Salvato in:
| Autori principali: | , , , , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | https://arxiv.org/abs/2504.20624 |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866912353354776576 |
|---|---|
| author | Niu, Zihan Xie, Zheyong Cao, Shaosheng Lu, Chonggang Ye, Zheyu Xu, Tong Liu, Zuozhu Gao, Yan Chen, Jia Xu, Zhe Wu, Yi Hu, Yao |
| author_facet | Niu, Zihan Xie, Zheyong Cao, Shaosheng Lu, Chonggang Ye, Zheyu Xu, Tong Liu, Zuozhu Gao, Yan Chen, Jia Xu, Zhe Wu, Yi Hu, Yao |
| contents | Social chatbots have become essential intelligent companions in daily scenarios ranging from emotional support to personal interaction. However, conventional chatbots with passive response mechanisms usually rely on users to initiate or sustain dialogues by bringing up new topics, resulting in diminished engagement and shortened dialogue duration. In this paper, we present PaRT, a novel framework enabling context-aware proactive dialogues for social chatbots through personalized real-time retrieval and generation. Specifically, PaRT first integrates user profiles and dialogue context into a large language model (LLM), which is initially prompted to refine user queries and recognize their underlying intents for the upcoming conversation. Guided by refined intents, the LLM generates personalized dialogue topics, which then serve as targeted queries to retrieve relevant passages from RedNote. Finally, we prompt LLMs with summarized passages to generate knowledge-grounded and engagement-optimized responses. Our approach has been running stably in a real-world production environment for more than 30 days, achieving a 21.77\% improvement in the average duration of dialogues. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_20624 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | PaRT: Enhancing Proactive Social Chatbots with Personalized Real-Time Retrieval Niu, Zihan Xie, Zheyong Cao, Shaosheng Lu, Chonggang Ye, Zheyu Xu, Tong Liu, Zuozhu Gao, Yan Chen, Jia Xu, Zhe Wu, Yi Hu, Yao Artificial Intelligence Social chatbots have become essential intelligent companions in daily scenarios ranging from emotional support to personal interaction. However, conventional chatbots with passive response mechanisms usually rely on users to initiate or sustain dialogues by bringing up new topics, resulting in diminished engagement and shortened dialogue duration. In this paper, we present PaRT, a novel framework enabling context-aware proactive dialogues for social chatbots through personalized real-time retrieval and generation. Specifically, PaRT first integrates user profiles and dialogue context into a large language model (LLM), which is initially prompted to refine user queries and recognize their underlying intents for the upcoming conversation. Guided by refined intents, the LLM generates personalized dialogue topics, which then serve as targeted queries to retrieve relevant passages from RedNote. Finally, we prompt LLMs with summarized passages to generate knowledge-grounded and engagement-optimized responses. Our approach has been running stably in a real-world production environment for more than 30 days, achieving a 21.77\% improvement in the average duration of dialogues. |
| title | PaRT: Enhancing Proactive Social Chatbots with Personalized Real-Time Retrieval |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2504.20624 |