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

Abstract

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.

Authors 6

Jordan Painter, Dipankar Srirag, Adarsh Kappiyath, Diptesh Kanojia, Aditya Joshi, Lu Yin

Specification

Official page: arxiv.org/abs/2607.07669
Source:arXiv (Atom API + RSS)T1observed 9 h agohigh
Arxiv announce type: replace
Source:arXiv (Atom API + RSS)T1observed 9 h agohigh
arXiv id: 2607.07669
Source:arXiv (Atom API + RSS)T1observed 9 h agohigh
Categories: cs.CL, cs.AI
Source:arXiv (Atom API + RSS)T1observed 9 h agohigh
PDF: arxiv.org/pdf/2607.07669
Source:arXiv (Atom API + RSS)T1observed 9 h agohigh
Primary category: cs.CL
Source:arXiv (Atom API + RSS)T1observed 9 h agohigh
Published: 12 Sept 2026
Source:arXiv (Atom API + RSS)T1observed 1 h agohigh

Each value shows its source, tier and observation time. Conflicting claims are kept side by side and flagged — never averaged. How AI Atlas records facts →

Provenance

Attributed facts

9

Source tiers

T19

Freshest observation

1 h ago

Conflicts

None

No models linked to this paper yet.

Authors: Jordan Painter, Dipankar Srirag, Adarsh Kappiyath

As of

Rewind the record: see this entity's attributes exactly as AI Atlas knew them on a given day.

Claim history · Abstract

1 claims · 1 propertiesShow all properties

Abstractabstract1

Claim history for Abstract
Value	Valid from → to	Status	Source	Confidence	Extractor
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.	11 Sept 2026 21:03 UTC → current	current	arXiv (Atom API + RSS)T1	high	deterministic

Claims are temporal and append-only: a new observation closes the previous claim (valid_to) instead of overwriting it. Conflicting claims from different sources are kept side by side and flagged — never averaged. Methodology →

12 Sept 2026
Property changedPaperDiaLLM: An Investigation into the Robustness-Generation Gap in English Dialect Adaptation
DiaLLM: An Investigation into the Robustness-Generation Gap in English Dialect Adaptation: published at changed from 2026-09-11T04:00:00+00:00 to 2026-09-12T04:00:00+00:00
Published11 Sept 2026→12 Sept 2026arxiv
rss.arxiv.org
11 Sept 2026
New paperPaperDiaLLM: An Investigation into the Robustness-Generation Gap in English Dialect Adaptation
New paper: DiaLLM: An Investigation into the Robustness-Generation Gap in English Dialect Adaptation
arxiv
rss.arxiv.org

Full timeline →

Source documents
Source	Document	Type	Tier	Last observed	Snapshots
arXiv (Atom API + RSS)	rss.arxiv.org/rss/cs.AI	feed	T1· Official	1 h ago	2
arXiv (Atom API + RSS)	rss.arxiv.org/rss/cs.CL	feed	T1· Official	1 h ago	1

Tier 1 = official/primary, 2 = quality secondary, 3 = community, 4 = unverified. Every snapshot is archived; see all sources and the methodology.