{
  "annotation_id": "cd6806bb-93f1-4a82-a1da-b90039a7d095",
  "date_created": "2026-02-17T05:53:08.870000Z",
  "date_modified": "2026-02-17T05:53:08.870000Z",
  "file_hash": "79d2323da633782dbcc6adb60c07e17824222c4e85a36b4df3785c951f1e7f66",
  "private": false,
  "record": {
    "abstract": "The development of resource-constrained approaches to automatic speech recognition (ASR) is of great interest due to its broad applicability to many low-resource languages for which there is scant usable data. Existing approaches to many low-resource natural language processing tasks leverage additional data from higher-resource languages that are closely related to a target low-resource language. One increasingly popular approach uses task arithmetic to combine models trained on different tasks to create a model for a task where there is little to no training data. In this paper, we consider training on a particular language to be a task, and we generate task vectors by fine-tuning variants of the Whisper ASR system. For pairings of high- and low-resource languages, we merge task vectors via a linear combination, optimizing the weights of the linear combination on the downstream word error rate on the low-resource target language\u0027s validation set. We find that this approach consistently improves performance on the target languages.",
    "arxiv_id": "2601.07038",
    "authors": [
      "Emma Rafkin",
      "Dan DeGenaro",
      "Xiulin Yang"
    ],
    "categories": [
      "cs.CL"
    ],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "title": "Task Arithmetic with Support Languages for Low-Resource ASR",
    "url": "https://arxiv.org/abs/2601.07038",
    "version": "v1"
  },
  "schema_id": "dorsal/arxiv",
  "source": {
    "execution_id": "b3e2f775-80b5-40c7-9a85-4439ac71d7ec",
    "id": "arXiv Dataset",
    "type": "Model",
    "variant": "snapshot-2026-01-17",
    "version": "0.1.0"
  },
  "user_id": 1000002
}