PU-GEN: Enhancing generative commonsense reasoning for language models with human-centered knowledge

Jaehyung Seo, Dongsuk Oh, Sugyeong Eo, Chanjun Park, Kisu Yang, Hyeonseok Moon, Kinam Park, Heuiseok Lim

Research output: Contribution to journalArticlepeer-review

2 Citations (Scopus)


Generative commonsense reasoning refers to the ability of a language model to generate a sentence with a given concept-set based on compositional generalization and commonsense reasoning. In the CommonGen challenge, which evaluates the capability of generative commonsense reasoning, language models continue to exhibit low performances and struggle to leverage knowledge representation from humans. Therefore, we propose PU-GEN to leverage human-centered knowledge in language models to enhance compositional generalization and commonsense reasoning considering the human language generation process. To incorporate human-centered knowledge, PU-GEN reinterprets two linguistic philosophies from Wittgenstein: picture theory and use theory. First, we retrieve scene knowledge to reflect picture theory such that a model can describe a general situation as if it were being painted. Second, we extend relational knowledge to consider use theory for understanding various contexts. PU-GEN demonstrates superior performance in qualitative and quantitative evaluations over baseline models in CommonGen and generates convincing evidence for CommonsenseQA. Moreover, it outperforms the state-of-the-art model used in the previous CommonGen challenge.

Original languageEnglish
Article number109861
JournalKnowledge-Based Systems
Publication statusPublished - 2022 Nov 28


  • Commonsense reasoning
  • Human-centered knowledge
  • Language model
  • Text generation

ASJC Scopus subject areas

  • Software
  • Management Information Systems
  • Information Systems and Management
  • Artificial Intelligence


Dive into the research topics of 'PU-GEN: Enhancing generative commonsense reasoning for language models with human-centered knowledge'. Together they form a unique fingerprint.

Cite this