A small language model fine-tuned on tool-augmented chain-of-thought data generated by a larger LLM learns to selectively call tools, delivering better content moderation accuracy at lower inference cost.
Small llms are weak tool learners: A multi-llm agent, 2024
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Tool-MCoT: Tool Augmented Multimodal Chain-of-Thought for Content Safety Moderation
A small language model fine-tuned on tool-augmented chain-of-thought data generated by a larger LLM learns to selectively call tools, delivering better content moderation accuracy at lower inference cost.