DADA: Dialect Adaptation via Dynamic Aggregation of Linguistic Rules
This addresses the issue of dialect bias in LLMs for users of diverse English dialects, though it is incremental as it builds on existing adapter-based methods.
The paper tackles the problem of large language models performing poorly on non-standard English dialects by proposing DADA, a modular approach that uses adapters for linguistic features to improve multi-dialectal robustness, showing effectiveness for both single-task and instruction-finetuned models.
Existing large language models (LLMs) that mainly focus on Standard American English (SAE) often lead to significantly worse performance when being applied to other English dialects. While existing mitigations tackle discrepancies for individual target dialects, they assume access to high-accuracy dialect identification systems. The boundaries between dialects are inherently flexible, making it difficult to categorize language into discrete predefined categories. In this paper, we propose DADA (Dialect Adaptation via Dynamic Aggregation), a modular approach to imbue SAE-trained models with multi-dialectal robustness by composing adapters which handle specific linguistic features. The compositional architecture of DADA allows for both targeted adaptation to specific dialect variants and simultaneous adaptation to various dialects. We show that DADA is effective for both single task and instruction finetuned language models, offering an extensible and interpretable framework for adapting existing LLMs to different English dialects.