DUET: Dual-Teacher On-Policy Distillation via Same-Weight Disagreement for Prohibition Compliance

[2608.14644] DUET: Dual-Teacher On-Policy Distillation via Same-Weight Disagreement for Prohibition Compliance Skip to main content Search Submit Donate Log in Search arXiv Press Enter to search · Advanced search Computer Science > Machine Learning arXiv:2608.14644 (cs) [Submitted on 29 Jul 2026] Title: DUET: Dual-Teacher On-Policy Distillation via Same-Weight Disagreement for Prohibition Compliance Authors: Zihan Li , Feifei Li , Wenhui Que View a PDF of the paper titled DUET: Dual-Teacher On-Policy Distillation via Same-Weight Disagreement for Prohibition Compliance, by Zihan Li and 2 other authors View PDF HTML (experimental) Abstract: Real-world LLM deployments increasingly rely on runtime-injected prohibitions--enterprise policies, PII redlines, tool boundaries--that vary per request and per tenant. Conventional post-training is structurally ill-suited: SFT hides the violation signal in compliant labels, and DPO's sequence-level preferences mismatch token-localized violations. We propose DUET, a token-selective on-policy distillation method for prohibition compliance. DUET pairs a teacher that sees the prohibition (positive) with an identical-weight teacher that does not (negative). Because the two teachers differ only in prohibition visibility, their per-token disagreement isolates the prohibition's causal effect--yielding a clean supervision signal uncontaminated by model capacity or mismatch. This disagreement drives two complementary mechanisms: signal cleaning, which discards agreement tokens as redundant or prefix-corrupted, and preference-directed learning, which pushes the student away from the negative teacher and toward the positive one at token granularity, embedding DPO-style optimization directly into OPD without offline preference data. We construct an industrial Prohibition-Compliance benchmark spanning five task families covering explicit-refusal, paraphrase robustness, and over-refusal. Across 1.5B-8B Qwen variants, DUET achieves 72.3-85.2% violation compliance while preserving 88-93% normal utility, dramatically outperforming teacher model and other distillation baselines. External evaluation on SysBench confirms improved safety alignment with minimal degradation on GSM8K and MATH-500. Subjects: Machine Learning (cs.LG) ; Computation and Language (cs.CL) Cite as: arXiv:2608.14644 [cs.LG] (or arXiv:2608.14644v1 [cs.LG] for this version) https://doi.org/10.48550/arXiv.2608.14644 Focus to learn more arXiv-issued DOI via DataCite Submission history From: Zihan Li [ view email ] [v1] Wed, 29 Jul 2026 07:17:43 UTC (173 KB) Full-text links: Access Paper: View a PDF of the paper titled DUET: Dual-Teacher On-Policy Distillation via Same-Weight Disagreement for Prohibition Compliance, by Zihan Li and 2 other authors View PDF HTML (experimental) TeX Source view license Current browse context: cs.LG < prev | next > new | recent | 2026-08 Change to browse by: cs cs.CL References & Citations NASA ADS Google Scholar Semantic Scholar export BibTeX citation Loading... BibTeX formatted citation × loading... Data provided by: Bookmark 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? ) IArxiv recommender toggle IArxiv Recommender ( What is IArxiv? ) 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? ) We gratefully acknowledge support from our major funders , member institutions , , and all contributors. About · Help · Contact · Subscribe · Copyright · Privacy · Accessibility · Operational Status (opens in new tab) Major funding support from

Related documents

• CLOOPD: Closing the Learner Loop in On-Policy Distillation#1050326
• Know When to Stop, Where to Restart: Accelerating Multi-Turn Agentic On-Policy Distillation#1084573
• RE-0: Verified Recursive Improvement of Embodied Code-as-Policy Agents through Local On-Policy Distillation#1116747
• Estimate, Don't Imitate: Reusing Differentiable State-Based Policies for Visuomotor Control#1119091
• Pyramid-based Bayesian modeling for high-resolution behavioral analysis.#342380