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

• URL: http://arxiv.org/abs/2607.07669v1
• Date: Wed, 08 Jul 2026 17:24:27 GMT
• Title: DiaLLM: An Investigation into the Robustness-Generation Gap in English Dialect Adaptation
• Abstract summary: Large language models increasingly emphunderstand dialectal English, yet still emphproduce only standard, US-leaning English.<n>We introduce textbfDiaLLM, which continually pretrains three open-weight language model families on the International Corpus of English.
• Score: 20.845447775728545
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large language models increasingly \emph{understand} dialectal English, yet still \emph{produce} only standard, US-leaning English, leaving dialectal generation, the harder half of the problem, largely unaddressed. We introduce \textbf{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 that dialectal robustness and generation are \emph{dissociated}: 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 preferred over broad alignment, yet the method that most aggressively optimises the dialectal reward is not preferred by human evaluators. 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.

Related papers

• On the Limitations of Cross-Lingual Consistency in Multilingual Text-to-image Generation [79.18001266925245]
  LingT2I is a benchmark covering 10 widely used languages with 33K prompts.<n>We conduct a comprehensive cross-lingual analysis, uncovering linguistic inequality and language-dependent trade-offs.
  arXiv  Detail & Related papers  (2026-08-11T14:49:23Z)
• Sycophancy as a Multilingual Alignment Failure: How Safety Degrades Across Languages, Topics, and Models [3.2555924024638667]
  Safety-aligned large language models often exhibit sycophancy, which is the tendency to affirm users' opinions regardless of factual accuracy.<n>We present the first large-scale, multi-model evaluation of cross-lingual sycophancy, benchmarking textbfsix instruction-tuned models across textbf38 languages and textbf33 topic categories.
  arXiv  Detail & Related papers  (2026-06-07T04:50:40Z)
• Which English Do LLMs Prefer? Triangulating Structural Bias Towards American English in Foundation Models [12.338320566839483]
  We investigate how geopolitical histories of data curation, digital dominance, and linguistic standardization shape the large language models (LLMs) development pipeline.<n>We construct a curated corpus of 1,813 AmE--BrE variants and introduce DiAlign, a training-free method for estimating dialectal alignment.<n>We find that contemporary LLMs privilege AmE as the de facto norm, raising concerns about linguistic homogenization, epistemic injustice, and inequity in global AI deployment.
  arXiv  Detail & Related papers  (2026-04-05T17:59:34Z)
• Mitigating Cross-Lingual Cultural Inconsistencies in LLMs via Consensus-Driven Preference Optimisation [58.01855677487771]
  We show that multilingual large language models (MLLMs) frequently exhibit inconsistent behaviour when the prompt's language changes.<n>We propose Cross-lingual Cultural Consistent Preference optimisation (C-3PO), a consensus-driven alignment framework.<n>C-3PO achieves up to a 0.10-point absolute increase in $_S$ over unaligned models, outperforming strong prompting and representation steering baselines.
  arXiv  Detail & Related papers  (2026-04-02T14:04:06Z)
• Beyond the Final Layer: Intermediate Representations for Better Multilingual Calibration in Large Language Models [50.34755385896279]
  Confidence calibration is crucial for the reliable deployment of Large Language Models (LLMs)<n>We conduct the first large-scale, systematic studies of multilingual calibration across six model families and over 100 languages.<n>We find that non-English languages suffer from systematically worse calibration.
  arXiv  Detail & Related papers  (2025-10-03T16:07:15Z)
• CM-Align: Consistency-based Multilingual Alignment for Large Language Models [84.19366314925593]
  We propose a consistency-based data method to construct high-quality multilingual preference data.<n> Specifically, our method includes two parts: consistency-guided English reference selection and cross-lingual consistency-based multilingual preference data construction.
  arXiv  Detail & Related papers  (2025-09-10T12:40:49Z)
• Overcoming Catastrophic Forgetting in Zero-Shot Cross-Lingual Generation [48.80125962015044]
  We investigate the problem of performing a generative task (i.e., summarization) in a target language when labeled data is only available in English. We find that parameter-efficient adaptation provides gains over standard fine-tuning when transferring between less-related languages. Our methods can provide further quality gains, suggesting that robust zero-shot cross-lingual generation is within reach.
  arXiv  Detail & Related papers  (2022-05-25T10:41:34Z)
• Towards Multi-Sense Cross-Lingual Alignment of Contextual Embeddings [41.148892848434585]
  We propose a novel framework to align contextual embeddings at the sense level by leveraging cross-lingual signal from bilingual dictionaries only. We operationalize our framework by first proposing a novel sense-aware cross entropy loss to model word senses explicitly. We then propose a sense alignment objective on top of the sense-aware cross entropy loss for cross-lingual model pretraining, and pretrain cross-lingual models for several language pairs.
  arXiv  Detail & Related papers  (2021-03-11T04:55:35Z)
• Cross-lingual Spoken Language Understanding with Regularized Representation Alignment [71.53159402053392]
  We propose a regularization approach to align word-level and sentence-level representations across languages without any external resource. Experiments on the cross-lingual spoken language understanding task show that our model outperforms current state-of-the-art methods in both few-shot and zero-shot scenarios.
  arXiv  Detail & Related papers  (2020-09-30T08:56:53Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.