Do LLM Recommenders Know When They're Hallucinating? Auditing Confidence Calibration in Catalog Faithfulness

arXiv 2608.10008•bbb1da53724e306a002497ca51eac15cc662d2525e47564e713ce51120a9b167
catalog-faithfulnesscollaborative-filteringconfidence-calibrationgraph-neural-networksinformation-retrievallarge-language-modelsllm-evaluationllm-hallucinationmodel-efficiencymultimodal-robustnesspersonalizationrecommender-systemsreliability-rerankingresearchsocial-graph-recommendation

Paper metadata

arXiv ID
2608.10008
Version
Not specified by this published record
Category
Computer Science — Information Retrieval (cs.IR)

The PDF link points to arxiv.org. Baitaphish does not expose a private stored PDF.

Evidence and limitations

Source ID
arxiv_cs_ir
Record identifier
bbb1da53724e306a002497ca51eac15cc662d2525e47564e713ce51120a9b167
Enrichment time
2026-08-12T08:52:09Z
AI-assisted enrichment
Yes

This record may overlap with other records. Its enrichment can be incomplete or wrong, and machine assistance was used. Validate consequential decisions against the linked source and your own environment.