Chain-of-Probe: Examining the Necessity and Accuracy of CoT Step-by-Step
Open Access
- 1 January 2025
- conference paper
- Published by Association for Computational Linguistics (ACL)
- p. 2586-2606
Abstract
Zezhong Wang, Xingshan Zeng, Weiwen Liu, Yufei Wang, Liangyou Li, Yasheng Wang, Lifeng Shang, Xin Jiang, Qun Liu, Kam-Fai Wong. Findings of the Association for Computational Linguistics: NAACL 2025. 2025.Keywords
All Related Versions
This publication has 15 references indexed in Scilit:
- Making Reasoning Matter: Measuring and Improving Faithfulness of Chain-of-Thought Reasoning2024
- On Measuring Faithfulness or Self-consistency of Natural Language Explanations2024
- A Chain-of-Thought Is as Strong as Its Weakest Link: A Benchmark for Verifiers of Reasoning Chains2024
- Whispers of Doubt Amidst Echoes of Triumph in NLP Robustness2024
- Faithful Chain-of-Thought Reasoning2023
- What Makes Chain-of-Thought Prompting Effective? A Counterfactual Study2023
- Towards Mitigating LLM Hallucination via Self Reflection2023
- Towards Understanding Chain-of-Thought Prompting: An Empirical Study of What Matters2023
- Chain-Of-Thought Prompting Elicits Reasoning in Large Language Models2022
- Maieutic Prompting: Logically Consistent Reasoning with Recursive Explanations2022