cs.CLNov 18, 2026

When Does Continual Pre-Training Help? A Controlled Study of Dialectal Adaptation for Québec French

Authors: Eeham Khan, Richard Khoury, Leila Kosseim

Organizations: CLaC Lab, Department of Computer Science and Software Engineering, Concordia University · GRAAL, Department of Computer Science and Software Engineering, Université Laval

Abstract

Continual pre-training (CPT) is widely used to adapt pretrained language models to dialectal and non-standard language varieties, yet it remains unclear when this additional training is necessary, what drives its benefits, and whether aggregate evaluation scores adequately capture its effects. In this paper, we present a controlled study of CPT for Québec French language understanding across nine LLMs spanning different families and scales. Using a budget-matched protocol of 30M tokens per experiment, our results show that the benefit of CPT depends strongly on the starting model's existing competence in the target variety. When CPT is beneficial, the improvements are driven more by corpus composition than by data volume, with literary text accounting for most of the gain. Paired Québec and standard French evaluations further show that CPT primarily improves expression comprehension rather than grammatical competence, and that corpus register determines which regional expressions are acquired. These gains also involve capability-specific trade-offs, including declines in reading comprehension that aggregate scores can conceal. Overall, these findings show that CPT for dialectal adaptation should not be treated as a uniformly beneficial default. Instead, adaptation strategies should begin with a careful assessment of the base model's existing competence, accompanied by source-level data analysis and task-level evaluation.

Figures & tables

Appendix figures & tables3 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

Aug 6, 2026

Different Perturbations, Different Mechanisms: Understanding Continued Pre-training for Zero-Shot Dialect Robustness

Dialectal variation remains a major challenge for multilingual language models. Perturbation-based continued pre-training (CPT) has emerged as a promising approach to improving robustness, yet existing work largely evaluates individual perturbation strategies in isolation and provides limited insight into why they work. We present a systematic study of perturbation-based CPT for multilingual dialect robustness in LLMs, comparing six training conditions across nine German, Italian, and Arabic dialect tasks. Perturbation-based CPT, especially character-noised CPT, consistently improves zero-shot dialect robustness while largely preserving standard variety performance. More importantly, we show that methods with similar downstream performance induce distinct mechanisms of robustness, exhibiting different patterns of language model adaptation, representational alignment, and prediction repair. Our results provide a more complete understanding of how synthetic surface variation improves robustness and offer practical guidance for selecting CPT strategies in multilingual and dialectal settings.
Aug 11, 2026

Diffract: Spectral View of LLM Domain Adaptation

We study continual pre-training (CPT) as a mechanism for adapting general-purpose large language models to specialized domains: mathematics, instruction, code, and natural text. Using singular value decomposition of weight matrices, we find that CPT leaves singular value spectra largely invariant, with adaptation driven mainly by changes in singular vectors. An analysis of attention-head projection matrices reveals strong, domain-dependent head heterogeneity, which we exploit to define a head importance criterion: up to 60% of head updates can be removed without measurable quality loss. Selectively rewinding low-importance heads to their pre-trained state improves benchmark accuracy by up to 4% versus the fully trained baseline. Finally, we identify domain connectivity - linear interpolation between CPT checkpoints yields smooth domain-quality interpolation without notable degradation on either domain - and release Diffract, an open-source toolkit for scalable spectral analysis of billion-parameter models.
Jul 8, 2026

DiaLLM: An Investigation into the Robustness-Generation Gap in English Dialect Adaptation

Large language models increasingly understand dialectal English, yet still produce only standard, US-leaning English, leaving dialectal generation, the harder half of the problem, largely unaddressed. We introduce DiaLLM, which continually pretrains three open-weight language model families on the International Corpus of English and applies implicit and explicit post-training paradigms, each combined with three model alignment strategies, giving the first controlled comparison of these components across Australian, Indian, and Northern British English. Our results reveal a robustness-generation gap: benchmarks are shaped by continual pretraining and SFT, while alignment visibly reshapes generation in ways benchmarks do not capture. Explicit variety-targeted adaptation produces output reliably recognised as dialectal and judged more dialectal than broad alignment, yet where human judgement was directly assessed, the method that most aggressively optimises the dialectal reward is not the one judged most dialectal. Independent linguistic analysis corroborates this reward-quality gap, most clearly on two of the three families. No single alignment method dominates, and closing the gap will require richer reward designs and continued investment in dialectal resources. We release all code, checkpoints, and preference datasets.