Generated Knowledge Prompting for Commonsense Reasoning
It remains an open question whether incorporating external knowledge benefits commonsense reasoning while maintaining the flexibility of pretrained sequence models. To investigate this question, we develop generated knowledge prompting, which consists of generating knowledge from a language model, then providing the knowledge as additional input when answering a question. Our method does not require task-specific supervision for knowledge integration, or access to a structured knowledge base, yet it improves performance of large-scale, state-of-the-art models on four commonsense reasoning tasks, achieving state-of-the-art results on numerical commonsense (NumerSense), general commonsense (CommonsenseQA 2.0), and scientific commonsense (QASC) benchmarks. Generated knowledge prompting highlights large-scale language models as flexible sources of external knowledge for improving commonsense reasoning. Our code is available at https://github.com/liujch1998/GKP
Code (1)
Tasks
Language ModelingLanguage ModellingOpen-Ended Question AnsweringSimilar Papers 제목 키워드 기반
Generated Knowledge Prompting for Commonsense Reasoning
It remains an open question whether incorporating external knowledge benefits commonsense reasoning while maintaining the flexibility of pretrained sequence models. To investigate this question, we develop generated know…
Language ModelingLanguage ModellingOpen-Ended Question AnsweringConstraintChecker: A Plugin for Large Language Models to Reason on Commonsense Knowledge Bases
Reasoning over Commonsense Knowledge Bases (CSKB), i.e. CSKB reasoning, has been explored as a way to acquire new commonsense knowledge based on reference knowledge in the original CSKBs and external prior knowledge. Des…
Prompt EngineeringZero-Shot LearningBoosting Language Models Reasoning with Chain-of-Knowledge Prompting
Recently, Chain-of-Thought (CoT) prompting has delivered success on complex reasoning tasks, which aims at designing a simple prompt like ``Let's think step by step'' or multiple in-context exemplars with well-designed r…
Arithmetic ReasoningWhen More Is Less: A Systematic Analysis of Spatial and Commonsense Information for Visual Spatial Reasoning
Visual spatial reasoning (VSR) remains challenging for modern vision-language models (VLMs), despite advances in multimodal architectures. A common strategy is to inject additional information at inference time, such as …
Multimodal ReasoningSpatial ReasoningPHALM: Building a Knowledge Graph from Scratch by Prompting Humans and a Language Model
Despite the remarkable progress in natural language understanding with pretrained Transformers, neural language models often do not handle commonsense knowledge well. Toward commonsense-aware models, there have been atte…
Language ModelingLanguage ModellingLarge Language ModelNatural Language Understanding