Tag
The author demonstrates that small vertical language models (6B-15B) can outperform top LLMs on niche benchmarks through cost-effective fine-tuning using open-source models and Codex orchestration, achieving results with a $300 dataset.
This paper compares a domain-trained small language model (Olava Extract) against frontier LLMs for structured contract extraction, showing that the specialized model achieves higher F1 scores and dramatically lower cost.
A developer trained a 350M-parameter model capable of navigating spreadsheets better than Anthropic's Opus 4.6.
SCURank introduces Summary Content Units to rank candidate summaries, enabling small models distilled from multiple LLMs to outperform traditional metrics and single-LLM distillates.
SmolDocling is a compact 256M parameter vision-language model designed for end-to-end multi-modal document conversion. It introduces a new universal markup format called DocTags to capture page elements with location, competing with models 27 times larger.