Salvato in:
| Autori principali: | , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2023
|
| Soggetti: | |
| Accesso online: | https://arxiv.org/abs/2308.15022 |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866918130014486528 |
|---|---|
| author | Wang, Qingyue Fu, Yanhe Cao, Yanan Wang, Shuai Tian, Zhiliang Ding, Liang |
| author_facet | Wang, Qingyue Fu, Yanhe Cao, Yanan Wang, Shuai Tian, Zhiliang Ding, Liang |
| contents | Recently, large language models (LLMs), such as GPT-4, stand out remarkable conversational abilities, enabling them to engage in dynamic and contextually relevant dialogues across a wide range of topics. However, given a long conversation, these chatbots fail to recall past information and tend to generate inconsistent responses. To address this, we propose to recursively generate summaries/ memory using large language models (LLMs) to enhance long-term memory ability. Specifically, our method first stimulates LLMs to memorize small dialogue contexts and then recursively produce new memory using previous memory and following contexts. Finally, the chatbot can easily generate a highly consistent response with the help of the latest memory. We evaluate our method on both open and closed LLMs, and the experiments on the widely-used public dataset show that our method can generate more consistent responses in a long-context conversation. Also, we show that our strategy could nicely complement both long-context (e.g., 8K and 16K) and retrieval-enhanced LLMs, bringing further long-term dialogue performance. Notably, our method is a potential solution to enable the LLM to model the extremely long context. The code and scripts are released. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2308_15022 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Recursively Summarizing Enables Long-Term Dialogue Memory in Large Language Models Wang, Qingyue Fu, Yanhe Cao, Yanan Wang, Shuai Tian, Zhiliang Ding, Liang Computation and Language Artificial Intelligence Recently, large language models (LLMs), such as GPT-4, stand out remarkable conversational abilities, enabling them to engage in dynamic and contextually relevant dialogues across a wide range of topics. However, given a long conversation, these chatbots fail to recall past information and tend to generate inconsistent responses. To address this, we propose to recursively generate summaries/ memory using large language models (LLMs) to enhance long-term memory ability. Specifically, our method first stimulates LLMs to memorize small dialogue contexts and then recursively produce new memory using previous memory and following contexts. Finally, the chatbot can easily generate a highly consistent response with the help of the latest memory. We evaluate our method on both open and closed LLMs, and the experiments on the widely-used public dataset show that our method can generate more consistent responses in a long-context conversation. Also, we show that our strategy could nicely complement both long-context (e.g., 8K and 16K) and retrieval-enhanced LLMs, bringing further long-term dialogue performance. Notably, our method is a potential solution to enable the LLM to model the extremely long context. The code and scripts are released. |
| title | Recursively Summarizing Enables Long-Term Dialogue Memory in Large Language Models |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2308.15022 |