AI-generated podcasts often add unsupported claims; a turn-level detector plus rewrite pass improves measured faithfulness across five models and in- and out-of-domain documents.
Dynamic Attention-Guided Context Decoding for Mitigating Context Faithfulness Hallucinations in Large Language Models
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
-
On Improving Faithfulness of Podcasts from Documents
AI-generated podcasts often add unsupported claims; a turn-level detector plus rewrite pass improves measured faithfulness across five models and in- and out-of-domain documents.