Journal Article10.18653/v1/2023.acl-long.294
Reasoning with Language Model Prompting: A Survey
Shuofei Qiao,Yixin Ou,Ningyu Zhang,Xiang Chen,Yunzhi Yao,Shumin Deng,Chuanqi Tan,Fei Huang,Huajun Chen +8 more
- 01 Jan 2023
TL;DR: A survey on reasoning with language model prompting explores the latest research on reasoning abilities in language models and provides a comprehensive overview of the field.
read more
Abstract: 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 1 .
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
A Multitask, Multilingual, Multimodal Evaluation of ChatGPT on Reasoning, Hallucination, and Interactivity
Yejin Bang,Samuel Cahyawijaya,Nayeon Lee,Wujiao Dai,Dan Su,Bryan Wilie,Holy Lovenia,Ziwei Ji,Tiezheng Yu,Willy Chung,V. Quyet,Yan Xu,Pascale Fung +12 more
- 01 Jan 2023
TL;DR: A multitask, multilingual, multimodal evaluation of ChatGPT on reasoning, hallucination, and interactivity demonstrates its capabilities across various tasks.
Graph of Thoughts: Solving Elaborate Problems with Large Language Models
Maciej Besta,Nils Blach,Ales Kubicek,Robert Gerstenberger,Lukas Gianinazzi,Joanna Gajda,Tomasz Lehmann,Michal Podstawski,H. Niewiadomski,P. Nyczyk,Torsten Hoefler +10 more
TL;DR: Graph of Thoughts is introduced: a framework that advances prompting capabilities in large language models (LLMs) beyond those offered by paradigms such as Chain-of-Thought or Tree of Thoughts, and is ensured that GoT is extensible with new thought transformations and thus can be used to spearhead new prompting schemes.
Towards Reasoning in Large Language Models: A Survey
Jie Huang,Kevin Chen-Chuan Chang +1 more
- 01 Jan 2023
TL;DR: The survey explores the reasoning abilities of large language models and investigates techniques for improving and eliciting reasoning abilities in these models.
Graph of Thoughts: Solving Elaborate Problems with Large Language Models
Maciej Besta,Nils Blach,Ales Kubicek,Robert Gerstenberger,Michał Podstawski,Lukas Gianinazzi,Janusz Gajda,Tomasz P. Lehmann,H. Niewiadomski,Piotr Nyczyk,Torsten Hoefler +10 more
TL;DR: Graph of Thoughts (GoT) is a framework that advances prompting capabilities in large language models by modeling information generated by LLMs as a graph. GoT enables combining arbitrary LLM thoughts into synergistic outcomes, distilling the essence of whole networks of thoughts, and enhancing thoughts using feedback loops.
LLMs for knowledge graph construction and reasoning: recent capabilities and future opportunities
Yuqi Zhu,Xiaohan Wang,Jing Chen,Shuofei Qiao,Yixin Ou,Yunzhi Yao,Shumin Deng,Huajun Chen,Ningyu Zhang +8 more
34
References
•Posted Content
Proximal Policy Optimization Algorithms
TL;DR: A new family of policy gradient methods for reinforcement learning, which alternate between sampling data through interaction with the environment, and optimizing a "surrogate" objective function using stochastic gradient ascent, are proposed.
18K
MuJoCo: A physics engine for model-based control
Emanuel Todorov,Tom Erez,Yuval Tassa +2 more
- 24 Dec 2012
TL;DR: A new physics engine tailored to model-based control, based on the modern velocity-stepping approach which avoids the difficulties with spring-dampers, which can compute both forward and inverse dynamics.
A learning algorithm for boltzmann machines
TL;DR: A general parallel search method is described, based on statistical mechanics, and it is shown how it leads to a general learning rule for modifying the connection strengths so as to incorporate knowledge about a task domain in an efficient way.
4.1K
Training language models to follow instructions with human feedback
04 Mar 2022
TL;DR: The authors used reinforcement learning from human feedback to align language models with user intent on a wide range of tasks by fine-tuning with human feedback, and showed that the resulting models showed improvements in truthfulness and reductions in toxic output generation while having minimal performance regressions on public NLP datasets.
Chain-of-Thought Prompting Elicits Reasoning in Large Language Models
27 Jan 2022
TL;DR: The authors explore how generating a chain of thought (a series of intermediate reasoning steps) significantly improves the ability of large language models to perform complex reasoning, and demonstrate that such reasoning abilities emerge naturally in sufficiently large language model via a simple method called chain-of-thought prompting, where a few chains of thought demonstrations are provided as exemplars in prompting.
1.9K