Prompt Compression with Context-Aware Sentence Encoding for Fast and Improved LLM Inference

• URL: http://arxiv.org/abs/2409.01227v2
• Date: Wed, 4 Sep 2024 10:20:59 GMT
• Title: Prompt Compression with Context-Aware Sentence Encoding for Fast and Improved LLM Inference
• Authors: Barys Liskavets, Maxim Ushakov, Shuvendu Roy, Mark Klibanov, Ali Etemad, Shane Luke,
• Abstract summary: We propose context-aware prompt compression (CPC), a sentence-level prompt compression technique. Key innovation is a novel context-aware sentence encoder that provides a relevance score for each sentence for a given question. Our method considerably outperforms prior works on prompt compression on benchmark datasets.
• Score: 16.830389144259584
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large language models (LLMs) have triggered a new stream of research focusing on compressing the context length to reduce the computational cost while ensuring the retention of helpful information for LLMs to answer the given question. Token-based removal methods are one of the most prominent approaches in this direction, but risk losing the semantics of the context caused by intermediate token removal, especially under high compression ratios, while also facing challenges in computational efficiency. In this work, we propose context-aware prompt compression (CPC), a sentence-level prompt compression technique where its key innovation is a novel context-aware sentence encoder that provides a relevance score for each sentence for a given question. To train this encoder, we generate a new dataset consisting of questions, positives, and negative pairs where positives are sentences relevant to the question, while negatives are irrelevant context sentences. We train the encoder in a contrastive setup to learn context-aware sentence representations. Our method considerably outperforms prior works on prompt compression on benchmark datasets and is up to 10.93x faster at inference compared to the best token-level compression method. We also find better improvement for shorter length constraints in most benchmarks, showing the effectiveness of our proposed solution in the compression of relevant information in a shorter context. Finally, we release the code and the dataset for quick reproducibility and further development: https://github.com/Workday/cpc.

Related papers

• Squeezed Attention: Accelerating Long Context Length LLM Inference [64.11145320159126]
  We propose Squeezed Attention as a mechanism to accelerate LLM applications where a large portion of the input prompt is fixed. We use K-means clustering offline to group the keys for the fixed context based on semantic similarity and represent each cluster with a single centroid value. We then compute exact attention using only these important keys from the fixed context, thereby reducing bandwidth and computational costs.
  arXiv  Detail & Related papers  (2024-11-14T18:54:19Z)
• SentenceVAE: Enable Next-sentence Prediction for Large Language Models with Faster Speed, Higher Accuracy and Longer Context [49.9628075245959]
  We present Sentence Variational Autoencoder (SentenceVAE), which includes a Sentence to compress multiple tokens in a sentence into a single token, and a Sentence Decoder to reconstruct it. The proposed method can accelerate inference speed by 204365%, reduce perplexity (PPL) to 4675% of its original metric, and decrease memory overhead by 8691% for the equivalent context length.
  arXiv  Detail & Related papers  (2024-08-01T15:45:19Z)
• Fundamental Limits of Prompt Compression: A Rate-Distortion Framework for Black-Box Language Models [21.025001473355996]
  We formalize the problem of prompt compression for large language models (LLMs) We present a framework to unify token-level prompt compression methods which create hard prompts for black-box models. We show that there is a large gap between the performance of current prompt compression methods and the optimal strategy.
  arXiv  Detail & Related papers  (2024-07-22T09:40:13Z)
• Context Embeddings for Efficient Answer Generation in RAG [10.702520553261756]
  We present COCOM, an effective context compression method, reducing long contexts to only a handful of Context Embeddings. Our method demonstrates a speed-up of up to 5.69 $times$ while achieving higher performance compared to existing efficient context compression methods.
  arXiv  Detail & Related papers  (2024-07-12T13:30:44Z)
• In-Context Former: Lightning-fast Compressing Context for Large Language Model [48.831304302467004]
  In this paper, we propose a new approach to compress the long input contexts of Transformer-based large language models (LLMs) We use the cross-attention mechanism and a small number of learnable digest tokens to condense information from the contextual word embeddings. Experimental results indicate that our method requires only 1/32 of the floating-point operations of the baseline during compression and improves processing speed by 68 to 112 times.
  arXiv  Detail & Related papers  (2024-06-19T15:14:55Z)
• Compressing Lengthy Context With UltraGist [22.054232261437186]
  We propose a new method called UltraGist, which is distinguished for its high-quality compression of lengthy context. UltraGist contributes to the flexibility of compression, as it can be effectively learned to support a broad range of context lengths and compression ratios. It makes the training process sample-efficient and thus maximizes the use of training data.
  arXiv  Detail & Related papers  (2024-05-26T17:23:56Z)
• Training LLMs over Neurally Compressed Text [55.11828645767342]
  This paper explores the idea of training large language models (LLMs) over highly compressed text. We propose Equal-Info Windows, a novel compression technique whereby text is segmented into blocks that each compress to the same bit length. We demonstrate effective learning over neurally compressed text that improves with scale, and outperforms byte-level baselines by a wide margin on perplexity and inference speed benchmarks.
  arXiv  Detail & Related papers  (2024-04-04T17:48:28Z)
• Unrolled Compressed Blind-Deconvolution [77.88847247301682]
  sparse multichannel blind deconvolution (S-MBD) arises frequently in many engineering applications such as radar/sonar/ultrasound imaging. We propose a compression method that enables blind recovery from much fewer measurements with respect to the full received signal in time.
  arXiv  Detail & Related papers  (2022-09-28T15:16:58Z)
• Implicit Neural Representations for Image Compression [103.78615661013623]
  Implicit Neural Representations (INRs) have gained attention as a novel and effective representation for various data types. We propose the first comprehensive compression pipeline based on INRs including quantization, quantization-aware retraining and entropy coding. We find that our approach to source compression with INRs vastly outperforms similar prior work.
  arXiv  Detail & Related papers  (2021-12-08T13:02:53Z)

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.