Mult-DPO: Multinomial Direct Preference Optimization for Recommender Systems
arXiv 2606.10078•0deb52d42e5c160cd3c9c45b8489778ff664db3d7d90634b2b5a31f4295d46ca
AIRBM25','retrieval','query-rewriting'CGMDPOMult-DPOPlackett-LuceRAGSIDInspectorSTORMSkillResolve-Benchagentic-recommendersbenchmarkscounterfactual-explanationsevaluationhealth-datainference-accelerationlarge-language-modelslexical-query-expansionpersonalizationprivacyrecommender-systemssafetysemantic-id-tokenizersskill-retrievaltau-Rec
Paper metadata
- arXiv ID
- 2606.10078
- 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
- 0deb52d42e5c160cd3c9c45b8489778ff664db3d7d90634b2b5a31f4295d46ca
- Enrichment time
- 2026-06-10T08:52:20Z
- 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.