Reasoning with Language Model Prompting: A Survey

By Shuofei Qiao, Yixin Ou, Ningyu Zhang, Yunzhi Yao, Shumin Deng, Chuanqi Tan, Fei Huang, Huajun Chen. 2022

441 citations recorded by the source corpus.

Reasoning, as an essential ability for complex problem-solving, can provide back-end support for various real-world applications, such as medical diagnosis, negotiation, etc. This paper provides a comprehensive survey of cutting-edge research on reasoning with language model prompting. We introduce research works with comparisons and summaries and provide systematic resources to help beginners. We also discuss the potential reasons for emerging such reasoning abilities and highlight future research directions. Resources are available at https://github.com/zjunlp/Prompt4ReasoningPapers (updated periodically).

Subfields: Artificial Intelligence, Natural Language Processing, Prompting & Reasoning

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Natural Language Processing

In Prompting & Reasoning

Citations in the corpus

Augmented Language Models: a Survey (2023, methodology): “Qiao et al. (2022) also propose a survey on reasoning albeit with a focus on prompting.”
A Survey on In-context Learning (2022, background): “There are many pieces of research on CoT prompting strategies (Qiao et al., 2022) including prompt designing and process optimization.”
Self-Polish: Enhance Reasoning in Large Language Models via Problem Refinement (2023, background): “In the context of enhancing the capabilities of large-scale language models, the prompting technique has emerged as one of the most popular approaches, and it offers the advantage of achieving improvements without the need for training (Qiao et al., 2022; Lewkowycz et al., 2022).”
A Multitask, Multilingual, Multimodal Evaluation of ChatGPT on Reasoning, Hallucination, and Interactivity (2023, methodology): “Other works focus on more specific abilities such as mathematical skills (Davis, 2023b), reasoning (Webb et al., 2022a; Qiao et al., 2022).”
Large language models for generative information extraction: a survey (2023, unknown): “They used a transformer encoder-decoder architecture with a pointing mechanism and a dynamic vocabulary of spans and relation types, to capture the structural characteristics and boundaries while grounding the output in the original text.”
Large Language Models are Better Reasoners with Self-Verification (2022, background): “Large language models such as GPT-3 exhibit impressive few-shot learning ability (Lu et al., 2022; Qiao et al., 2022), it requires only filling a few exemplars into context as prompts and without the need for finetuning on a dataset of training examples.”
Tool learning with large language models: a survey (2024, unknown): “Meanwhile, we also acknowledge the foundational contributions of earlier perspective papers like those by Mialon et al. (2023) [45] and Qin et al. (2023) [16], which initially highlighted the promising opportunities that tools present to enhance LLMs capabilities.”
MoreHopQA: More Than Multi-hop Reasoning (2024, background): “In Qiao et al. (2023), five types of reasoning are explored: arithmetic reasoning, commonsense reasoning, symbolic reasoning, logical reasoning, and multimodal reasoning.”
Hallucination of Multimodal Large Language Models: A Survey (2024, unknown): “Recently, the emergence of large language models (LLMs) [29, 81, 85, 99, 132] has dominated a wide range of tasks in natural language processing (NLP), achieving unprecedented progress in language understanding [39, 47], generation [128, 140] and reasoning [20, 58, 87, 107, 115].”
Editing Large Language Models: Problems, Methods, and Opportunities (2023, unknown): “Large language models (LLMs) have demonstrated a remarkable capacity for understanding and generating human-like text (Brown et al., 2020; OpenAI, 2023; Anil et al., 2023; Touvron et al., 2023; Qiao et al., 2022; Zhao et al., 2023).”
A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions (2023, unknown): “LLMs typically adopt a transformer-based architecture following the paradigm established by GPT (Radford et al., 2018, 2019; Brown et al., 2020), where they acquire representations through a causal language modeling objective, a framework exemplified by models such as OPT(Zhang et al., 2022), Falcon”
Making Large Language Models Better Reasoners with Alignment (2023, unknown): “Reasoning is a cognitive process that involves utilizing evidence to reach a well-founded conclusion (Qiao et al., 2023; Huang & Chang, 2023).”
A Survey of Large Language Models (2023, unknown): “Complex reasoning refers to the ability of understanding and utilizing supporting evidence or logic to derive conclusions or make decisions [51, 52].”