retrieval text
LoTTE
LoTTE (Long-Tail Topic-stratified Evaluation for IR) is designed to evaluate retrieval models on underrepresented, long-tail topics. Unlike MSMARCO or BEIR, LoTTE features domain-specific queries and passages from StackExchange (covering writing, recreation, science, technology, and lifestyle), providing a challenging out-of-domain generalization benchmark.
Domains: AcademicWebSocial
Languages: English
In benchmark:
- Task type
- Retrieval
- Main metric
hit_rate_at_5- Source dataset
- mteb/LoTTE
- License
- mit
- Dates
- 2021-12-02 → 2022-06-10
- Annotations
- derived
- Sample creation
- found
Models scored …