The authors build ConfuseBench for three sources of LLM uncertainty and show that asking a follow-up question and checking whether its answer is unique improves source identification.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Do not Abstain! Identify and Solve the Uncertainty
The authors build ConfuseBench for three sources of LLM uncertainty and show that asking a follow-up question and checking whether its answer is unique improves source identification.