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

• URL: http://arxiv.org/abs/2401.05618v1
• Date: Thu, 11 Jan 2024 01:52:25 GMT
• Title: The Benefits of a Concise Chain of Thought on Problem-Solving in Large Language Models
• Authors: Matthew Renze and Erhan Guven
• Abstract summary: 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. Overall, CCoT leads to an average per-token cost reduction of 22.67%.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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%. These results have practical implications for AI systems engineers using LLMs to solve real-world problems with CoT prompt-engineering techniques. In addition, these results provide more general insight for AI researchers studying the emergent behavior of step-by-step reasoning in LLMs.

Related papers

• VeriThinker: Learning to Verify Makes Reasoning Model Efficient [52.74493506816969]
  Large Reasoning Models excel at complex tasks using Chain-of-Thought (CoT) reasoning.<n>Their tendency to overthinking leads to unnecessarily lengthy reasoning chains.<n>We introduce VeriThinker, a novel approach for CoT compression.
  arXiv  Detail & Related papers  (2025-05-23T14:17:56Z)
• Not All Tokens Are What You Need In Thinking [34.767739567093656]
  Conditional Token Selection (CTS) identifies and preserves only the most essential tokens in chains of thought.<n>CTS effectively compresses long CoT while maintaining strong reasoning performance.<n>Further reducing training tokens by 42% incurs only a marginal 5% accuracy drop while yielding a 75.8% reduction in reasoning tokens.
  arXiv  Detail & Related papers  (2025-05-23T12:41:29Z)
• Evaluating ChatGPT-3.5 Efficiency in Solving Coding Problems of Different Complexity Levels: An Empirical Analysis [6.123324869194196]
  We assess the performance of ChatGPT's GPT-3.5-turbo model on LeetCode. We show ChatGPT solves fewer problems as difficulty rises. Second, prompt engineering improves ChatGPT's performance. Third, ChatGPT performs better in popular languages like Python, Java, and C++ than in less common ones like Elixir, Erlang, and Racket.
  arXiv  Detail & Related papers  (2024-11-12T04:01:09Z)
• Towards Scalable Automated Grading: Leveraging Large Language Models for Conceptual Question Evaluation in Engineering [5.160473221022088]
  This study explores the feasibility of using large language models (LLMs) for automated grading of conceptual questions. We compared the grading performance of GPT-4o with that of human teaching assistants (TAs) on ten quiz problems from the MEEN 361 course at Texas A&M University. Our analysis reveals that GPT-4o performs well when grading criteria are straightforward but struggles with nuanced answers.
  arXiv  Detail & Related papers  (2024-11-06T04:41:13Z)
• To CoT or not to CoT? Chain-of-thought helps mainly on math and symbolic reasoning [55.52872152909785]
  Chain-of-thought (CoT) via prompting is the de facto method for eliciting reasoning capabilities from large language models (LLMs) We show that CoT gives strong performance benefits primarily on tasks involving math or logic, with much smaller gains on other types of tasks.
  arXiv  Detail & Related papers  (2024-09-18T17:55:00Z)
• Comparing Neighbors Together Makes it Easy: Jointly Comparing Multiple Candidates for Efficient and Effective Retrieval [36.445443789036226]
  A common retrieve-and-rerank paradigm involves retrieving relevant candidates from a broad set using a fast bi-encoder (BE) We propose the Comparing Multiple Candidates framework, which compares a query and multiple embeddings of similar candidates through shallow self-attention layers. Experimental results on the ZeSHEL dataset demonstrate that CMC, when plugged in between bi-encoders and cross-encoders as a seamless intermediate reranker, can effectively improve recall@k.
  arXiv  Detail & Related papers  (2024-05-21T13:51:48Z)
• Constrained C-Test Generation via Mixed-Integer Programming [55.28927994487036]
  This work proposes a novel method to generate C-Tests; a form of cloze tests (a gap filling exercise) where only the last part of a word is turned into a gap. In contrast to previous works that only consider varying the gap size or gap placement to achieve locally optimal solutions, we propose a mixed-integer programming (MIP) approach. We publish our code, model, and collected data consisting of 32 English C-Tests with 20 gaps each (totaling 3,200 individual gap responses) under an open source license.
  arXiv  Detail & Related papers  (2024-04-12T21:35:21Z)
• Mitigating Misleading Chain-of-Thought Reasoning with Selective Filtering [59.495717939664246]
  Large language models have manifested remarkable capabilities by leveraging chain-of-thought (CoT) reasoning techniques to solve intricate questions. We propose a novel approach called the selective filtering reasoner (SelF-Reasoner) that assesses the entailment relationship between the question and the candidate reasoning chain. SelF-Reasoner improves the fine-tuned T5 baseline consistently over the ScienceQA, ECQA, and LastLetter tasks.
  arXiv  Detail & Related papers  (2024-03-28T06:28:35Z)
• Applying Large Language Models and Chain-of-Thought for Automatic Scoring [23.076596289069506]
  This study investigates the application of large language models (LLMs) in the automatic scoring of student-written responses to science assessments. We focused on overcoming the challenges of accessibility, technical complexity, and lack of explainability that have previously limited the use of artificial intelligence-based automatic scoring tools.
  arXiv  Detail & Related papers  (2023-11-30T21:22:43Z)
• Eval-GCSC: A New Metric for Evaluating ChatGPT's Performance in Chinese Spelling Correction [60.32771192285546]
  ChatGPT has demonstrated impressive performance in various downstream tasks. In the Chinese Spelling Correction (CSC) task, we observe a discrepancy: while ChatGPT performs well under human evaluation, it scores poorly according to traditional metrics. This paper proposes a new evaluation metric: Eval-GCSC. By incorporating word-level and semantic similarity judgments, it relaxes the stringent length and phonics constraints.
  arXiv  Detail & Related papers  (2023-11-14T14:56:33Z)
• Progressive-Hint Prompting Improves Reasoning in Large Language Models [63.98629132836499]
  This paper proposes a new prompting method, named Progressive-Hint Prompting (PHP) It enables automatic multiple interactions between users and Large Language Models (LLMs) by using previously generated answers as hints to progressively guide toward the correct answers. We conducted extensive and comprehensive experiments on seven benchmarks. The results show that PHP significantly improves accuracy while remaining highly efficient.
  arXiv  Detail & Related papers  (2023-04-19T16:29:48Z)
• Faithful Chain-of-Thought Reasoning [51.21714389639417]
  Chain-of-Thought (CoT) prompting boosts Language Models' (LM) performance on a gamut of reasoning tasks. We propose Faithful CoT, a reasoning framework involving two stages: Translation and Problem Solving. This guarantees that the reasoning chain provides a faithful explanation of the final answer.
  arXiv  Detail & Related papers  (2023-01-31T03:04:26Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.