PleaSQLarify: Visual Pragmatic Repair for Natural Language Database Querying

TL;DR

This work operationalizes pragmatic repair by structuring interaction around interpretable decision variables that enable efficient clarification in natural language database interfaces and highlights pragmatic repair as a design principle that fosters effective user control in natural language interfaces.

Abstract

Natural language database interfaces broaden data access, yet they remain brittle under input ambiguity. Standard approaches often collapse uncertainty into a single query, offering little support for mismatches between user intent and system interpretation. We reframe this challenge through pragmatic inference: while users economize expressions, systems operate on priors over the action space that may not align with the users'. In this view, pragmatic repair -- incremental clarification through minimal interaction -- is a natural strategy for resolving underspecification. We present \textsc{PleaSQLarify}, which operationalizes pragmatic repair by structuring interaction around interpretable decision variables that enable efficient clarification. A visual interface complements this by surfacing the action space for exploration, requesting user disambiguation, and making belief updates traceable across turns. In a study with twelve participants, \textsc{PleaSQLarify} helped users recognize alternative interpretations and efficiently resolve ambiguity. Our findings highlight pragmatic repair as a design principle that fosters effective user control in natural language interfaces.

Figures (11)

• Figure 1: Pragmatic repair in HCI, applied to the text-to-SQL task. A misalignment of priors over system actions, i.e., a user not knowing what actions are possible or considered probable by a system, amplifies ambiguity.
• Figure 2: Visualization of the algorithm described in Section \ref{['sec:algorithm']} applied to text-to-SQL. First, an LLM generates diverse outputs, which are then embedded and clustered together. For each cluster, we extract the most characteristic feature based on the lift. Finally, we order decision variables based on expected information gain. Once a user has made a decision, the candidate set is filtered, and the remaining candidates are reclustered.
• Figure 3: Iterative candidate filtering and query population using the proposed algorithm Section \ref{['sec:algorithm']} applied to text-to-SQL. The initial candidate set is iteratively filtered through targeted user feedback on the decision variables proposed by our algorithm until the candidate set consists of a single query, i.e., until the user has identified the query that most closely matches their intent.
• Figure 4: Median per-turn gold-label entropy (top) and functional output similarity (bottom) across three ambiguity types in the AMBROSIA dataset. Clustering-based methods (solid blue) resolve uncertainty more rapidly and converge to functionally coherent hypotheses in fewer turns than baselines (dashed red/orange).
• Figure 5: The visual interactive interface consists of the user's input/utterance field (1), three main analysis views, i.e., the Action Space (2) for exploration, Decision Space (3) for decision making, and Predicted Query (4) for confirmation tasks, and the Predicted Output view (5) showing the predicted result of the database.