Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2501.01625 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866929657162498048 |
|---|---|
| author | Yu, Ziyang Liu, Yuyu |
| author_facet | Yu, Ziyang Liu, Yuyu |
| contents | Despite the recent success of Large Language Models (LLMs), it remains challenging to feed LLMs with long prompts due to the fixed size of LLM inputs. As a remedy, prompt compression becomes a promising solution by removing redundant tokens in the prompt. However, using LLM in the existing works requires additional computation resources and leads to memory overheads. To address it, we propose ICPC (In-context Prompt Compression), a novel and scalable prompt compression method that adaptively reduces the prompt length. The key idea of ICPC is to calculate the probability of each word appearing in the prompt using encoders and calculate information carried by each word through the information function, which effectively reduces the information loss during prompt compression and increases the speed of compression. Empirically, we demonstrate that ICPC can effectively compress long texts of different categories and thus achieve better performance and speed on different types of NLP tasks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2501_01625 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | ICPC: In-context Prompt Compression with Faster Inference Yu, Ziyang Liu, Yuyu Computation and Language Artificial Intelligence Despite the recent success of Large Language Models (LLMs), it remains challenging to feed LLMs with long prompts due to the fixed size of LLM inputs. As a remedy, prompt compression becomes a promising solution by removing redundant tokens in the prompt. However, using LLM in the existing works requires additional computation resources and leads to memory overheads. To address it, we propose ICPC (In-context Prompt Compression), a novel and scalable prompt compression method that adaptively reduces the prompt length. The key idea of ICPC is to calculate the probability of each word appearing in the prompt using encoders and calculate information carried by each word through the information function, which effectively reduces the information loss during prompt compression and increases the speed of compression. Empirically, we demonstrate that ICPC can effectively compress long texts of different categories and thus achieve better performance and speed on different types of NLP tasks. |
| title | ICPC: In-context Prompt Compression with Faster Inference |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2501.01625 |