A Sensitivity-Aware Test Collection for Search Among Personal Information
2026-06-29T08:52:24Z•f3859b2840315ca17edb547b8cb22d3e06a58ba793d306c48f13a23fc30101d9
Enron-corpusHuggingFaceLLM-judgingcode-retrievaldata-labelingdata-leakage-riskdataset-releaseexplainabilityir_datasetsmodel-inference-adaptationpersonal-dataprivacyrecommendation-systemssensitivity-aware-search
What happened
This collection announces multiple IR and ML research preprints. Most notable from a security/privacy perspective is a Sensitivity-Aware Search (SAS) test collection built from a manually labeled subset of the Enron email corpus: 50 topics, 150 crowdsourced queries, 11,471 query-relevance assessments, extended with LLM-judged labels, and distributed via ir_datasets with pre-built sparse/dense indices on Hugging Face. Other papers introduce methods for LLM-based recommendation (IntuRec), asymmetric bidirectional discrete-diffusion LMs (Bifocal dLLMs / R2LM), resource-adaptive inference (L2A), a
Why it matters
A reviewed impact interpretation has not been published for this record.
Evidence and limitations
- Source ID
- arxiv_cs_ir
- Record identifier
- f3859b2840315ca17edb547b8cb22d3e06a58ba793d306c48f13a23fc30101d9
- Enrichment time
- 2026-06-29T08:52:24Z
- 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.