ExpeTrans: LLMs Are Experiential Transfer Learners
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866912401982488576 |
|---|---|
| author | Gao, Jinglong Ding, Xiao Zou, Lingxiao Cai, Bibo Qin, Bing Liu, Ting |
| author_facet | Gao, Jinglong Ding, Xiao Zou, Lingxiao Cai, Bibo Qin, Bing Liu, Ting |
| contents | Recent studies provide large language models (LLMs) with textual task-solving experiences via prompts to improve their performance. However, previous methods rely on substantial human labor or time to gather such experiences for each task, which is impractical given the growing variety of task types in user queries to LLMs. To address this issue, we design an autonomous experience transfer framework to explore whether LLMs can mimic human cognitive intelligence to autonomously transfer experience from existing source tasks to newly encountered target tasks. This not only allows the acquisition of experience without extensive costs of previous methods, but also offers a novel path for the generalization of LLMs. Experimental results on 13 datasets demonstrate that our framework effectively improves the performance of LLMs. Furthermore, we provide a detailed analysis of each module in the framework. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_23191 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | ExpeTrans: LLMs Are Experiential Transfer Learners Gao, Jinglong Ding, Xiao Zou, Lingxiao Cai, Bibo Qin, Bing Liu, Ting Computation and Language Artificial Intelligence Recent studies provide large language models (LLMs) with textual task-solving experiences via prompts to improve their performance. However, previous methods rely on substantial human labor or time to gather such experiences for each task, which is impractical given the growing variety of task types in user queries to LLMs. To address this issue, we design an autonomous experience transfer framework to explore whether LLMs can mimic human cognitive intelligence to autonomously transfer experience from existing source tasks to newly encountered target tasks. This not only allows the acquisition of experience without extensive costs of previous methods, but also offers a novel path for the generalization of LLMs. Experimental results on 13 datasets demonstrate that our framework effectively improves the performance of LLMs. Furthermore, we provide a detailed analysis of each module in the framework. |
| title | ExpeTrans: LLMs Are Experiential Transfer Learners |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2505.23191 |