EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Toward Exploring Mixed-Initiative Conversation Generation Based on Community Question Answering

Lili Lu, Pranav Kasela, Federico Ravenda, Chuan Meng, Gabriella Pasi, Fabio Crestani

ACM Transactions on Information Systems · 30.06.2026 · 44 (5) · 1-29

DOI: 10.1145/3814610 ↗

Kurz gefasst

Fachartikel in der Zeitschrift ACM Transactions on Information Systems, online erschienen am 11.06.2026. Verfasst von Lili Lu und 5 weiteren Autor:innen. Die Arbeit nennt 81 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Swiss National Science Foundation.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Conversational search addresses users’ information needs through multi-turn and context-aware interactions. Given that user queries are often ambiguous, the use of clarifying questions can effectively reduce uncertainty and enable a mixed-initiative conversational system. However, current datasets for clarifying questions remain limited in the following three aspects: (1) underrepresented multi-turn conversational data, (2) limited diversity, and (3) heavily reliance on crowdsourcing, thereby suffering from limitations such as high annotation cost. To address these issues, we propose a large language model (LLM)-based three-stage framework that relies on an existing community question answering dataset. It encompasses: (1) extracting essential information from the initial user query with the relevant contextual information, (2) generating clarifying questions paired with corresponding answers, and (3) refining conversations to ensure coherence and a natural conversational flow. We assess our multi-stage method against a baseline that directly prompts LLMs to generate conversations in a single-step process, evaluating on an answer retrieval task using recall, precision, normalized discounted cumulative gain and mean average precision. Results show that our three-stage generation approach consistently outperforms the baseline particularly in recall, while also achieving competitive results across other metrics. Human and automatic evaluations further indicate the high quality of generated conversations and fine-tuning on them improves retrieval performance, highlighting the pipeline’s potential.

Förderung

  • Swiss National Science Foundation

Zitieren

APA

Lu, L., Kasela, P., Ravenda, F., Meng, C., Pasi, G., & Crestani, F. (2026). Toward Exploring Mixed-Initiative Conversation Generation Based on Community Question Answering. ACM Transactions on Information Systems, 44(5), 1-29. https://doi.org/10.1145/3814610

Vancouver

Lu L, Kasela P, Ravenda F, Meng C, Pasi G, Crestani F. Toward Exploring Mixed-Initiative Conversation Generation Based on Community Question Answering. ACM Transactions on Information Systems. 2026;44(5):1-29. doi:10.1145/3814610

BibTeX
@article{Lu2026,
  author = {Lu, Lili and Kasela, Pranav and Ravenda, Federico and Meng, Chuan and Pasi, Gabriella and Crestani, Fabio},
  title = {Toward Exploring Mixed-Initiative Conversation Generation Based on Community Question Answering},
  journal = {ACM Transactions on Information Systems},
  year = {2026},
  volume = {44},
  number = {5},
  pages = {1--29},
  doi = {10.1145/3814610}
}
Kostenlos starten →