A Benchmark and Framework for Evaluating Next Action Predictions in Spreadsheets
For spreadsheet users and developers of productivity tools, this work provides the first benchmark for next-action prediction, though the dataset size (52 sequences) and incremental nature limit its impact.
This paper introduces a benchmark and evaluation framework for predicting next user actions in spreadsheets, a domain lacking auto-completion tools. The benchmark includes 52 manually curated action sequences and an online evaluation method, with baselines showing that fine-tuned small language models outperform zero-shot LLMs and classical models.
Predictive code completion greatly accelerates how quickly developers work. In spreadsheets, despite being much more common, such auto-completion features are virtually non-existent. To address this gap, we introduce a benchmark for systems that observe a sequence of user actions in a spreadsheet and predict future actions. Two challenges are (1) the absence of edit histories in public spreadsheet corpora and (2) the complex space of spreadsheet actions (spatial, temporal, composite). To address (1), we manually curate 52 sequences of 12K actions that recreate spreadsheets from public corpora, seeded by parametrized heuristics and LLM refinement. To address (2), we propose an online evaluation that expects a prediction after each user action, accepts or rejects that prediction, updates the future actions upon acceptance, and repeats this until the target spreadsheet is obtained. We use multiple baseline predictors (including zero-shot LLMs, fine-tuned SLMs, and classical models) and analyze different properties that our benchmark teaches us, including but not limited to: properties of saved actions and false positives, efficiency, effect of user profiles, effect of triggers, and effect of context.