Federated Topic-Preference Learning for Knowledge-Grounded Chat with Differential Privacy
Journal of Technology Informatics and Engineering · 25.08.2025 · 4 (2) · 385-401
DOI: 10.51903/jtie.v4i2.502 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Technology Informatics and Engineering, online erschienen am 25.08.2025. Verfasst von Meng-Ju Kuo und 2 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY-SA 4.0).
Abstract (Originalsprache)
Retrieval-augmented approaches have become central in knowledge-grounded dialogue systems, yet incorporating topical preferences remains difficult due to privacy constraints on user interaction data. This study introduces a lightweight federated topic-preference (FedTP) mechanism that models session-level preferences without centralizing raw data and uses client-level differential privacy (DP). Using the Topical-Chat dataset (8,628 conversations), each conversation is treated as a client, and evidence routing is framed as selecting relevant knowledge snippets based on dialogue context. The proposed method augments a TF-IDF relevance score with a small preference-based component derived from both local session distributions and a DP-aggregated global prior. Experimental results on 9,553 grounded test turns show a consistent but limited improvement in evidence hit rate, from 0.6167 to 0.6194. The small optimal preference weight (λ = 0.005) indicates that the preference signal mainly influences decisions when competing candidates have similar relevance scores, rather than substantially altering routing behavior. A privacy–utility analysis under Gaussian DP (ε ranging from 9.69 to 0.606, δ = 1e−5) shows negligible changes in performance, which is expected given the large number of clients in a one-shot aggregation setting. Additional metrics remain largely stable, suggesting that the method affects selection margins rather than overall alignment. These findings suggest that federated preference aggregation can provide a modest, privacy-preserving bias for evidence routing, but its practical impact remains incremental and context-dependent.
Zitieren
APA
Kuo, M., Zheng, D., & Hires, J. (2025). Federated Topic-Preference Learning for Knowledge-Grounded Chat with Differential Privacy. Journal of Technology Informatics and Engineering, 4(2), 385-401. https://doi.org/10.51903/jtie.v4i2.502
Vancouver
Kuo M, Zheng D, Hires J. Federated Topic-Preference Learning for Knowledge-Grounded Chat with Differential Privacy. Journal of Technology Informatics and Engineering. 2025;4(2):385-401. doi:10.51903/jtie.v4i2.502
BibTeX
@article{Kuo2025,
author = {Kuo, Meng-Ju and Zheng, Daren and Hires, Julie},
title = {Federated Topic-Preference Learning for Knowledge-Grounded Chat with Differential Privacy},
journal = {Journal of Technology Informatics and Engineering},
year = {2025},
volume = {4},
number = {2},
pages = {385--401},
doi = {10.51903/jtie.v4i2.502}
}
EUVIMED