HackerPapers

arXiv:2401.05618cs.CL

The Benefits of a Concise Chain of Thought on Problem-Solving in Large Language Models

Matthew Renze, Erhan Guven

Abstract

In this paper, we introduce Concise Chain-of-Thought (CCoT) prompting. We compared standard CoT and CCoT prompts to see how conciseness impacts response length and correct-answer accuracy. We evaluated this using GPT-3.5 and GPT-4 with a multiple-choice question-and-answer (MCQA) benchmark. CCoT reduced average response length by 48.70% for both GPT-3.5 and GPT-4 while having a negligible impact on problem-solving performance. However, on math problems, GPT-3.5 with CCoT incurs a performance penalty of 27.69%. Overall, CCoT leads to an average per-token cost reduction of 22.67%. All code, data, and supplemental materials are available on GitHub at https://github.com/matthewrenze/jhu-concise-cot

arXiv comments
Journal reference
2nd International Conference on Foundation and Large Language Models (FLLM 2024), pp.476-483
DOI
doi:10.1109/FLLM63129.2024.10852493
Subjects
cs.CLComputation and Language cs.AIArtificial Intelligence

On Hacker News

Linked by 3 identifiable commenters in 3 comments across 3 threads, from Mar 2025 to Jul 2026.

Comments linking this paper, per year.

Discussed in comments3 threads

  1. Autistic Caveman: Why use many token when correct token do trick 1 comment

    • Author here. I enjoyed the original idea behind the Caveman skill. I tried to log and do RLHF over my own mistakes and corrections in the LLM conversations and realized the skills were slowing everything down. Hence, I've this opinionated system prompt that aims to add a few…

      AIrtemisView on HNParent context

  2. Caveman: Why use many token when few token do trick 1 comment

    • Author here. A few people are arguing against a stronger claim than the repo is meant to make. As well, this was very much intended to be a joke and not research level commentary. This skill is not intended to reduce hidden reasoning / thinking tokens. Anthropic’s own docs…

      JBrussee-2View on HNParent context

  3. Sketch-of-Thought: Efficient LLM Reasoning 1 comment

    • After reading both papers, I have to disagree. Chain of Draft seems "identical" to Concise Chain-of-Thought (CCoT) https://arxiv.org/abs/2401.05618. Additionally, the CoD authors seem to mention that it is cognitive inspired but don't give any actual basis for that.…

      xyz7786View on HNParent context

Submitted to Hacker News

Connected through shared HN threads, not inferred similarity or a recommendation.