English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Large Language Models (LLMs) have generated considerable interest and debateregarding their potential emergence of Theory of Mind (ToM). Several recentinquiries reveal a lack of robust ToM in these models and pose a pressingdemand to develop new benchmarks, as current ones primarily focus on differentaspects of ToM and are prone to shortcuts and data leakage. In this positionpaper, we seek to answer two road-blocking questions: (1) How can we taxonomizea holistic landscape of machine ToM? (2) What is a more effective evaluationprotocol for machine ToM? Following psychological studies, we taxonomizemachine ToM into 7 mental state categories and delineate existing benchmarks toidentify under-explored aspects of ToM. We argue for a holistic and situatedevaluation of ToM to break ToM into individual components and treat LLMs as anagent who is physically situated in environments and socially situated ininteractions with humans. Such situated evaluation provides a morecomprehensive assessment of mental states and potentially mitigates the risk ofshortcuts and data leakage. We further present a pilot study in a grid worldsetup as a proof of concept. We hope this position paper can facilitate futureresearch to integrate ToM with LLMs and offer an intuitive means forresearchers to better position their work in the landscape of ToM. Projectpage: https://github.com/Mars-tin/awesome-theory-of-mind

Towards A Holistic Landscape of Situated Theory of Mind in Large Language Models