Introduces the CHA-Gen dataset for Chinese ambiguity based on Potential Ambiguity Theory and shows LLMs struggle to detect ambiguity, exhibiting specific failure modes and overconfidence after instruction tuning.
, author Garc \' a-Sierra, \'O
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Evaluating Chinese Ambiguity Understanding in Large Language Models
Introduces the CHA-Gen dataset for Chinese ambiguity based on Potential Ambiguity Theory and shows LLMs struggle to detect ambiguity, exhibiting specific failure modes and overconfidence after instruction tuning.