When and How to Ask: Dynamic Preference Elicitation Strategies for Conversational Recommendation
2026-07-09T08:52:15Z•ed82a53be5790bca63dbfc12132df30476e47857e7a193be2c6c873cd6dccd46
HIPAALLMPHIRAGadaptive-retrievalagent-systemsbenchmarksconversational-recommenderdata-leakagedatasetsembeddingsknowledge-graphmemory-systemsmodel-hallucinationmultimodalopen-source-codeprecision-vs-recallprivacyretrieval-augmented-generationsemantic-searchskill-routing
What happened
Collection of recent arXiv papers (07/09/2026) on LLM-based recommendation, retrieval, memory, and embedding systems. Highlights include: InPE and COPE for stage-aware conversational preference elicitation; MMEACR for multimodal memory-enhanced agent collaboration; a large-scale health-system semantic search indexing 166M clinical notes under a HIPAA governance framework; PrecisionMemBench and Tenure showing structural retrieval precision failures in LLM memory systems; R3-Skill and R3 retrievers for query-conditional skill routing; uncertainty-aware adaptive QA (efficient single-pass hidden‑/
Why it matters
A reviewed impact interpretation has not been published for this record.
Evidence and limitations
- Source ID
- arxiv_cs_ir
- Record identifier
- ed82a53be5790bca63dbfc12132df30476e47857e7a193be2c6c873cd6dccd46
- Enrichment time
- 2026-07-09T08:52:15Z
- 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.