Tag
The paper distinguishes between revision-driven updates (non-monotonic) and delayed elaboration (monotonic) in incremental narrative interpretation, demonstrating their application through visual narratives.
This paper introduces MT-InfoSeek, a controlled evaluation suite for assessing LLMs' multi-turn information seeking capabilities, revealing that models underestimate missing information and perform poorly with increased underspecification across domains.
This paper introduces a framework for interactive task alignment under ambiguity, formalized as a POMDP, and shows that current LLMs recover intended tasks only 22–32% of the time, lagging behind human performance.