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

Human beings are social creatures. We routinely reason about other agents,and a crucial component of this social reasoning is inferring people's goals aswe learn about their actions. In many settings, we can perform intuitive butreliable goal inference from language descriptions of agents, actions, and thebackground environments. In this paper, we study this process of languagedriving and influencing social reasoning in a probabilistic goal inferencedomain. We propose a neuro-symbolic model that carries out goal inference fromlinguistic inputs of agent scenarios. The "neuro" part is a large languagemodel (LLM) that translates language descriptions to code representations, andthe "symbolic" part is a Bayesian inverse planning engine. To test our model,we design and run a human experiment on a linguistic goal inference task. Ourmodel closely matches human response patterns and better predicts humanjudgements than using an LLM alone.

The Neuro-Symbolic Inverse Planning Engine (NIPE): Modeling Probabilistic Social Inferences from Linguistic Inputs