Jie Tang, Jing Zhang, Jifan Yu, Bohan Zhang, Xiaokang Zhang, Sijia Luo
We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Current inference scaling methods, such as Self-consistency and Best-of-N, have proven effective in improving the accuracy of LLMs on complex reasoning tasks. However, these methods rely heavily on the quality of candidate responses and are unable to produce correct answers when all candidates are incorrect. In this paper, we propose a novel inference scaling strategy, CoT-based Synthesizer, which leverages CoT reasoning to synthesize superior answers by analyzing complementary information from multiple candidate responses, even when all candidate responses are flawed. To enable a lightweight and cost-effective implementation, we introduce an automated data generation pipeline that creates diverse training data. This allows smaller LLMs trained on this data to improve the inference accuracy of larger models, including API-based LLMs. Experimental results across four benchmark datasets with seven policy models demonstrate that our method significantly enhances performance, with gains of 11.8% for Llama3-8B and 10.3% for GPT-4o on the MATH500 dataset. The corresponding training data and code are publicly available on the repository 1 .
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2501.01668")
get_code_for_paper("2501.01668")
have("2501.01668")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2501.01668.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2501.01668)
Connect an agent — have() is free.