Reasoning with Language Model Prompting: A Survey (2022-12-19T00:00:00.000000Z)

TL;DR

This paper provides a comprehensive survey of cutting-edge research on reasoning with language model prompting with comparisons and summaries and provides systematic resources to help beginners.

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. Resources are available at https://github.com/zjunlp/Prompt4ReasoningPapers (updated periodically).

Authors

Huajun Chen

8 papers

Ningyu Zhang

12 papers

Shumin Deng

11 papers

TL;DR

Abstract

Authors

References218 items

Large Language Models

Holistic Evaluation of Language Models

Clever Hans or Neural Theory of Mind? Stress Testing Social Reasoning in Large Language Models

Abstract Meaning Representation-Based Logic-Driven Data Augmentation for Logical Reasoning

Answering Questions by Meta-Reasoning over Multiple Chains of Thought

Boosting Theory-of-Mind Performance in Large Language Models via Prompting

Chameleon: Plug-and-Play Compositional Reasoning with Large Language Models

Tool Learning with Foundation Models

Why think step-by-step? Reasoning emerges from the locality of experience

REFINER: Reasoning Feedback on Intermediate Representations

A Survey of Large Language Models

Self-Refine: Iterative Refinement with Self-Feedback

MM-REACT: Prompting ChatGPT for Multimodal Reasoning and Action

GPT-4 Technical Report

ViperGPT: Visual Inference via Python Execution for Reasoning

Visual ChatGPT: Talking, Drawing and Editing with Visual Foundation Models

MathPrompter: Mathematical Reasoning using Large Language Models

Language Is Not All You Need: Aligning Perception with Language Models

Automatic Prompt Augmentation and Selection with Chain-of-Thought from Labeled Data

Toolformer: Language Models Can Teach Themselves to Use Tools

Multimodal Chain-of-Thought Reasoning in Language Models

Synthetic Prompting: Generating Chain-of-Thought Demonstrations for Large Language Models

Large Language Models are Versatile Decomposers: Decomposing Evidence and Questions for Table-based Reasoning

Faithful Chain-of-Thought Reasoning

Specializing Smaller Language Models towards Multi-Step Reasoning

Editing Language Model-based Knowledge Graph Embeddings

See, Think, Confirm: Interactive Prompting Between Vision and Language Models for Knowledge-based Visual Reasoning

Iterated Decomposition: Improving Science Q&A by Supervising Reasoning Processes

Rethinking with Retrieval: Faithful Large Language Model Inference

Language Models as Inductive Reasoners

Large Language Models Are Reasoning Teachers

LAMBADA: Backward Chaining for Automated Reasoning in Natural Language

Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questions

Towards Reasoning in Large Language Models: A Survey

A Survey of Deep Learning for Mathematical Reasoning

Emergent analogical reasoning in large language models

Evaluating Step-by-Step Reasoning through Symbolic Verification

Teaching Small Language Models to Reason

ALERT: Adapt Language Models to Reasoning Tasks

On Second Thought, Let’s Not Think Step by Step! Bias and Toxicity in Zero-Shot Reasoning

Prompting Is Programming: A Query Language for Large Language Models

Successive Prompting for Decomposing Complex Questions

What learning algorithm is in-context learning? Investigations with linear models

TSGP: Two-Stage Generative Prompting for Unsupervised Commonsense Question Answering

Program of Thoughts Prompting: Disentangling Computation from Reasoning for Numerical Reasoning Tasks

PAL: Program-aided Language Models

Teaching Algorithmic Reasoning via In-context Learning

Finding Skill Neurons in Pre-trained Transformer-based Language Models

PINTO: Faithful Language Reasoning Using Prompt-Generated Rationales

Neural Theory-of-Mind? On the Limits of Social Intelligence in Large LMs

Scaling Instruction-Finetuned Language Models

Large Language Models Can Self-Improve

Large Language Models are few(1)-shot Table Reasoners

Explanations from Large Language Models Make Small Reasoners Better

Language Models of Code are Few-Shot Commonsense Learners

Mind's Eye: Grounded Language Model Reasoning through Simulation

Automatic Chain of Thought Prompting in Large Language Models

Measuring and Narrowing the Compositionality Gap in Language Models

Language Models are Multilingual Chain-of-Thought Reasoners

Binding Language Models in Symbolic Languages

Rainier: Reinforced Knowledge Introspector for Commonsense Question Answering

Decomposed Prompting: A Modular Approach for Solving Complex Tasks

Complexity-Based Prompting for Multi-Step Reasoning

Multimodal Analogical Reasoning over Knowledge Graphs

Dynamic Prompt Learning via Policy Gradient for Semi-structured Mathematical Reasoning

Learn to Explain: Multimodal Reasoning via Thought Chains for Science Question Answering

Socially situated artificial intelligence enables learning from human interaction

Selective Annotation Makes Language Models Better Few-Shot Learners

Faithful Reasoning Using Large Language Models

Multi-Step Deductive Reasoning Over Natural Language: An Empirical Study on Out-of-Distribution Generalisation

Language Model Cascades

Exploring Length Generalization in Large Language Models

Rationale-Augmented Ensembles in Language Models

Solving Quantitative Reasoning Problems with Language Models

Emergent Abilities of Large Language Models

Memory-Based Model Editing at Scale