SEAD: Competence-Aware On-Policy Distillation via Entropy-Guided Supervision
A new arXiv paper proposes SEAD, which uses entropy as a unified probe to address the issue of teacher supervision quality varying with student competence in on-policy distillation (OPD) at three scales: token partitioning, KL divergence annealing, and curriculum learning. It achieves a +4.8% average accuracy improvement on OLMo-3.
[2606.28562] SEAD: Competence-Aware On-Policy Distillation via Entropy-Guided Supervision
[Submitted on 26 Jun 2026]
Title:SEAD: Competence-Aware On-Policy Distillation via Entropy-Guided Supervision
View a PDF of the paper titled SEAD: Competence-Aware On-Policy Distillation via Entropy-Guided Supervision, by Chia-Hsuan Lee and 6 other authors
View PDF HTML (experimental)
Abstract:On-policy distillation (OPD) has a property absent in offline distillation and RL: teacher supervision quality depends on student competence. Incoherent rollouts yield noisy gradients; already-mastered tokens yield redundant ones. This creates waste at three scales (tokens, training phases, and prompts) yet existing methods supervise uniformly. We introduce SEAD, which uses entropy as a unified probe of this competence-dependent degradation at three scales: (1) joint teacher-student entropy partitions tokens into zones receiving tailored divergences or zero gradient (approx. 50% skipped); (2) a cosine schedule anneals from forward to reverse KL as competence grows; (3) a competence-gated curriculum introduces prompts easy-to-hard. These components are symbiotically necessary: token selection requires coherent rollouts (curriculum), annealing requires monotonic improvement (also curriculum). On OLMo-3 (7B to 32B), SEAD achieves +4.8 avg accuracy over vanilla OPD across six math benchmarks, with ablations confirming super-additive interactions.
Subjects:
Computation and Language (cs.CL)
Cite as: arXiv:2606.28562 [cs.CL]
(or arXiv:2606.28562v1 [cs.CL] for this version)
https://doi.org/10.48550/arXiv.2606.28562
arXiv-issued DOI via DataCite (pending registration)
Submission history
From: Chia-Hsuan Lee [view email] [v1] Fri, 26 Jun 2026 19:41:02 UTC (463 KB)
Full-text links:
Access Paper:
View a PDF of the paper titled SEAD: Competence-Aware On-Policy Distillation via Entropy-Guided Supervision, by Chia-Hsuan Lee and 6 other authors
View PDF
HTML (experimental)
TeX Source
view license
Current browse context:
cs.CL
new | recent | 2026-06
Change to browse by:
cs
References & Citations
NASA ADS
Google Scholar
Semantic Scholar
Loading...
Data provided by:
Bibliographic Tools
Bibliographic and Citation Tools
Bibliographic Explorer Toggle
Bibliographic Explorer (What is the Explorer?)
Connected Papers Toggle
Connected Papers (What is Connected Papers?)
Litmaps Toggle
Litmaps (What is Litmaps?)
scite.ai Toggle
scite Smart Citations (What are Smart Citations?)
Code, Data, Media
Code, Data and Media Associated with this Article
alphaXiv Toggle
alphaXiv (What is alphaXiv?)
Links to Code Toggle
CatalyzeX Code Finder for Papers (What is CatalyzeX?)
DagsHub Toggle
DagsHub (What is DagsHub?)
GotitPub Toggle
Gotit.pub (What is GotitPub?)
Huggingface Toggle
Hugging Face (What is Huggingface?)
ScienceCast Toggle
ScienceCast (What is ScienceCast?)
Demos
Demos
Replicate Toggle
Replicate (What is Replicate?)
Spaces Toggle
Hugging Face Spaces (What is Spaces?)
Spaces Toggle
TXYZ.AI (What is TXYZ.AI?)
Related Papers
Recommenders and Search Tools
Link to Influence Flower
Influence Flower (What are Influence Flowers?)
Core recommender toggle
CORE Recommender (What is CORE?)
Author
Venue
Institution
Topic
About arXivLabs
arXivLabs: experimental projects with community collaborators
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)