Sensitivity of Small Language Models to Fine-tuning Data Contamination

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Scaria, Nicy, Kennedy, Silvester John Joseph, Subramani, Deepak
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912698097205248
author Scaria, Nicy
Kennedy, Silvester John Joseph
Subramani, Deepak
author_facet Scaria, Nicy
Kennedy, Silvester John Joseph
Subramani, Deepak
contents Small Language Models (SLMs) are increasingly being deployed in resource-constrained environments, yet their behavioral robustness to data contamination during instruction tuning remains poorly understood. We systematically investigate the contamination sensitivity of 23 SLMs (270M to 4B parameters) across multiple model families by measuring susceptibility to syntactic and semantic transformation types during instruction tuning: syntactic transformations (character and word reversal) and semantic transformations (irrelevant and counterfactual responses), each applied at contamination levels of 25\%, 50\%, 75\%, and 100\%. Our results reveal fundamental asymmetries in vulnerability patterns: syntactic transformations cause catastrophic performance degradation, with character reversal producing near-complete failure across all models regardless of size or family, while semantic transformations demonstrate distinct threshold behaviors and greater resilience in core linguistic capabilities. Critically, we discover a ``\textit{capability curse}" where larger, more capable models become more susceptible to learning semantic corruptions, effectively following harmful instructions more readily, while our analysis of base versus instruction-tuned variants reveals that alignment provides inconsistent robustness benefits, sometimes even reducing resilience. Our work establishes three core contributions: (1) empirical evidence of SLMs' disproportionate vulnerability to syntactic pattern contamination, (2) identification of asymmetric sensitivity patterns between syntactic and semantic transformations, and (3) systematic evaluation protocols for contamination robustness assessment. These findings have immediate deployment implications, suggesting that current robustness assumptions may not hold for smaller models and highlighting the need for contamination-aware training protocols.
format Preprint
id arxiv_https___arxiv_org_abs_2511_06763
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Sensitivity of Small Language Models to Fine-tuning Data Contamination
Scaria, Nicy
Kennedy, Silvester John Joseph
Subramani, Deepak
Computation and Language
Artificial Intelligence
Small Language Models (SLMs) are increasingly being deployed in resource-constrained environments, yet their behavioral robustness to data contamination during instruction tuning remains poorly understood. We systematically investigate the contamination sensitivity of 23 SLMs (270M to 4B parameters) across multiple model families by measuring susceptibility to syntactic and semantic transformation types during instruction tuning: syntactic transformations (character and word reversal) and semantic transformations (irrelevant and counterfactual responses), each applied at contamination levels of 25\%, 50\%, 75\%, and 100\%. Our results reveal fundamental asymmetries in vulnerability patterns: syntactic transformations cause catastrophic performance degradation, with character reversal producing near-complete failure across all models regardless of size or family, while semantic transformations demonstrate distinct threshold behaviors and greater resilience in core linguistic capabilities. Critically, we discover a ``\textit{capability curse}" where larger, more capable models become more susceptible to learning semantic corruptions, effectively following harmful instructions more readily, while our analysis of base versus instruction-tuned variants reveals that alignment provides inconsistent robustness benefits, sometimes even reducing resilience. Our work establishes three core contributions: (1) empirical evidence of SLMs' disproportionate vulnerability to syntactic pattern contamination, (2) identification of asymmetric sensitivity patterns between syntactic and semantic transformations, and (3) systematic evaluation protocols for contamination robustness assessment. These findings have immediate deployment implications, suggesting that current robustness assumptions may not hold for smaller models and highlighting the need for contamination-aware training protocols.
title Sensitivity of Small Language Models to Fine-tuning Data Contamination
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2511.06763