ChemOPD: Multi-Teacher On-Policy Distillation for Multi-Task Chemical Reasoning
cs.LG, cs.CL
Submitted: 2026-09-27
Updated: 2026-09-27
License: http://creativecommons.org/licenses/by/4.0/
The gist: Large language models are increasingly expected to support diverse chemical reasoning capabilities within a unified model.
Terminology
Abstract
Large language models are increasingly expected to support diverse chemical reasoning capabilities within a unified model. One approach is to develop specialized capabilities separately and consolidate them through multi-teacher on-policy distillation, but this raises two questions: how should specialization be organized, and how should specialist guidance be integrated? We introduce ChemOPD, which addresses both. We estimate task affinities from supervised fine-tuning gradients and solve a constrained mixed-integer program(MIP) to construct partially overlapping specialist groups. During distillation, we retain a generalist teacher trained on all tasks so that specialist guidance supplements rather than replaces its supervision. Our anchor-residual objective gradually increases the routed specialist's contribution on student-generated responses. On ChemCoTBench, affinity-guided specialization produces task-dependent gains over the generalist teacher and improves several capabilities beyond semantic task grouping. Yet stronger teacher-side performance does not automatically yield stronger students: with the same specialists and routes, anchor-residual OPD improves most reported metrics over specialist-only distillation and realizes a larger share of the available teacher gains. These results highlight specialization and capability integration as connected but distinct design problems in chemical reasoning.
Sources
- Counteraction-Aware Multi-Teacher On-Policy Distillation for General Capability Recovery with Domain Preservation
- Adapting Auxiliary Losses Using Gradient Similarity
- Distilling the Knowledge in a Neural Network
- Learning Task Grouping and Overlap in Multi-task Learning
- Rethinking On-Policy Distillation of Large Language Models: Phenomenology, Mechanism, and Recipe
- Enhancing Chemical Reaction and Retrosynthesis Prediction with Large Language Model and Dual-task Learning
- MOPD: Multi-Teacher On-Policy Distillation for Capability Integration in LLM Post-Training
- A Survey of On-Policy Distillation for Large Language Models
- Towards Principled Task Grouping for Multi-Task Learning
- MAD-OPD: Breaking the Ceiling in On-Policy Distillation via Multi-Agent Debate
- A Survey on Knowledge Distillation of Large Language Models
- TIP: Token Importance in On-Policy Distillation
- Qwen3 Technical Report
- LlaSMol: Advancing Large Language Models for Chemistry with a Large-Scale, Comprehensive, High-Quality Instruction Tuning Dataset
- ChemLLM: A Chemical Large Language Model
- MolEmb: Multimodal Large Language Models Can Be Strong Molecular Embedding Models
- ChemDFM-R: A Chemical Reasoning LLM Enhanced with Atomized Chemical Knowledge
- DanceOPD: On-Policy Generative Field Distillation
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks