Papers › CoT-based Synthesizer: Enhancing LLM Performance through Answer Synthesis

CoT-based Synthesizer: Enhancing LLM Performance through Answer Synthesis

3 Jan 2025arXiv:2501.01668archive 2025-07-28

Bohan Zhang, Xiaokang Zhang, Jing Zhang, Jifan Yu, Sijia Luo, Jie Tang

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 MATH dataset. The corresponding training data and code are publicly available on https://github.com/RUCKBReasoning/CoT-based-Synthesizer.

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

ruckbreasoning/cot-based-synthesizer officialmentioned in papermentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Math

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

AttentionLinear LayerMulti-Head AttentionSoftmaxSynthesizer

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections