Understanding and Improving Information Preservation in Prompt Compression for LLMs

Weronika Łajewska, Momchil Hardalov, Laura Aina, Neha Anna John, Hang Su, Lluis Marquez


Abstract
Recent advancements in large language models (LLMs) have enabled their successful application to a broad range of tasks. However, in information-intensive tasks, the prompt length can grow fast, leading to increased computational requirements, performance degradation, and induced biases from irrelevant or redundant information. Recently, various prompt compression techniques have been introduced to optimize the trade-off between reducing input length and retaining performance. We propose a holistic evaluation framework that allows for in-depth analysis of prompt compression methods. We focus on three key aspects, besides compression ratio: (i) downstream task performance, (ii) grounding in the input context, and (iii) information preservation. Using our framework, we analyze state-of-the-art soft and hard compression methods and show that some fail to preserve key details from the original prompt, limiting performance on complex tasks. By identifying these limitations, we are able to improve one soft prompting method by controlling compression granularity, achieving up to +23% in downstream performance, +8 BERTScore points in grounding, and 2.7× more entities preserved in compression. Ultimately, we find that the best effectiveness/compression rate trade-off is achieved with soft prompting combined with sequence-level training.
Anthology ID:
2025.findings-emnlp.949
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2025
Month:
November
Year:
2025
Address:
Suzhou, China
Editors:
Christos Christodoulopoulos, Tanmoy Chakraborty, Carolyn Rose, Violet Peng
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
17520–17541
Language:
URL:
https://aclanthology.org/2025.findings-emnlp.949/
DOI:
Bibkey:
Cite (ACL):
Weronika Łajewska, Momchil Hardalov, Laura Aina, Neha Anna John, Hang Su, and Lluis Marquez. 2025. Understanding and Improving Information Preservation in Prompt Compression for LLMs. In Findings of the Association for Computational Linguistics: EMNLP 2025, pages 17520–17541, Suzhou, China. Association for Computational Linguistics.
Cite (Informal):
Understanding and Improving Information Preservation in Prompt Compression for LLMs (Łajewska et al., Findings 2025)
Copy Citation:
PDF:
https://aclanthology.org/2025.findings-emnlp.949.pdf
Checklist:
 2025.findings-emnlp.949.checklist.pdf