Domain Mixture Design via Log-Likelihood Differences for Aligning Language Models with a Target Model

arXiv:2603.16622 · cs.CL · Submitted 2026-03-17 · Read on arXiv

cs.CL

Submitted: 2026-03-17

Updated: 2026-08-31

Comments: EMNLP 2026 Findings

Code: https://github.com/shimo-lab/modelmap

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

Terminology

• Distillation — 22× in this paper · explained in 2 episodes
• Aggregation — 15× in this paper · explained in 1 episode
• Alignment — 15× in this paper · explained in 1 episode
• Knowledge Distillation — 13× in this paper · explained in 11 episodes
• Regularization — 3× in this paper · explained in 3 episodes
• Ablation — 2× in this paper · explained in 1 episode
• Adam — 2× in this paper · explained in 2 episodes
• Downstream Tasks — 2× in this paper · explained in 2 episodes
• Adaptation — 1× in this paper · explained in 1 episode
• Clustering — 1× in this paper · explained in 2 episodes
• Consistency — 1× in this paper · explained in 3 episodes
• Domain Adaptation — 1× in this paper · explained in 5 episodes
• Fine-Tuning — 1× in this paper · explained in 5 episodes
• Fisher Information — 1× in this paper · explained in 3 episodes
• Instruction Tuning — 1× in this paper · explained in 2 episodes
• Reinforcement Learning — 1× in this paper · explained in 4 episodes

Sources

• Why Less is More (Sometimes): A Theory of Data Curation
• The Pile: An 800GB Dataset of Diverse Text for Language Modeling
• Gemma: Open Models Based on Gemini Research and Technology
• Distilling the Knowledge in a Neural Network
• Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge
• CodeGemma: Open Code Models Based on Gemma
• Establishing a Scale for Kullback-Leibler Divergence in Language Models Across Various Settings
• LIMO: Less is More for Reasoning

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