PulseExploreJournal ClubDebatesTrendingResearchersJournals
Instagram
HomeExploreJournal ClubTrending
Synapse
⌘+K
Synapse
February 2, 20261 citationsOpen Access

AnthroSet: a Challenge Dataset for Anthropomorphic Language Detection

View Full Paper
DLDorielle LonkeUniversity of AmsterdamJBJ.; id_orcid 0000-0003-2221-0554 BloemAmsterdam University CollegePSPia SommerauerVrije Universiteit Amsterdam

Key Points

  • The research aims to establish a dataset for detecting anthropomorphic language in AI and critique existing detection methods.
  • Developed a dataset called AnthroSet containing 600 annotated utterances
  • Evaluated current methods for anthropomorphism and animacy detection
  • Assessed the limitations of masked language models in detecting anthropomorphic language
  • Highlighted the constraints of masked language models in this context
  • Found that existing methods struggle with anthropomorphizing terminology
  • Identified a need for clearer definitions and targeted approaches in anthropomorphism detection

Abstract

This paper addresses the challenge of detecting anthropomorphic language in AI research. We introduce AnthroSet, a novel dataset of 600 manually annotated utterances covering various linguistic structures. Through the evaluation of two current approaches for anthropomorphism and atypical animacy detection, we highlight the limitations of a masked language model approach, arising from masking constraints as well as increasingly anthropomorphizing AIrelated terminology. Our findings underscore the need for more targeted methods and a robust definition of anthropomorphism.

Ask AI
Helpful
Bookmark
Share
View Full Paper

Cite This Study

Lonke et al. (2025) studied this question.

synapsesocial.com/papers/6980fff5c1c9540dea812dc0https://doi.org/10.26615/978-954-452-101-1-003
Ask AI
Helpful
Bookmark
Share
View Full Paper