A prompting framework that recursively decomposes reasoning tasks and self-scores candidate thoughts is reported to improve LLM accuracy on math and letter-concatenation benchmarks, though the headline improvement is overstated relative to the presented baselines.
Can Separators Improve Chain-of-Thought Prompting?
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
Chain-of-thought (CoT) prompting is a simple and effective method for improving the reasoning capabilities of Large Language Models (LLMs). The basic idea of CoT is to let LLMs break down their thought processes step-by-step by putting exemplars in the input prompt. However, the densely structured prompt exemplars of CoT may cause the cognitive overload of LLMs. Inspired by human cognition, we introduce COT-SEP, a method that strategically employs separators at the end of each exemplar in CoT prompting. These separators are designed to help the LLMs understand their thought processes better while reasoning. Interestingly, it turns out that COT-SEP significantly improves the LLMs' performances on complex reasoning tasks (e.g., GSM8K, AQuA, CSQA), compared with the vanilla CoT, which does not use separators. We also study the effects of the type and the location of separators tested on multiple LLMs, including GPT-3.5-Turbo, GPT-4, and LLaMA-2 7B.
citation-role summary
background 1
citation-polarity summary
fields
cs.CL 1years
2025 1verdicts
REJECT 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Recursive Decomposition of Logical Thoughts: Framework for Superior Reasoning and Knowledge Propagation in Large Language Models
A prompting framework that recursively decomposes reasoning tasks and self-scores candidate thoughts is reported to improve LLM accuracy on math and letter-concatenation benchmarks, though the headline improvement is overstated relative to the presented baselines.