On Memory Construction and Retrieval for Personalized Conversational Agents
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866913715998162944 |
|---|---|
| author | Pan, Zhuoshi Wu, Qianhui Jiang, Huiqiang Luo, Xufang Cheng, Hao Li, Dongsheng Yang, Yuqing Lin, Chin-Yew Zhao, H. Vicky Qiu, Lili Gao, Jianfeng |
| author_facet | Pan, Zhuoshi Wu, Qianhui Jiang, Huiqiang Luo, Xufang Cheng, Hao Li, Dongsheng Yang, Yuqing Lin, Chin-Yew Zhao, H. Vicky Qiu, Lili Gao, Jianfeng |
| contents | To deliver coherent and personalized experiences in long-term conversations, existing approaches typically perform retrieval augmented response generation by constructing memory banks from conversation history at either the turn-level, session-level, or through summarization techniques.In this paper, we present two key findings: (1) The granularity of memory unit matters: turn-level, session-level, and summarization-based methods each exhibit limitations in both memory retrieval accuracy and the semantic quality of the retrieved content. (2) Prompt compression methods, such as LLMLingua-2, can effectively serve as a denoising mechanism, enhancing memory retrieval accuracy across different granularities. Building on these insights, we propose SeCom, a method that constructs the memory bank at segment level by introducing a conversation segmentation model that partitions long-term conversations into topically coherent segments, while applying compression based denoising on memory units to enhance memory retrieval. Experimental results show that SeCom exhibits a significant performance advantage over baselines on long-term conversation benchmarks LOCOMO and Long-MT-Bench+. Additionally, the proposed conversation segmentation method demonstrates superior performance on dialogue segmentation datasets such as DialSeg711, TIAGE, and SuperDialSeg. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_05589 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | On Memory Construction and Retrieval for Personalized Conversational Agents Pan, Zhuoshi Wu, Qianhui Jiang, Huiqiang Luo, Xufang Cheng, Hao Li, Dongsheng Yang, Yuqing Lin, Chin-Yew Zhao, H. Vicky Qiu, Lili Gao, Jianfeng Computation and Language Artificial Intelligence To deliver coherent and personalized experiences in long-term conversations, existing approaches typically perform retrieval augmented response generation by constructing memory banks from conversation history at either the turn-level, session-level, or through summarization techniques.In this paper, we present two key findings: (1) The granularity of memory unit matters: turn-level, session-level, and summarization-based methods each exhibit limitations in both memory retrieval accuracy and the semantic quality of the retrieved content. (2) Prompt compression methods, such as LLMLingua-2, can effectively serve as a denoising mechanism, enhancing memory retrieval accuracy across different granularities. Building on these insights, we propose SeCom, a method that constructs the memory bank at segment level by introducing a conversation segmentation model that partitions long-term conversations into topically coherent segments, while applying compression based denoising on memory units to enhance memory retrieval. Experimental results show that SeCom exhibits a significant performance advantage over baselines on long-term conversation benchmarks LOCOMO and Long-MT-Bench+. Additionally, the proposed conversation segmentation method demonstrates superior performance on dialogue segmentation datasets such as DialSeg711, TIAGE, and SuperDialSeg. |
| title | On Memory Construction and Retrieval for Personalized Conversational Agents |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2502.05589 |