Personalization and Evaluation of Conversational Information Access

2026-06-15T08:52:16Z24040b8819ea0fb0097c2fbd5d96602aa5a35d129f9f0bcc81419e03b0a97c82
ADOREArabic NLPKGERMAR','CoRe','query rewriting','production systemsPADQuranic passage retrievalTASRconversational information accessdataset constructiondenoisingentity linkingevaluation metricshybrid retrievaliterative retrievalknowledge graphlong-context modelingmedical nomenclaturememory-augmented retrievalmood-aware recommendationmusic recommendationontologypersonalizationpopularity biasquery expansionrelevance feedbackstopping rule

What happened

Collection of recent arXiv CS/IR submissions (announced 2026-06-15) covering advances in conversational information access, personalization, retrieval, and evaluation. Highlights include: a thesis on personalized Conversational Information Access introducing ConEL (conversational entity linking), CREL (conversational EL method), LAPS (large-scale personalized conversational dataset construction) and FACE (reference-free conversation-level evaluation); NOMAD, a two-level ontology and large-scale classifier for disease-name nomenclature applied to ICD-10-CM entries; TASR, a simple training-free,

Why it matters

A reviewed impact interpretation has not been published for this record.

Evidence and limitations

Source ID
arxiv_cs_ir
Record identifier
24040b8819ea0fb0097c2fbd5d96602aa5a35d129f9f0bcc81419e03b0a97c82
Enrichment time
2026-06-15T08:52:16Z
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.