Post-training pipeline choice (SFT+RL vs RL-only vs SFT-only) reliably shifts hallucination rates in large reasoning models on fact-seeking benchmarks.
PAL: program-aided language models
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
other 1
citation-polarity summary
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1roles
other 1polarities
unclear 1representative citing papers
citing papers explorer
-
Are Reasoning Models More Prone to Hallucination?
Post-training pipeline choice (SFT+RL vs RL-only vs SFT-only) reliably shifts hallucination rates in large reasoning models on fact-seeking benchmarks.