pith. sign in

Title resolution pending

Conclusion In this paper, we introduced WASIL, to our knowledge the first in-the-wild dataset of Arabic spoken interactions with LLMs, designed to capture realistic conversational

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it
browse 1 citing papers

Title metadata for this work has not finished resolving. The hub is built from the citation graph; the title resolver retries DOI and OpenAlex on its next pass.

fields

cs.SD 1

years

2026 1

verdicts

ACCEPT 1

representative citing papers

WASIL: In-the-Wild Arabic Spoken Interactions with LLMs

cs.SD · 2026-05-09 · accept · novelty 7.0

WASIL is a released dataset of 8,529 in-the-wild Arabic spoken LLM interactions with audio, ASR hypotheses, responses, explicit like/dislike feedback, answerability annotations, a 2,000-turn MSA and dialect test set, and a reference-free multi-judge LLM evaluation method.

citing papers explorer

Showing 1 of 1 citing paper.

  • WASIL: In-the-Wild Arabic Spoken Interactions with LLMs cs.SD · 2026-05-09 · accept · none · ref 6

    WASIL is a released dataset of 8,529 in-the-wild Arabic spoken LLM interactions with audio, ASR hypotheses, responses, explicit like/dislike feedback, answerability annotations, a 2,000-turn MSA and dialect test set, and a reference-free multi-judge LLM evaluation method.