paperSeptember 2026Unreviewed

PragAlign: Feedback-Guided Pragmatic Alignment for Controlled Synthetic Dialogue Generation

Smitha Muthya Sudheendra, Jaideep Srivastava

Abstract

Synthetic dialogue generation can support research in privacy-restricted service settings, but generated conversations must preserve communicative intent, affective meaning, and natural dialogue flow. We introduce PragAlign, a feedback-guided framework for controlled synthetic dialogue generation conditioned on service context, target intent, and target emotion, with auxiliary trait-style controls. PragAlign uses a generate--evaluate--revise loop in which an LLM-based evaluator scores intent ali

Cite

@misc{sudheendra2026pragalign,
  title = {{PragAlign: Feedback-Guided Pragmatic Alignment for Controlled Synthetic Dialogue Generation}},
  author = {Smitha Muthya Sudheendra and Jaideep Srivastava},
  year = {2026},
  month = sep,
  eprint = {2609.02480},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2609.02480}
}