DialectGen: Benchmarking and Improving Dialect Robustness in Multimodal Generation

• URL: http://arxiv.org/abs/2510.14949v1
• Date: Thu, 16 Oct 2025 17:56:55 GMT
• Title: DialectGen: Benchmarking and Improving Dialect Robustness in Multimodal Generation
• Authors: Yu Zhou, Sohyun An, Haikang Deng, Da Yin, Clark Peng, Cho-Jui Hsieh, Kai-Wei Chang, Nanyun Peng,
• Abstract summary: Can multimodal generative models effectively produce content given dialectal textual input?<n>We construct a new large-scale benchmark spanning six common English dialects.<n>We design a general encoder-based mitigation strategy for multimodal generative models.
• Score: 111.94720088481614
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Contact languages like English exhibit rich regional variations in the form of dialects, which are often used by dialect speakers interacting with generative models. However, can multimodal generative models effectively produce content given dialectal textual input? In this work, we study this question by constructing a new large-scale benchmark spanning six common English dialects. We work with dialect speakers to collect and verify over 4200 unique prompts and evaluate on 17 image and video generative models. Our automatic and human evaluation results show that current state-of-the-art multimodal generative models exhibit 32.26% to 48.17% performance degradation when a single dialect word is used in the prompt. Common mitigation methods such as fine-tuning and prompt rewriting can only improve dialect performance by small margins (< 7%), while potentially incurring significant performance degradation in Standard American English (SAE). To this end, we design a general encoder-based mitigation strategy for multimodal generative models. Our method teaches the model to recognize new dialect features while preserving SAE performance. Experiments on models such as Stable Diffusion 1.5 show that our method is able to simultaneously raise performance on five dialects to be on par with SAE (+34.4%), while incurring near zero cost to SAE performance.

Related papers

• Voxlect: A Speech Foundation Model Benchmark for Modeling Dialects and Regional Languages Around the Globe [29.70578165040035]
  We present Voxlect, a novel benchmark for modeling dialects and regional languages worldwide using speech foundation models.<n>Specifically, we report comprehensive benchmark evaluations on dialects and regional language varieties in English, Arabic, Mandarin and Cantonese, Tibetan, Indic languages, Thai, Spanish, French, German, Brazilian Portuguese, and Italian.
  arXiv  Detail & Related papers  (2025-08-03T09:51:28Z)
• To Distill or Not to Distill? On the Robustness of Robust Knowledge Distillation [16.655022975392992]
  Current multilingual ASR models are compute-intensive and lack proper comprehensive evaluations. We distill knowledge from large teacher models into smaller student variants that are more efficient. Our best-distilled model's overall performance ($45.0$% WER) surpasses that of a SoTA model twice its size.
  arXiv  Detail & Related papers  (2024-06-06T21:11:53Z)
• Multilingual Audio-Visual Speech Recognition with Hybrid CTC/RNN-T Fast Conformer [59.57249127943914]
  We present a multilingual Audio-Visual Speech Recognition model incorporating several enhancements to improve performance and audio noise robustness. We increase the amount of audio-visual training data for six distinct languages, generating automatic transcriptions of unlabelled multilingual datasets. Our proposed model achieves new state-of-the-art performance on the LRS3 dataset, reaching WER of 0.8%.
  arXiv  Detail & Related papers  (2024-03-14T01:16:32Z)
• Retrieval is Accurate Generation [99.24267226311157]
  We introduce a novel method that selects context-aware phrases from a collection of supporting documents. Our model achieves the best performance and the lowest latency among several retrieval-augmented baselines.
  arXiv  Detail & Related papers  (2024-02-27T14:16:19Z)
• Generative Spoken Language Model based on continuous word-sized audio tokens [52.081868603603844]
  We introduce a Generative Spoken Language Model based on word-size continuous-valued audio embeddings. The resulting model is the first generative language model based on word-size continuous embeddings.
  arXiv  Detail & Related papers  (2023-10-08T16:46:14Z)
• Multi-VALUE: A Framework for Cross-Dialectal English NLP [49.55176102659081]
  Multi- Dialect is a controllable rule-based translation system spanning 50 English dialects. Stress tests reveal significant performance disparities for leading models on non-standard dialects. We partner with native speakers of Chicano and Indian English to release new gold-standard variants of the popular CoQA task.
  arXiv  Detail & Related papers  (2022-12-15T18:17:01Z)
• Quantifying Language Variation Acoustically with Few Resources [4.162663632560141]
  Deep acoustic models might have learned linguistic information that transfers to low-resource languages. We compute pairwise pronunciation differences averaged over 10 words for over 100 individual dialects from four (regional) languages. Our results show that acoustic models outperform the (traditional) transcription-based approach without requiring phonetic transcriptions.
  arXiv  Detail & Related papers  (2022-05-05T15:00:56Z)
• Unsupervised Cross-lingual Representation Learning for Speech Recognition [63.85924123692923]
  XLSR learns cross-lingual speech representations by pretraining a single model from the raw waveform of speech in multiple languages. We build on wav2vec 2.0 which is trained by solving a contrastive task over masked latent speech representations. Experiments show that cross-lingual pretraining significantly outperforms monolingual pretraining.
  arXiv  Detail & Related papers  (2020-06-24T18:25:05Z)

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.