Mitigating Shortcut Learning through Change-Aware Losses for ARC-AGI

Learning a new task from a handful of demonstrations is a skill often assumed to require the scale of large language models or test-time training on the demonstrations themselves, while purely in-context, non-LLM approaches have received far less attention. We find that small models trained for this setting are prone to shortcuts: since most output pixels in ARC-AGI are identical to the input, a uniform per-pixel cross-entropy biases the model toward leaving cells unchanged and erasing content, rather than learning the transformation. We propose a change-aware loss that up-weights the pixels that change and balances the loss across colors. In controlled comparisons, it raises accuracy on changing pixels from 52.3% to 59.8% at equal training, while also increasing the number of tasks solved. Using this loss, we train the Change-Aware In-Context Learner (CAIL), a 23M-parameter model that achieves 1.25% on the ARC-AGI-2 public evaluation with \$8 worth of training compute and \$0.0003 per task at inference, without using test-time training.

Authors

Publication Details

Journal
Zenodo (CERN European Organization for Nuclear Research)
Published
2026-11-14
DOI
https://doi.org/10.5281/zenodo.24223159
Primary Topic
Domain Adaptation and Few-Shot Learning
Type
preprint
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
preprint

Mitigating Shortcut Learning through Change-Aware Losses for ARC-AGI

Daniel Caballero
Zenodo (CERN European Organization for Nuclear Research)
Domain Adaptation and Few-Shot Learning
preprint

Mitigating Shortcut Learning through Change-Aware Losses for ARC-AGI

Daniel Caballero
preprint en

Abstract

Learning a new task from a handful of demonstrations is a skill often assumed to require the scale of large language models or test-time training on the demonstrations themselves, while purely in-context, non-LLM approaches have received far less attention. We find that small models trained for this setting are prone to shortcuts: since most output pixels in ARC-AGI are identical to the input, a uniform per-pixel cross-entropy biases the model toward leaving cells unchanged and erasing content, rather than learning the transformation. We propose a change-aware loss that up-weights the pixels that change and balances the loss across colors. In controlled comparisons, it raises accuracy on changing pixels from 52.3% to 59.8% at equal training, while also increasing the number of tasks solved. Using this loss, we train the Change-Aware In-Context Learner (CAIL), a 23M-parameter model that achieves 1.25% on the ARC-AGI-2 public evaluation with \$8 worth of training compute and \$0.0003 per task at inference, without using test-time training.

Zenodo (CERN European Organization for Nuclear Research)
Domain Adaptation and Few-Shot Learning
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon