Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2402.11975 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910507243405312 |
|---|---|
| author | Chen, Nuo Li, Hongguang Huang, Juhua Wang, Baoyuan Li, Jia |
| author_facet | Chen, Nuo Li, Hongguang Huang, Juhua Wang, Baoyuan Li, Jia |
| contents | Existing retrieval-based methods have made significant strides in maintaining long-term conversations. However, these approaches face challenges in memory database management and accurate memory retrieval, hindering their efficacy in dynamic, real-world interactions. This study introduces a novel framework, COmpressive Memory-Enhanced Dialogue sYstems (COMEDY), which eschews traditional retrieval modules and memory databases. Instead, COMEDY adopts a "One-for-All" approach, utilizing a single language model to manage memory generation, compression, and response generation. Central to this framework is the concept of compressive memory, which intergrates session-specific summaries, user-bot dynamics, and past events into a concise memory format. To support COMEDY, we curated a large-scale Chinese instruction-tuning dataset, Dolphin, derived from real user-chatbot interactions. Comparative evaluations demonstrate COMEDY's superiority over traditional retrieval-based methods in producing more nuanced and human-like conversational experiences. Our codes are available at https://github.com/nuochenpku/COMEDY. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_11975 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Compress to Impress: Unleashing the Potential of Compressive Memory in Real-World Long-Term Conversations Chen, Nuo Li, Hongguang Huang, Juhua Wang, Baoyuan Li, Jia Computation and Language Existing retrieval-based methods have made significant strides in maintaining long-term conversations. However, these approaches face challenges in memory database management and accurate memory retrieval, hindering their efficacy in dynamic, real-world interactions. This study introduces a novel framework, COmpressive Memory-Enhanced Dialogue sYstems (COMEDY), which eschews traditional retrieval modules and memory databases. Instead, COMEDY adopts a "One-for-All" approach, utilizing a single language model to manage memory generation, compression, and response generation. Central to this framework is the concept of compressive memory, which intergrates session-specific summaries, user-bot dynamics, and past events into a concise memory format. To support COMEDY, we curated a large-scale Chinese instruction-tuning dataset, Dolphin, derived from real user-chatbot interactions. Comparative evaluations demonstrate COMEDY's superiority over traditional retrieval-based methods in producing more nuanced and human-like conversational experiences. Our codes are available at https://github.com/nuochenpku/COMEDY. |
| title | Compress to Impress: Unleashing the Potential of Compressive Memory in Real-World Long-Term Conversations |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2402.11975 |