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.
Detecting ambiguous utterances in an intelligent assistant,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.SD 1years
2026 1verdicts
ACCEPT 1representative citing papers
citing papers explorer
-
WASIL: In-the-Wild Arabic Spoken Interactions with LLMs
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.