Personalized Large Language Model Assistant with Evolving Conditional Memory (2312.17257v2)
Abstract: With the rapid development of LLMs, AI assistants like ChatGPT have become increasingly integrated into people's works and lives but are limited in personalized services. In this paper, we present a plug-and-play framework that could facilitate personalized LLM assistants with evolving conditional memory. The personalized assistant focuses on intelligently preserving the knowledge and experience from the history dialogue with the user, which can be applied to future tailored responses that better align with the user's preferences. Generally, the assistant generates a set of records from the dialogue dialogue, stores them in a memory bank, and retrieves related memory to improve the quality of the response. For the crucial memory design, we explore different ways of constructing the memory and propose a new memorizing mechanism named conditional memory. We also investigate the retrieval and usage of memory in the generation process. We build the first benchmark to evaluate personalized assistants' ability from three aspects. The experimental results illustrate the effectiveness of our method.
- Topiocqa: Open-domain conversational question answering with topic switching. Transactions of the Association for Computational Linguistics, 10: 468–483.
- Skeleton-to-response: Dialogue generation guided by retrieval memory. arXiv preprint arXiv:1809.05296.
- Look before you hop: Conversational question answering over knowledge graphs using judicious context expansion. In Proceedings of the 28th ACM International Conference on Information and Knowledge Management, 729–738.
- Wizard of wikipedia: Knowledge-powered conversational agents. arXiv preprint arXiv:1811.01241.
- Simcse: Simple contrastive learning of sentence embeddings. arXiv preprint arXiv:2104.08821.
- Controlling dialogue generation with semantic exemplars. arXiv preprint arXiv:2008.09075.
- Rethinking with retrieval: Faithful large language model inference. arXiv preprint arXiv:2301.00303.
- Internet-augmented dialogue generation. arXiv preprint arXiv:2107.07566.
- Learning to select knowledge for response generation in dialog systems. arXiv preprint arXiv:1902.04911.
- Lin, C.-Y. 2004. Rouge: A package for automatic evaluation of summaries. In Text summarization branches out, 74–81.
- RETA-LLM: A Retrieval-Augmented Large Language Model Toolkit. arXiv preprint arXiv:2306.05212.
- Hindsight: Posterior-guided training of retrievers for improved open-ended generation. arXiv preprint arXiv:2110.07752.
- Generative agents: Interactive simulacra of human behavior. arXiv preprint arXiv:2304.03442.
- Conversing by reading: Contentful neural conversation with on-demand machine reading. arXiv preprint arXiv:1906.02738.
- Open-retrieval conversational question answering. In Proceedings of the 43rd International ACM SIGIR conference on research and development in Information Retrieval, 539–548.
- BERT with history answer embedding for conversational question answering. In Proceedings of the 42nd international ACM SIGIR conference on research and development in information retrieval, 1133–1136.
- In-context retrieval-augmented language models. arXiv preprint arXiv:2302.00083.
- Question rewriting for conversational question answering. In Proceedings of the 14th ACM international conference on web search and data mining, 355–363.
- Self-instruct: Aligning language model with self generated instructions. arXiv preprint arXiv:2212.10560.
- Response generation by context-aware prototype editing. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 33, 7281–7288.
- A controllable model of grounded response generation. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 35, 14085–14093.
- Beyond goldfish memory: Long-term open-domain conversation. arXiv preprint arXiv:2107.07567.
- RefGPT: Reference-¿ Truthful & Customized Dialogues Generation by GPTs and for GPTs. arXiv preprint arXiv:2305.14994.
- A hybrid retrieval-generation neural conversation model. In Proceedings of the 28th ACM international conference on information and knowledge management, 1341–1350.