Across four LLMs and six interaction modes, models solve hidden-function inference more often with upfront or oracle-provided evidence than with self-selected queries, and they struggle to know when to stop.
""Returns x unchanged if it is non-negative , otherwise returns x plus 7
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Don't Let Me Ask for It: LLMs Show Deficiencies in Active Multi-Turn Information Acquisition for Abductive Inference
Across four LLMs and six interaction modes, models solve hidden-function inference more often with upfront or oracle-provided evidence than with self-selected queries, and they struggle to know when to stop.