mlsanityData to 7 Oct 2026

Can LLM Agents Identify Spoken Dialects like a Linguist?

arXiv 2603.29541 ↗First posted 31 Mar 2026cs.CLcited by 0

On the map: LLM agents and tool use → General LLM agent frameworks and benchmarks

Abstract (arXiv)

Due to the scarcity of labeled dialectal speech, audio dialect classification is a challenging task for most languages, including Swiss German. In this work, we explore the ability of large language models (LLMs) as agents in understanding the dialects and whether they can show comparable performance to models such as HuBERT in dialect classification. In addition, we provide an LLM baseline and a human linguist one. Our approach uses phonetic transcriptions produced by ASR systems and combines them with linguistic resources such as dialect feature maps, vowel history, and rules. Our findings indicate that, when linguistic information is provided, the LLM predictions improve. The human baseline shows that automatically generated transcriptions can be beneficial for such classifications, but also presents opportunities for improvement.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in General LLM agent frameworks and benchmarks, one of 16 directions in LLM agents and tool use. Builds on 14 of its 30 references that are in the map. First posted on arXiv 31 Mar 2026.

Builds on

14 of 30 references.

Closest ancestors · 1

Same direction, newest first

  1. 2024Exploration of LLM Multi-Agent Application Implementation Based on LangGraph+CrewAI27 Nov

Other references · 13

  1. 2017Attention Is All You Needcited by 59,932
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  3. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 13,958
  4. 2023Toolformer: Language Models Can Teach Themselves to Use Toolscited by 4,072
  5. 2021HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Unitscited by 2,301
  6. 2022Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language modelscited by 1,970
  7. 2020Universal Phone Recognition with a Multilingual Allophone Systemcited by 81
  8. 2021Simple and Effective Zero-shot Cross-lingual Phoneme Recognitioncited by 79
  9. 2021SwissDial: Parallel Multidialectal Corpus of Spoken Swiss Germancited by 25
  10. 2020PuzzLing Machines: A Challenge on Learning From Small Datacited by 15
  11. 2024Sebastian, Basti, Wastl?! Recognizing Named Entities in Bavarian Dialectal Datacited by 8
  12. 2024Does Whisper understand Swiss German? An automatic, qualitative, and human evaluationcited by 8
1 more
  1. 2025Improving Low-Resource Dialect Classification Using Retrieval-based Voice Conversioncited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026A Dialectic Pipeline for Improving LLM Robustness
  2. 2026PolySpeech-100: A Large-Scale Benchmark for Speech Understanding Across 100+ Languages and Dialects
  3. 2026agentic-ger: terminology recovery in long-form speech using global context
  4. 2025Learning LLM Preference over Intra-Dialogue Pairs: A Framework for Utterance-level Understandings
  5. 2023A Comprehensive Overview of Large Language Models
  6. 2024A Survey of Large Language Models for European Languages
  7. 2023LLaSM: Large Language and Speech Model
  8. 2024Data-Augmentation-Based Dialectal Adaptation for LLMs