Position IDs Matter: An Enhanced Position Layout for Efficient Context Compression in Large Language Models

• URL: http://arxiv.org/abs/2409.14364v3
• Date: Fri, 23 May 2025 03:05:49 GMT
• Title: Position IDs Matter: An Enhanced Position Layout for Efficient Context Compression in Large Language Models
• Authors: Runsong Zhao, Xin Liu, Xinyu Liu, Pengcheng Huang, Chunyang Xiao, Tong Xiao, Jingbo Zhu,
• Abstract summary: We propose Enhanced Position Layout (EPL) to improve the context compression capability of large language models (LLMs)<n>EPL minimizes the distance between context tokens and their corresponding special tokens and at the same time maintains the sequence order in position IDs.<n>When extended to multimodal scenarios, EPL brings an average accuracy gain of 2.6 to vision compression LLMs.
• Score: 50.637714223178456
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Using special tokens (e.g., gist, memory, or compressed tokens) to compress context information is a common practice for large language models (LLMs). However, existing approaches often neglect that position encodings inherently induce local inductive biases in models, causing the compression process to ignore holistic contextual dependencies. We propose Enhanced Position Layout (EPL), a simple yet effective method that improves the context compression capability of LLMs by only adjusting position IDs, the numerical identifiers that specify token positions. EPL minimizes the distance between context tokens and their corresponding special tokens and at the same time maintains the sequence order in position IDs between context tokens, special tokens, and the subsequent tokens. Integrating EPL into our best performing context compression model results in 1.9 ROUGE-1 F1 improvement on out-of-domain question answering datasets in average. When extended to multimodal scenarios, EPL brings an average accuracy gain of 2.6 to vision compression LLMs.

Related papers

• SeqPE: Transformer with Sequential Position Encoding [76.22159277300891]
  SeqPE represents each $n$-dimensional position index as a symbolic sequence and employs a lightweight sequential position encoder to learn their embeddings.<n> Experiments across language modeling, long-context question answering, and 2D image classification demonstrate that SeqPE not only surpasses strong baselines in perplexity, exact match (EM) and accuracy--but also enables seamless generalization to multi-dimensional inputs without requiring manual architectural redesign.
  arXiv  Detail & Related papers  (2025-06-16T09:16:40Z)
• PaTH Attention: Position Encoding via Accumulating Householder Transformations [56.32365080761523]
  PaTH is a flexible data-dependent position encoding scheme based on accumulated products of Householder transformations.<n>We derive an efficient parallel algorithm for training through exploiting a compact representation of products of Householder matrices.
  arXiv  Detail & Related papers  (2025-05-22T08:36:09Z)
• Efficient Token Compression for Vision Transformer with Spatial Information Preserved [59.79302182800274]
  Token compression is essential for reducing the computational and memory requirements of transformer models. We propose an efficient and hardware-compatible token compression method called Prune and Merge.
  arXiv  Detail & Related papers  (2025-03-30T14:23:18Z)
• Embedding Compression Distortion in Video Coding for Machines [67.97469042910855]
  Currently, video transmission serves not only the Human Visual System (HVS) for viewing but also machine perception for analysis. We propose a Compression Distortion Embedding (CDRE) framework, which extracts machine-perception-related distortion representation and embeds it into downstream models. Our framework can effectively boost the rate-task performance of existing codecs with minimal overhead in terms of execution time, and number of parameters.
  arXiv  Detail & Related papers  (2025-03-27T13:01:53Z)
• UniPCGC: Towards Practical Point Cloud Geometry Compression via an Efficient Unified Approach [4.754973569457509]
  We propose an efficient unified point cloud geometry compression framework, dubbed as UniPCGC. It supports lossy compression, lossless compression, variable rate and variable complexity. Our method achieves a compression ratio (CR) gain of 8.1% on lossless compression, and a Bjontegaard Delta Rate (BD-Rate) gain of 14.02% on lossy compression.
  arXiv  Detail & Related papers  (2025-03-24T10:51:28Z)
• DAST: Context-Aware Compression in LLMs via Dynamic Allocation of Soft Tokens [20.044306399439265]
  Large Language Models (LLMs) face computational inefficiencies and redundant processing when handling long context inputs.<n>We propose Dynamic Allocation of Soft Tokens (DAST), a simple yet effective method that leverages the LLM's intrinsic understanding of contextual relevance to guide compression.<n> Experimental results across multiple benchmarks demonstrate that DAST surpasses state-of-the-art methods.
  arXiv  Detail & Related papers  (2025-02-17T06:55:13Z)
• ICPC: In-context Prompt Compression with Faster Inference [0.0]
  We propose I CPC (In-context Prompt Compression), a novel and scalable prompt compression method that adaptively reduces the prompt length. The key idea of I CPC is to calculate the probability of each word appearing in the prompt using encoders and calculate information carried by each word through the information function. Empirically, we demonstrate that I CPC can effectively compress long texts of different categories and thus achieve better performance and speed on different types of NLP tasks.
  arXiv  Detail & Related papers  (2025-01-03T03:46:51Z)
• L3TC: Leveraging RWKV for Learned Lossless Low-Complexity Text Compression [23.179381396167084]
  We introduce a novel Learned Lossless Low-complexity Text Compression method (L3TC) RWKV models achieve the fastest decoding speed with a moderate compression ratio. We propose an outlier-aware tokenizer that uses a limited vocabulary to cover frequent tokens.
  arXiv  Detail & Related papers  (2024-12-21T14:24:32Z)
• EoRA: Training-free Compensation for Compressed LLM with Eigenspace Low-Rank Approximation [79.56709262189953]
  EoRA consistently outperforms previous methods in compensating errors for compressed LLaMA2/3 models on various tasks. EoRA offers a scalable, training-free solution to compensate for compression errors.
  arXiv  Detail & Related papers  (2024-10-28T17:59:03Z)
• Perception Compressor:A training-free prompt compression method in long context scenarios [17.720102137585503]
  Perception is a training-free prompt compression method for large language models. It outperforms existing methods by a large margin, achieving state-of-the-art performance.
  arXiv  Detail & Related papers  (2024-09-28T07:13:33Z)
• Token-level Correlation-guided Compression for Efficient Multimodal Document Understanding [54.532578213126065]
  Most document understanding methods preserve all tokens within sub-images and treat them equally. This neglects their different informativeness and leads to a significant increase in the number of image tokens. We propose Token-level Correlation-guided Compression, a parameter-free and plug-and-play methodology to optimize token processing.
  arXiv  Detail & Related papers  (2024-07-19T16:11:15Z)
• Contextual Position Encoding: Learning to Count What's Important [42.038277620194]
  We propose a new position encoding method, Contextual Position Flop (CoPE) CoPE allows positions to be conditioned on context by incrementing position on certain tokens determined by the model. We show that CoPE can solve the selective copy, counting and Flip-Flop tasks where popular position embeddings fail.
  arXiv  Detail & Related papers  (2024-05-29T02:57:15Z)
• Progressive Learning with Visual Prompt Tuning for Variable-Rate Image Compression [60.689646881479064]
  We propose a progressive learning paradigm for transformer-based variable-rate image compression. Inspired by visual prompt tuning, we use LPM to extract prompts for input images and hidden features at the encoder side and decoder side, respectively. Our model outperforms all current variable image methods in terms of rate-distortion performance and approaches the state-of-the-art fixed image compression methods trained from scratch.
  arXiv  Detail & Related papers  (2023-11-23T08:29:32Z)
• FLIP: Fine-grained Alignment between ID-based Models and Pretrained Language Models for CTR Prediction [49.510163437116645]
  Click-through rate (CTR) prediction plays as a core function module in personalized online services. Traditional ID-based models for CTR prediction take as inputs the one-hot encoded ID features of tabular modality. Pretrained Language Models(PLMs) has given rise to another paradigm, which takes as inputs the sentences of textual modality. We propose to conduct Fine-grained feature-level ALignment between ID-based Models and Pretrained Language Models(FLIP) for CTR prediction.
  arXiv  Detail & Related papers  (2023-10-30T11:25:03Z)
• The Locality and Symmetry of Positional Encodings [9.246374019271938]
  We conduct a systematic study of positional encodings in textbfBi Masked Language Models (BERT-style) We uncover the core function of PEs by identifying two common properties, Locality and Symmetry. We quantify the weakness of current PEs by introducing two new probing tasks, on which current PEs perform poorly.
  arXiv  Detail & Related papers  (2023-10-19T16:15:15Z)
• Lossy and Lossless (L$^2$) Post-training Model Size Compression [12.926354646945397]
  We propose a post-training model size compression method that combines lossy and lossless compression in a unified way. Our method can achieve a stable $10times$ compression ratio without sacrificing accuracy and a $20times$ compression ratio with minor accuracy loss in a short time.
  arXiv  Detail & Related papers  (2023-08-08T14:10:16Z)
• Quick Dense Retrievers Consume KALE: Post Training Kullback Leibler Alignment of Embeddings for Asymmetrical dual encoders [89.29256833403169]
  We introduce Kullback Leibler Alignment of Embeddings (KALE), an efficient and accurate method for increasing the inference efficiency of dense retrieval methods. KALE extends traditional Knowledge Distillation after bi-encoder training, allowing for effective query encoder compression without full retraining or index generation. Using KALE and asymmetric training, we can generate models which exceed the performance of DistilBERT despite having 3x faster inference.
  arXiv  Detail & Related papers  (2023-03-31T15:44:13Z)
• Deep Lossy Plus Residual Coding for Lossless and Near-lossless Image Compression [85.93207826513192]
  We propose a unified and powerful deep lossy plus residual (DLPR) coding framework for both lossless and near-lossless image compression. We solve the joint lossy and residual compression problem in the approach of VAEs. In the near-lossless mode, we quantize the original residuals to satisfy a given $ell_infty$ error bound.
  arXiv  Detail & Related papers  (2022-09-11T12:11:56Z)
• Modeling Image Quantization Tradeoffs for Optimal Compression [0.0]
  Lossy compression algorithms target tradeoffs by quantizating high frequency data to increase compression rates. We propose a new method of optimizing quantization tables using Deep Learning and a minimax loss function.
  arXiv  Detail & Related papers  (2021-12-14T07:35:22Z)
• Towards Compact CNNs via Collaborative Compression [166.86915086497433]
  We propose a Collaborative Compression scheme, which joints channel pruning and tensor decomposition to compress CNN models. We achieve 52.9% FLOPs reduction by removing 48.4% parameters on ResNet-50 with only a Top-1 accuracy drop of 0.56% on ImageNet 2012.
  arXiv  Detail & Related papers  (2021-05-24T12:07:38Z)
• Compressing Images by Encoding Their Latent Representations with Relative Entropy Coding [5.687243501594734]
  Variational Autoencoders (VAEs) have seen widespread use in learned image compression. We propose a novel method, Relative Entropy Coding (REC), that can directly encode the latent representation with codelength close to the relative entropy for single images.
  arXiv  Detail & Related papers  (2020-10-02T20:23:22Z)
• Rethinking Positional Encoding in Language Pre-training [111.2320727291926]
  We show that in absolute positional encoding, the addition operation applied on positional embeddings and word embeddings brings mixed correlations. We propose a new positional encoding method called textbfTransformer with textbfUntied textPositional textbfEncoding (T)
  arXiv  Detail & Related papers  (2020-06-28T13:11:02Z)

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.