# CLASS-IT: Conversational and Lecture-Aligned Small-Scale Instruction Tuning for BabyLMs

Source: [CLASS-IT: Conversational and Lecture-Aligned Small-Scale Instruction Tuning for BabyLMs](<https://www.sota2.com/research/paper/6902f0e33ef7ccd74e5e416e>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-31T05:04:16.982Z

Authors: Luca Capone, Alessandro Bondielli, Alessandro Lenci

Published: 2025-10-29T10:36:39.000Z

## Abstract

This work investigates whether small-scale LMs can benefit from instruction tuning. We compare conversational and question-answering instruction tuning datasets, applied either in a merged or sequential curriculum, using decoder-only models with 100M and 140M parameters. Evaluation spans both fine-tuning (SuperGLUE) and zero-shot (BLiMP, EWoK, WUGs, entity tracking, and psycholinguistic correlation) settings. Results show that instruction tuning yields small but consistent gains in fine-tuning scenarios, with sequential curricula outperforming merged data; however, improvements do not consistently transfer to zero-shot tasks, suggesting a trade-off between interaction-focused adaptation and broad linguistic generalization. These results highlight both the potential and the constraints of adapting human-inspired learning strategies to low-resource LMs, and point toward hybrid, curriculum-based approaches for enhancing generalization under ecological training limits.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2510.25364>)

[PDF](<https://arxiv.org/pdf/2510.25364.pdf>)
