Search papers, labs, and topics across Lattice.
This paper introduces ARCS, a novel text-to-SQL benchmark designed to address the critical challenge of ambiguity in real-world user queries by proposing a paradigm of structured disambiguation over free-form dialogue. By creating a corpus with detailed annotations of ambiguity points, interpretations, and SQL queries across real-world databases, the authors highlight the significant performance drop in current LLMs, with gpt-6-sol achieving only 51% execution accuracy. The findings underscore the need for more robust ambiguity resolution mechanisms to improve
Key contribution not extracted.
As text-to-SQL systems move beyond demonstrations toward real-world deployment, ambiguity in user questions becomes a primary source of errors. Such ambiguities are often subtle, domain- or data-specific, and can silently cause system outputs to deviate from the user's true intent. Ambiguity is traditionally addressed through conversational clarification, which is often inefficient, cognitively demanding, and poorly aligned with real-world user workflows. We propose structured disambiguation, a new paradigm in which ambiguity is resolved through explicit, constrained interactions rather than free-form dialogue. We construct ARCS (Ambiguity Resolution Corpus for SQL), the first text-to-SQL benchmark featuring naturally occurring, unconstrained ambiguities over real-world databases, with complete annotations of all valid ambiguity points, interpretations, and SQL queries. Experimental results show that text-to-SQL remains challenging in the presence of ambiguity: gpt-6-sol achieves only 51% end-to-end execution accuracy, and no open-source model exceeds 27%.
