Adaptive Mutual Distillation for Balanced Multi-Task Post-Training of Large Language Models

arXiv:2610.02856 · cs.CL · Submitted 2026-10-02 · Read on arXiv

cs.CL

Submitted: 2026-10-02

Updated: 2026-10-02

Code: https://github.com/open-compass/opencompass

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Distillation — 1× in this paper · explained in 2 episodes

Sources

• Massively Multilingual Neural Machine Translation in the Wild: Findings and Challenges
• Scaling Instruction-Finetuned Language Models
• The Llama 3 Herd of Models
• Distilling the Knowledge in a Neural Network
• Infinity Instruct: Scaling Instruction Selection and Synthesis to Enhance Language Models
• DoReMi: Optimizing Data Mixtures Speeds Up Language Model Pretraining
• DISC-LawLLM: Fine-tuning Large Language Models for Intelligent Legal Services
• Adaptive Multi-Teacher Knowledge Distillation with Meta-Learning

Related papers

• Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
• Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
• Subliminal Steering: Stronger Encoding of Hidden Signals
• MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
• The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
• Untangling the Mechanisms of Misleading Context in Medical Question Answering