Tag
This paper proposes an assistive AI agent architecture based on hierarchical compositionality and simple heuristics to resolve ambiguity in object references, outperforming data-driven baselines while supporting adaptation to user preferences.
This paper presents GPTKB 2.0, a large-scale disambiguated knowledge base derived from LLMs, containing 38.4M triples over 1.6M canonical entities. It offers a web interface for browsing, SPARQL/ natural language querying, and auditing fact provenance and disambiguation decisions.
SCICONVBENCH is a benchmark that evaluates LLMs on multi-turn clarification for ill-posed scientific queries across computational science domains, finding that even frontier models struggle with disambiguation and frequently make silent assumptions.