20 results for “Small Language Model”
CS papers onlyHybrid search: Keyword + semantic, ranked by combined score.ⓘ
Want pure semantic search? Try claim verification →
This paper evaluates the performance of twelve Small Language Models on Arabic natural language processing tasks.
ProbScale is a novel framework that combines neural scaling laws and language model probing to identify highly efficient, task-specific subnetworks within pre-trained Small Language Models, achieving…
Divya Tadimeti, Shawn Pan, Sameera Lanka, Chenghui Zhou +1 more
This paper demonstrates that targeted adaptation of the small language model Phi Silica, using dataset curation and fine-tuning, significantly improves its performance in short-form text rewriting, na…
This paper demonstrates that fine-tuning small language models (SLMs) on a synthetic, solution-rich Windows event log dataset allows them to outperform larger LLMs in identifying issues and providing…
This paper investigates the performance of small language models in relation extraction tasks, showing that task-specific adaptation can enable them to outperform larger, general-purpose models.
The paper proposes an aggressive, parameter-efficient method to prune non-essential experts from Mixture-of-Experts (MoE) LLMs, significantly compressing the model while maintaining high machine trans…
Develops specialized Japanese-English translation models for real-world translation tasks.
Zhilin Guo, Boqiao Zhang, Hakan Aktas, Kyle Fogarty +13 more
This paper introduces a Telescopic Language Model (TLM) that can serve multiple compute budgets with a single training run.
This paper introduces a pipeline to extract grammatical rules, example sentences, and lexicons from grammar books and generates synthetic parallel corpora for fine-tuning machine translation models on…
Developed the first open Speech Language Model for Basque for low-latency, end-to-end spoken interaction.
The paper introduces PortBERT, a family of RoBERTa-based language models for Portuguese, which achieves competitive performance while explicitly balancing efficiency and accuracy.
This paper introduces Weight Pair Encoding, a method to explicitly finetune neural network weights to admit a smaller grammar.
Minhua Lin, Zijun Wang, Zewen Liu, Zhaotian Weng +6 more
This paper proposes a method, LM2LM, to train large language models to generate effective improvement proposals using reinforcement learning and a research world model.
Tianjian Li, Jingyu Zhang, William Jurayj, Xi Wang +4 more
This paper proposes SelfCompact, a scaffold that allows models to decide when and how to compact long agent traces, improving summarization at a lower token cost.
Marek Šuppa, Andrej Ridzik, Daniel Hládek, Natália Kňažeková +1 more
This paper introduces SkMTEB, a comprehensive text embedding benchmark for Slovak, and develops efficient, locally-deployable Slovak embeddings.
The paper introduces OCC-RAG, a family of compact, task-specialized Small Language Models (SLMs) designed to achieve highly faithful, multi-hop question answering grounded strictly in provided context…