mlsanityData to 14 Oct 2026

Enhancing Zero-shot Chain of Thought Prompting via Uncertainty-Guided Strategy Selection

arXiv 2412.00353 ↗First posted 30 Nov 2024cs.CL cs.AIcited by 4

On the map: LLM reasoning → Prompting and chain-of-thought reasoning

Abstract (arXiv)

Chain-of-thought (CoT) prompting has significantly enhanced the capability of large language models (LLMs) by structuring their reasoning processes. However, existing methods face critical limitations: handcrafted demonstrations require extensive human expertise, while trigger phrases are prone to inaccuracies. In this paper, we propose the Zero-shot Uncertainty-based Selection (ZEUS) method, a novel approach that improves CoT prompting by utilizing uncertainty estimates to select effective demonstrations without needing access to model parameters. Unlike traditional methods, ZEUS offers high sensitivity in distinguishing between helpful and ineffective questions, ensuring more precise and reliable selection. Our extensive evaluation shows that ZEUS consistently outperforms existing CoT strategies across four challenging reasoning benchmarks, demonstrating its robustness and scalability.

Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Placed in Prompting and chain-of-thought reasoning, one of 17 directions in LLM reasoning. Builds on 17 of its 46 references that are in the map. First posted on arXiv 30 Nov 2024.

Builds on

17 of 46 references.

Closest ancestors · 1

Same direction, newest first

  1. 2023Active Prompting with Chain-of-Thought for Large Language Models23 Feb

Other references · 16

  1. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 14,132
  2. 2021Training Verifiers to Solve Math Word Problemscited by 10,109
  3. 2023Tree of Thoughts: Deliberate Problem Solving with Large Language Modelscited by 3,211
  4. 2023Mistral 7Bcited by 3,164
  5. 2024Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phonecited by 1,917
  6. 2022LaMDA: Language Models for Dialog Applicationscited by 1,220
  7. 2021Scaling Language Models: Methods, Analysis & Insights from Training Gophercited by 1,202
  8. 2023Encouraging Divergent Thinking in Large Language Models through Multi-Agent Debatecited by 1,011
  9. 2020Beyond Accuracy: Behavioral Testing of NLP models with CheckListcited by 1,006
  10. 2023Semantic Uncertainty: Linguistic Invariances for Uncertainty Estimation in Natural Language Generationcited by 819
  11. 2023Unleashing the Emergent Cognitive Synergy in Large Language Models: A Task-Solving Agent through Multi-Persona Self-Collaborationcited by 251
  12. 2022Holistic Evaluation of Language Modelscited by 131
4 more
  1. 2024Benchmarking Uncertainty Quantification Methods for Large Language Models with LM-Polygraphcited by 105
  2. 2024Uncertainty-Based Abstention in LLMs Improves Safety and Reduces Hallucinationscited by 54
  3. 2023MindGames: Targeting Theory of Mind in Large Language Models with Dynamic Epistemic Modal Logiccited by 18
  4. 2024ActiveLLM: Large Language Model-based Active Learning for Textual Few-Shot Scenarioscited by 18

Built on by

Cited by year

Citing papers per year: 2025: 4.

4 papers.

  1. 2025Unveiling the Key Factors for Distilling Chain-of-Thought Reasoningcited by 40
  2. 2025RL of Thoughts: Navigating LLM Reasoning with Inference-time Reinforcement Learningcited by 16
  3. 2025Efficient Model Selection for Time Series Forecasting via LLMscited by 4
  4. 2025Instruction-Tuning Open-Weight Language Models for BPMN Model Generationcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024Zero-Shot Chain-of-Thought Reasoning Guided by Evolutionary Algorithms in Large Language Models
  2. 2024Instance-adaptive Zero-shot Chain-of-Thought Prompting
  3. 2023An automatically discovered chain-of-thought prompt generalizes to novel models and datasets
  4. 2024Enhancing Chain of Thought Prompting in Large Language Models via Reasoning Patterns
  5. 2024Unveiling the Statistical Foundations of Chain-of-Thought Prompting Methods
  6. 2026Diverge to Induce Prompting: Multi-Rationale Induction for Zero-Shot Reasoning
  7. 2023Plan-and-Solve Prompting: Improving Zero-Shot Chain-of-Thought Reasoning by Large Language Models
  8. 2024ChainLM: Empowering Large Language Models with Improved Chain-of-Thought Prompting