international-corpus-of-english-f886e689·1 events·first seen Aliases: International Corpus of English
Researchers introduce DiaLLM, a framework that continually pretrains three open-weight LLM families on the International Corpus of English to study dialect adaptation across Australian, Indian, and Northern British English. The study finds that dialectal robustness (understanding) and generation are dissociated: benchmarks are shaped by pretraining and SFT, while alignment reshapes generation in ways benchmarks fail to capture. A key finding is that the alignment method most aggressively optimizing dialectal reward is not preferred by human evaluators, revealing a reward-quality gap. Code, checkpoints, and preference datasets are released.