Adaptive In-Context Learning with Large Language Models for Bundle Generation
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2023
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866909498281558016 |
|---|---|
| author | Sun, Zhu Feng, Kaidong Yang, Jie Qu, Xinghua Fang, Hui Ong, Yew-Soon Liu, Wenyuan |
| author_facet | Sun, Zhu Feng, Kaidong Yang, Jie Qu, Xinghua Fang, Hui Ong, Yew-Soon Liu, Wenyuan |
| contents | Most existing bundle generation approaches fall short in generating fixed-size bundles. Furthermore, they often neglect the underlying user intents reflected by the bundles in the generation process, resulting in less intelligible bundles. This paper addresses these limitations through the exploration of two interrelated tasks, i.e., personalized bundle generation and the underlying intent inference, based on different user sessions. Inspired by the reasoning capabilities of large language models (LLMs), we propose an adaptive in-context learning paradigm, which allows LLMs to draw tailored lessons from related sessions as demonstrations, enhancing the performance on target sessions. Specifically, we first employ retrieval augmented generation to identify nearest neighbor sessions, and then carefully design prompts to guide LLMs in executing both tasks on these neighbor sessions. To tackle reliability and hallucination challenges, we further introduce (1) a self-correction strategy promoting mutual improvements of the two tasks without supervision signals and (2) an auto-feedback mechanism for adaptive supervision based on the distinct mistakes made by LLMs on different neighbor sessions. Thereby, the target session can gain customized lessons for improved performance by observing the demonstrations of its neighbor sessions. Experiments on three real-world datasets demonstrate the effectiveness of our proposed method. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2312_16262 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Adaptive In-Context Learning with Large Language Models for Bundle Generation Sun, Zhu Feng, Kaidong Yang, Jie Qu, Xinghua Fang, Hui Ong, Yew-Soon Liu, Wenyuan Information Retrieval Artificial Intelligence Most existing bundle generation approaches fall short in generating fixed-size bundles. Furthermore, they often neglect the underlying user intents reflected by the bundles in the generation process, resulting in less intelligible bundles. This paper addresses these limitations through the exploration of two interrelated tasks, i.e., personalized bundle generation and the underlying intent inference, based on different user sessions. Inspired by the reasoning capabilities of large language models (LLMs), we propose an adaptive in-context learning paradigm, which allows LLMs to draw tailored lessons from related sessions as demonstrations, enhancing the performance on target sessions. Specifically, we first employ retrieval augmented generation to identify nearest neighbor sessions, and then carefully design prompts to guide LLMs in executing both tasks on these neighbor sessions. To tackle reliability and hallucination challenges, we further introduce (1) a self-correction strategy promoting mutual improvements of the two tasks without supervision signals and (2) an auto-feedback mechanism for adaptive supervision based on the distinct mistakes made by LLMs on different neighbor sessions. Thereby, the target session can gain customized lessons for improved performance by observing the demonstrations of its neighbor sessions. Experiments on three real-world datasets demonstrate the effectiveness of our proposed method. |
| title | Adaptive In-Context Learning with Large Language Models for Bundle Generation |
| topic | Information Retrieval Artificial Intelligence |
| url | https://arxiv.org/abs/2312.16262 |