Saidzoda-Kazakh-EmbeddingGemma-300M: How Far One Epoch of Generated Questions Takes a Small Kazakh Embedder
cs.CL
Submitted: 2026-11-12
Updated: 2026-11-12
Code: https://github.com/ProgrammerXX1/kaz-embed
Terminology
Sources
- InPars: Data Augmentation for Information Retrieval using Large Language Models
- M3-Embedding: Multi-Linguality, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillation
- Promptagator: Few-shot Dense Retrieval From 8 Examples
- MMTEB: Massive Multilingual Text Embedding Benchmark
- Scaling Deep Contrastive Learning Batch Size under Memory Limited Setup
- Gemma 3 Technical Report
- Efficient Natural Language Response Suggestion for Smart Reply
- Connecting the Persian-speaking World through Transliteration
- NV-Retriever: Improving text embedding models with effective hard-negative mining
- Synthetic Test Collections for Retrieval Evaluation
- Towards Understanding Bias in Synthetic Data for Evaluation
- Adapting Qwen3 to Tajik from 0.6B to 8B: Lower Text Loss Did Not Mean Better Understanding
- Saidzoda-CA-EmbeddingGemma-300M: One Small Embedder for Tajik, Kazakh, Uzbek and Kyrgyz
- Saidzoda-Tajik-E5-Large: Fine-Tuning a 560M Embedder for Tajik Retrieval
- Saidzoda-Tajik-LFM-2.6B: Adapting a 2.6B Hybrid Model to Tajik Tool Calling, and What Continued Pretraining Takes Away
- EmbeddingGemma: Powerful and Lightweight Text Representations
- GPL: Generative Pseudo Labeling for Unsupervised Domain Adaptation of Dense Retrieval
- Multilingual E5 Text Embeddings: A Technical Report
Related papers
- ALARM: Audio-Language Alignment for Reasoning Models
- ThinkSum: Probabilistic reasoning over sets using large language models
- Coherence boosting: When your pretrained language model is not paying enough attention
- From Facts to Insights: A Persona-Driven Dual Memory Framework and Dataset for Role-Playing Agents
- Improving General Role-Playing Agents via Psychology-Grounded Reasoning and Role-Aware Policy Optimization
- The Art of Asking: Multilingual Prompt Optimization for Synthetic Data