When do you need Chain-of-Thought Prompting for ChatGPT?

• URL: http://arxiv.org/abs/2304.03262v2
• Date: Tue, 18 Apr 2023 14:45:18 GMT
• Title: When do you need Chain-of-Thought Prompting for ChatGPT?
• Authors: Jiuhai Chen, Lichang Chen, Heng Huang, Tianyi Zhou
• Abstract summary: Chain-of-Thought (CoT) prompting can effectively elicit complex multi-step reasoning from Large Language Models(LLMs) It is not clear whether CoT is still effective on more recent instruction finetuned (IFT) LLMs such as ChatGPT.
• Score: 87.45382888430643
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Chain-of-Thought (CoT) prompting can effectively elicit complex multi-step reasoning from Large Language Models~(LLMs). For example, by simply adding CoT instruction ``Let's think step-by-step'' to each input query of MultiArith dataset, GPT-3's accuracy can be improved from 17.7\% to 78.7\%. However, it is not clear whether CoT is still effective on more recent instruction finetuned (IFT) LLMs such as ChatGPT. Surprisingly, on ChatGPT, CoT is no longer effective for certain tasks such as arithmetic reasoning while still keeping effective on other reasoning tasks. Moreover, on the former tasks, ChatGPT usually achieves the best performance and can generate CoT even without being instructed to do so. Hence, it is plausible that ChatGPT has already been trained on these tasks with CoT and thus memorized the instruction so it implicitly follows such an instruction when applied to the same queries, even without CoT. Our analysis reflects a potential risk of overfitting/bias toward instructions introduced in IFT, which becomes more common in training LLMs. In addition, it indicates possible leakage of the pretraining recipe, e.g., one can verify whether a dataset and instruction were used in training ChatGPT. Our experiments report new baseline results of ChatGPT on a variety of reasoning tasks and shed novel insights into LLM's profiling, instruction memorization, and pretraining dataset leakage.

Related papers

• 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)
• Can Separators Improve Chain-of-Thought Prompting? [10.398343318429367]
  Chain-of-thought (CoT) prompting is a simple and effective method for improving the reasoning capabilities of Large Language Models (LLMs) Inspired by human cognition, we introduce COT-SEP, a method that strategically employs separators at the end of each exemplar in CoT prompting.
  arXiv  Detail & Related papers  (2024-02-16T12:46:16Z)
• Fewer is More: Boosting LLM Reasoning with Reinforced Context Pruning [31.110005898556892]
  Large Language Models (LLMs) have shown impressive capabilities, yet they still struggle with math reasoning. We propose CoT-Influx, a novel approach that pushes the boundary of few-shot Chain-of-Thoughts (CoT) learning. CoT-Influx employs a coarse-to-fine pruner to maximize the input of effective and concise CoT examples.
  arXiv  Detail & Related papers  (2023-12-14T13:03:13Z)
• Exploring ChatGPT's Capabilities on Vulnerability Management [56.4403395100589]
  We explore ChatGPT's capabilities on 6 tasks involving the complete vulnerability management process with a large-scale dataset containing 70,346 samples. One notable example is ChatGPT's proficiency in tasks like generating titles for software bug reports. Our findings reveal the difficulties encountered by ChatGPT and shed light on promising future directions.
  arXiv  Detail & Related papers  (2023-11-11T11:01:13Z)
• Investigating the Effectiveness of Task-Agnostic Prefix Prompt for Instruction Following [44.701091969256055]
  We present our finding that prepending a Task-Agnostic Prefix Prompt (TAPP) to the input improves the instruction-following ability of various Large Language Models (LLMs) during inference. We observe that both base LLMs (i.e. not fine-tuned to follow instructions) and instruction-tuned models benefit from TAPP, resulting in 34.58% and 12.26% improvement on average.
  arXiv  Detail & Related papers  (2023-02-28T16:06:35Z)
• A Multitask, Multilingual, Multimodal Evaluation of ChatGPT on Reasoning, Hallucination, and Interactivity [79.12003701981092]
  We carry out an extensive technical evaluation of ChatGPT using 23 data sets covering 8 different common NLP application tasks. We evaluate the multitask, multilingual and multi-modal aspects of ChatGPT based on these data sets and a newly designed multimodal dataset. ChatGPT is 63.41% accurate on average in 10 different reasoning categories under logical reasoning, non-textual reasoning, and commonsense reasoning.
  arXiv  Detail & Related papers  (2023-02-08T12:35:34Z)
• Is ChatGPT a General-Purpose Natural Language Processing Task Solver? [113.22611481694825]
  Large language models (LLMs) have demonstrated the ability to perform a variety of natural language processing (NLP) tasks zero-shot. Recently, the debut of ChatGPT has drawn a great deal of attention from the natural language processing (NLP) community. It is not yet known whether ChatGPT can serve as a generalist model that can perform many NLP tasks zero-shot.
  arXiv  Detail & Related papers  (2023-02-08T09:44:51Z)
• Towards Understanding Chain-of-Thought Prompting: An Empirical Study of What Matters [82.84696222087396]
  Chain-of-Thought (CoT) prompting can dramatically improve the multi-step reasoning abilities of large language models (LLMs) We show that CoT reasoning is possible even with invalid demonstrations.
  arXiv  Detail & Related papers  (2022-12-20T05:20:54Z)

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.