Metraipolis › archive › dc_ed431fa3a14e
PragAlign: Feedback-Guided Pragmatic Alignment for Controlled Synthetic Dialogue Generation — arXiv:2609.02480
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.02480
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-17T04:16:51.751Z
- SHA-256 of the archived text
93b1b2833a09bcaf273c10ce0022525198c8f06eadd873171e3df35b87529869- Stable URL of this page
https://metraipolis.com/documento/dc_ed431fa3a14e
How to cite
PragAlign: Feedback-Guided Pragmatic Alignment for Controlled Synthetic Dialogue Generation — arXiv:2609.02480 — arXiv (en), https://arxiv.org/abs/2609.02480 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ed431fa3a14e (Metraipolis archive dc_ed431fa3a14e, sha256 93b1b2833a09bcaf273c10ce0022525198c8f06eadd873171e3df35b87529869)
BibTeX
@misc{dced431fa3a14e,
title = {PragAlign: Feedback-Guided Pragmatic Alignment for Controlled Synthetic Dialogue Generation — arXiv:2609.02480},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.02480},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ed431fa3a14e; sha256 93b1b2833a09bcaf273c10ce0022525198c8f06eadd873171e3df35b87529869},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.02480. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
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 alignment, emotion alignment, coherence, fluency, and aggregate quality, then provides criterion-specific feedback for up to three refinement rounds. On 800 matched dialogue specifications, PragAlign achieves 99.50\% evaluator-defined acceptance, compared with 72.25\% for one-shot generation and 95.88\% for repeated generation without structured feedback. This indicates that repeated attempts account for much of the gain over one-shot generation, while structured feedback primarily improves last-mile multi-constraint satisfaction rather than broad average quality. Refinement gains are concentrated in emotion alignment, which is also the dominant failure mode in ablations. A separate human evaluation of 1,200 generated dialogues shows that intent expression and dialogue flow are highly recognizable to annotators, while emotion appropriateness is less stable and more subjective. These results support PragAlign as a quality-control framework for improving evaluator-defined communicative constraint satisfaction, while showing that affective realization and independent human-perceived quality remain open challenges. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-03 in cs.CL). Categorie arXiv: Computation and Language (cs.CL). Pagina del lavoro: https://arxiv.org/abs/2609.02480 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-17T03:26:49.795Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-09-03?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).