LongLLMLingua: Accelerating and Enhancing LLMs in Long Context Scenarios via Prompt Compression

Huiqiang Jiang, Qianhui Wu, Xufang Luo, Dongsheng Li, Chin-Yew Lin, Yuqing Yang, Lili Qiu


Abstract
In long context scenarios, large language models (LLMs) face three main challenges: higher computational cost, performance reduction, and position bias. Research indicates that LLM performance hinges on the density and position of key information in the input prompt. Inspired by these findings, we propose LongLLMLingua for prompt compression towards improving LLMs’ perception of the key information to simultaneously address the three challenges. Our extensive evaluation across various long context scenarios demonstrates that LongLLMLingua not only enhances performance but also significantly reduces costs and latency. For instance, in the NaturalQuestions benchmark, LongLLMLingua boosts performance by up to 21.4% with around 4x fewer tokens in GPT-3.5-Turbo, leading to substantial cost savings. It achieves a 94.0% cost reduction in the LooGLE benchmark. Moreover, when compressing prompts of about 10k tokens at ratios of 2x-6x, LongLLMLingua can accelerate end-to-end latency by 1.4x-2.6x.
Anthology ID:
2024.acl-long.91
Volume:
Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
Month:
August
Year:
2024
Address:
Bangkok, Thailand
Editors:
Lun-Wei Ku, Andre Martins, Vivek Srikumar
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
1658–1677
Language:
URL:
https://aclanthology.org/2024.acl-long.91
DOI:
10.18653/v1/2024.acl-long.91
Bibkey:
Cite (ACL):
Huiqiang Jiang, Qianhui Wu, Xufang Luo, Dongsheng Li, Chin-Yew Lin, Yuqing Yang, and Lili Qiu. 2024. LongLLMLingua: Accelerating and Enhancing LLMs in Long Context Scenarios via Prompt Compression. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 1658–1677, Bangkok, Thailand. Association for Computational Linguistics.
Cite (Informal):
LongLLMLingua: Accelerating and Enhancing LLMs in Long Context Scenarios via Prompt Compression (Jiang et al., ACL 2024)
Copy Citation:
PDF:
https://preview.aclanthology.org/add_acl24_videos/2024.acl-long.91.pdf
Video:
 https://preview.aclanthology.org/add_acl24_videos/2024.acl-long.91.mp4