Didactic to Constructive: Turning Expert Solutions into Learnable Reasoning

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Mendes, Ethan, Park, Jungsoo, Ritter, Alan
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914301726425088
author Mendes, Ethan
Park, Jungsoo
Ritter, Alan
author_facet Mendes, Ethan
Park, Jungsoo
Ritter, Alan
contents Improving the reasoning capabilities of large language models (LLMs) typically relies either on the model's ability to sample a correct solution to be reinforced or on the existence of a stronger model able to solve the problem. However, many difficult problems remain intractable for even current frontier models, preventing the extraction of valid training signals. A promising alternative is to leverage high-quality expert human solutions, yet naive imitation of this data fails because it is fundamentally out of distribution: expert solutions are typically didactic, containing implicit reasoning gaps intended for human readers rather than computational models. Furthermore, high-quality expert solutions are expensive, necessitating generalizable sample-efficient training methods. We propose Distribution Aligned Imitation Learning (DAIL), a two-step method that bridges the distributional gap by first transforming expert solutions into detailed, in-distribution reasoning traces and then applying a contrastive objective to focus learning on expert insights and methodologies. We find that DAIL can leverage fewer than 1000 high-quality expert solutions to achieve 10-25% pass@k gains on Qwen2.5-Instruct and Qwen3 models, improve reasoning efficiency by 2x to 4x, and enable out-of-domain generalization.
format Preprint
id arxiv_https___arxiv_org_abs_2602_02405
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Didactic to Constructive: Turning Expert Solutions into Learnable Reasoning
Mendes, Ethan
Park, Jungsoo
Ritter, Alan
Machine Learning
Artificial Intelligence
Improving the reasoning capabilities of large language models (LLMs) typically relies either on the model's ability to sample a correct solution to be reinforced or on the existence of a stronger model able to solve the problem. However, many difficult problems remain intractable for even current frontier models, preventing the extraction of valid training signals. A promising alternative is to leverage high-quality expert human solutions, yet naive imitation of this data fails because it is fundamentally out of distribution: expert solutions are typically didactic, containing implicit reasoning gaps intended for human readers rather than computational models. Furthermore, high-quality expert solutions are expensive, necessitating generalizable sample-efficient training methods. We propose Distribution Aligned Imitation Learning (DAIL), a two-step method that bridges the distributional gap by first transforming expert solutions into detailed, in-distribution reasoning traces and then applying a contrastive objective to focus learning on expert insights and methodologies. We find that DAIL can leverage fewer than 1000 high-quality expert solutions to achieve 10-25% pass@k gains on Qwen2.5-Instruct and Qwen3 models, improve reasoning efficiency by 2x to 4x, and enable out-of-domain generalization.
title Didactic to Constructive: Turning Expert Solutions into Learnable Reasoning
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2602.02405