Implicit Federated In-context Learning For Task-Specific LLM Fine-Tuning
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866917070466187264 |
|---|---|
| author | Li, Dongcheng Chen, Junhan Zhou, Aoxiang Li, Chunpei Xian, Youquan Liu, Peng Li, Xianxian |
| author_facet | Li, Dongcheng Chen, Junhan Zhou, Aoxiang Li, Chunpei Xian, Youquan Liu, Peng Li, Xianxian |
| contents | As large language models continue to develop and expand, the extensive public data they rely on faces the risk of depletion. Consequently, leveraging private data within organizations to enhance the performance of large models has emerged as a key challenge. The federated learning paradigm, combined with model fine-tuning techniques, effectively reduces the number of trainable parameters. However,the necessity to process high-dimensional feature spaces results in substantial overall computational overhead. To address this issue, we propose the Implicit Federated In-Context Learning (IFed-ICL) framework. IFed-ICL draws inspiration from federated learning to establish a novel distributed collaborative paradigm, by converting client local context examples into implicit vector representations, it enables distributed collaborative computation during the inference phase and injects model residual streams to enhance model performance. Experiments demonstrate that our proposed method achieves outstanding performance across multiple text classification tasks. Compared to traditional methods, IFed-ICL avoids the extensive parameter updates required by conventional fine-tuning methods while reducing data transmission and local computation at the client level in federated learning. This enables efficient distributed context learning using local private-domain data, significantly improving model performance on specific tasks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_06757 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Implicit Federated In-context Learning For Task-Specific LLM Fine-Tuning Li, Dongcheng Chen, Junhan Zhou, Aoxiang Li, Chunpei Xian, Youquan Liu, Peng Li, Xianxian Machine Learning Artificial Intelligence As large language models continue to develop and expand, the extensive public data they rely on faces the risk of depletion. Consequently, leveraging private data within organizations to enhance the performance of large models has emerged as a key challenge. The federated learning paradigm, combined with model fine-tuning techniques, effectively reduces the number of trainable parameters. However,the necessity to process high-dimensional feature spaces results in substantial overall computational overhead. To address this issue, we propose the Implicit Federated In-Context Learning (IFed-ICL) framework. IFed-ICL draws inspiration from federated learning to establish a novel distributed collaborative paradigm, by converting client local context examples into implicit vector representations, it enables distributed collaborative computation during the inference phase and injects model residual streams to enhance model performance. Experiments demonstrate that our proposed method achieves outstanding performance across multiple text classification tasks. Compared to traditional methods, IFed-ICL avoids the extensive parameter updates required by conventional fine-tuning methods while reducing data transmission and local computation at the client level in federated learning. This enables efficient distributed context learning using local private-domain data, significantly improving model performance on specific tasks. |
| title | Implicit Federated In-context Learning For Task-Specific LLM Fine-Tuning |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2511.06757 |