TACO-RL: Task Aware Prompt Compression Optimization with Reinforcement Learning

• URL: http://arxiv.org/abs/2409.13035v2
• Date: Mon, 23 Sep 2024 07:40:10 GMT
• Title: TACO-RL: Task Aware Prompt Compression Optimization with Reinforcement Learning
• Authors: Shivam Shandilya, Menglin Xia, Supriyo Ghosh, Huiqiang Jiang, Jue Zhang, Qianhui Wu, Victor Rühle,
• Abstract summary: Large language models (LLMs) such as GPT-4 have led to a surge in the size of prompts required for optimal performance. We propose a novel and efficient reinforcement learning (RL) based task-aware prompt compression method. We demonstrate that our RL-guided compression method improves the task performance by 8% - 260% over state-of-the-art compression techniques.
• Score: 11.167198972934736
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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% - 260% across these three scenarios over state-of-the-art compression techniques while satisfying the same compression rate and latency requirements.

Related papers

• Selection-p: Self-Supervised Task-Agnostic Prompt Compression for Faithfulness and Transferability [67.77534983324229]
  In this paper, we investigate the ability of Large Language Models to develop a unified compression method that discretizes uninformative tokens. Experiments show Selection-p achieves state-of-the-art performance across numerous classification tasks. It exhibits superior transferability to different models compared to prior work.
  arXiv  Detail & Related papers  (2024-10-15T17:05:25Z)
• From Reading to Compressing: Exploring the Multi-document Reader for Prompt Compression [9.5823848981136]
  Large language models (LLMs) have achieved significant performance gains using advanced prompting techniques. Prompt compression has been proposed to alleviate these issues, but it faces challenges in capturing the global context and training the compressor effectively.
  arXiv  Detail & Related papers  (2024-10-05T12:27:47Z)
• LoRC: Low-Rank Compression for LLMs KV Cache with a Progressive Compression Strategy [59.1298692559785]
  Key-Value ( KV) cache is crucial component in serving transformer-based autoregressive large language models (LLMs) Existing approaches to mitigate this issue include: (1) efficient attention variants integrated in upcycling stages; (2) KV cache compression at test time; and (3) KV cache compression at test time. We propose a low-rank approximation of KV weight matrices, allowing plug-in integration with existing transformer-based LLMs without model retraining. Our method is designed to function without model tuning in upcycling stages or task-specific profiling in test stages.
  arXiv  Detail & Related papers  (2024-10-04T03:10:53Z)
• Expediting and Elevating Large Language Model Reasoning via Hidden Chain-of-Thought Decoding [14.175444025026508]
  Large language models (LLMs) have demonstrated remarkable capabilities in tasks requiring chain-of-thought (CoT) prompting. generating the full CoT process results in significantly longer output sequences, leading to increased computational costs and latency during inference. We propose a novel approach to compress the CoT process through semantic alignment, enabling more efficient decoding while preserving the benefits of CoT reasoning.
  arXiv  Detail & Related papers  (2024-09-13T06:29:20Z)
• LanguaShrink: Reducing Token Overhead with Psycholinguistics [8.123272461141815]
  LanguaShrink is a prompt compression framework for large language models. It reduces prompt length while preserving essential information. Compared to existing prompt compression methods, LanguaShrink improves end-to-end latency by 1.43 times.
  arXiv  Detail & Related papers  (2024-09-01T22:09:20Z)
• LLMLingua-2: Data Distillation for Efficient and Faithful Task-Agnostic Prompt Compression [43.048684907893104]
  This paper focuses on task-agnostic prompt compression for better generalizability and efficiency. We formulate prompt compression as a token classification problem to guarantee the faithfulness of the compressed prompt to the original one. Our approach leads to lower latency by explicitly learning the compression objective with smaller models such as XLM-RoBERTa-large and mBERT.
  arXiv  Detail & Related papers  (2024-03-19T17:59:56Z)
• PYRA: Parallel Yielding Re-Activation for Training-Inference Efficient Task Adaptation [61.57833648734164]
  We propose a novel Parallel Yielding Re-Activation (PYRA) method for training-inference efficient task adaptation. PYRA outperforms all competing methods under both low compression rate and high compression rate.
  arXiv  Detail & Related papers  (2024-03-14T09:06:49Z)
• Long Context Compression with Activation Beacon [22.054232261437186]
  Activation Beacon is a plug-in module for transformer-based LLMs. It targets effective, efficient, and flexible compression of long contexts. It achieves a 2x acceleration in inference time and an 8x reduction of memory costs for KV cache.
  arXiv  Detail & Related papers  (2024-01-07T11:57:40Z)
• Instance-wise Prompt Tuning for Pretrained Language Models [72.74916121511662]
  Instance-wise Prompt Tuning (IPT) is the first prompt learning paradigm that injects knowledge from the input data instances to the prompts. IPT significantly outperforms task-based prompt learning methods, and achieves comparable performance to conventional finetuning with only 0.5% - 1.5% of tuned parameters.
  arXiv  Detail & Related papers  (2022-06-04T10:08:50Z)
• Robust Predictable Control [149.71263296079388]
  We show that our method achieves much tighter compression than prior methods, achieving up to 5x higher reward than a standard information bottleneck. We also demonstrate that our method learns policies that are more robust and generalize better to new tasks.
  arXiv  Detail & Related papers  (2021-09-07T17:29:34Z)
• An Information Theory-inspired Strategy for Automatic Network Pruning [88.51235160841377]
  Deep convolution neural networks are well known to be compressed on devices with resource constraints. Most existing network pruning methods require laborious human efforts and prohibitive computation resources. We propose an information theory-inspired strategy for automatic model compression.
  arXiv  Detail & Related papers  (2021-08-19T07:03:22Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.