Translate, Search, or Answer: Cost-Aware Cross-Lingual Retrieval for Kazakh Small Language Models
This work systematically compares zero-shot parametric generation, in-language retrieval, and cross-lingual (translate-then-retrieve) web search using three 4B-parameter SLMs in both reasoning and non-reasoning modes and proposes a training-free, self-aware router that uses majority voting over repeated self-verificati...
Akylbek Maxutov, Nūrali Medeu, Vladimir Albrekht et al.
· Big Data and Cognitive Compu... · 0 citations