@inproceedings{shandilya-etal-2025-taco,
    title = "{TACO}-{RL}: Task Aware Prompt Compression Optimization with Reinforcement Learning",
    author = {Shandilya, Shivam  and
      Xia, Menglin  and
      Ghosh, Supriyo  and
      Jiang, Huiqiang  and
      Zhang, Jue  and
      Wu, Qianhui  and
      R{\"u}hle, Victor  and
      Rajmohan, Saravan},
    editor = "Che, Wanxiang  and
      Nabende, Joyce  and
      Shutova, Ekaterina  and
      Pilehvar, Mohammad Taher",
    booktitle = "Findings of the Association for Computational Linguistics: ACL 2025",
    month = jul,
    year = "2025",
    address = "Vienna, Austria",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/display_plenaries/2025.findings-acl.81/",
    pages = "1582--1597",
    ISBN = "979-8-89176-256-5",
    abstract = "The increasing prevalence of large language models (LLMs) such as GPT-4 in various applications has led to a surge in the size of prompts required for optimal performance, leading to challenges in computational efficiency. Prompt compression aims to reduce the inference cost by minimizing input tokens without compromising on the task performance. However, existing prompt compression techniques either rely on sub-optimal metrics such as information entropy or model it as a task-agnostic token classification problem that fails to capture task-specific information.To address these issues, we propose a novel and efficient reinforcement learning (RL) based task-aware prompt compression method. To ensure low latency requirements, we leverage existing Transformer encoder-based token classification model while guiding the learning process with task-specific reward signals using lightweight REINFORCE algorithm. We evaluate the performance of our method on three diverse and challenging tasks including text summarization, question answering and code summarization. We demonstrate that our RL-guided compression method improves the task performance by 8{\%} - 189{\%} across these three scenarios over state-of-the-art compression techniques while satisfying the same compression rate and latency requirements."
}