). To address it, we propose Contextual Digest for On-Policy Distillation (CD-OPD). CD-OPD struct...
Ming-Yuan Li, Yu-Cheng Li, Xiaxia Wang et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.