Two are better than one: Context window extension with multi-grained self-injection
- URL: http://arxiv.org/abs/2410.19318v1
- Date: Fri, 25 Oct 2024 06:08:59 GMT
- Title: Two are better than one: Context window extension with multi-grained self-injection
- Authors: Wei Han, Pan Zhou, Soujanya Poria, Shuicheng Yan,
- Abstract summary: SharedLLM is a novel approach grounded in the design philosophy of multi-grained context compression and query-aware information retrieval.
We introduce a specialized tree-style data structure to efficiently encode, store and retrieve multi-grained contextual information for text chunks.
- Score: 111.1376461868317
- License:
- Abstract: The limited context window of contemporary large language models (LLMs) remains a huge barrier to their broader application across various domains. While continual pre-training on long-context data is a straightforward and effective solution, it incurs substantial costs in terms of data acquisition and computational resources. To alleviate this issue, we propose SharedLLM, a novel approach grounded in the design philosophy of multi-grained context compression and query-aware information retrieval. SharedLLM is composed of two short-context LLMs such as LLaMA-2, termed upper model and lower model. The lower model functions as a compressor while the upper model acts as a decoder. The upper model receives compressed, multi-grained context information from the lower model and performs context-aware modeling on the running text. Information transfer between the compressor and decoder occurs only at the lowest layers to refrain from long forward paths in the lower model and redundant cross-attention modules in the upper model. Based on this architecture, we introduce a specialized tree-style data structure to efficiently encode, store and retrieve multi-grained contextual information for text chunks. This structure, combined with a search algorithm, enables rapid encoding and retrieval of relevant information from various levels of the tree based on the input query. This entire process, wherein the sender and receiver are derived from the same LLM layer, is referred to as self-injection.
Related papers
- Towards Text-Image Interleaved Retrieval [49.96332254241075]
We introduce the text-image interleaved retrieval (TIIR) task, where the query and document are interleaved text-image sequences.
We construct a TIIR benchmark based on naturally interleaved wikiHow tutorials, where a specific pipeline is designed to generate interleaved queries.
We propose a novel Matryoshka Multimodal Embedder (MME), which compresses the number of visual tokens at different granularity.
arXiv Detail & Related papers (2025-02-18T12:00:47Z) - BRIEF: Bridging Retrieval and Inference for Multi-hop Reasoning via Compression [91.23933111083389]
Retrieval-augmented generation (RAG) can supplement large language models (LLMs) by integrating external knowledge.
This paper presents BRIEF, a lightweight approach that performs query-aware multi-hop reasoning.
Based on our synthetic data built entirely by open-source models, BRIEF generates more concise summaries.
arXiv Detail & Related papers (2024-10-20T04:24:16Z) - Enhancing Long Context Performance in LLMs Through Inner Loop Query Mechanism [2.919891871101241]
Transformers have a quadratic scaling of computational complexity with input size.
Retrieval-augmented generation (RAG) can better handle longer contexts by using a retrieval system.
We introduce a novel approach, Inner Loop Memory Augmented Tree Retrieval (ILM-TR)
arXiv Detail & Related papers (2024-10-11T19:49:05Z) - Less is More: Making Smaller Language Models Competent Subgraph Retrievers for Multi-hop KGQA [51.3033125256716]
We model the subgraph retrieval task as a conditional generation task handled by small language models.
Our base generative subgraph retrieval model, consisting of only 220M parameters, competitive retrieval performance compared to state-of-the-art models.
Our largest 3B model, when plugged with an LLM reader, sets new SOTA end-to-end performance on both the WebQSP and CWQ benchmarks.
arXiv Detail & Related papers (2024-10-08T15:22:36Z) - LLMLingua: Compressing Prompts for Accelerated Inference of Large
Language Models [22.06402870816756]
Large language models (LLMs) have been applied in various applications due to their astonishing capabilities.
This paper presents LLMLingua, a coarse-to-fine prompt compression method that involves a budget controller to maintain semantic integrity.
We show that the proposed approach yields state-of-the-art performance and allows for up to 20x compression with little performance loss.
arXiv Detail & Related papers (2023-10-09T14:10:21Z) - Retrieving-to-Answer: Zero-Shot Video Question Answering with Frozen
Large Language Models [69.59125732317972]
We propose a simple yet effective Retrieving-to-Answer (R2A) framework for VideoQA.
R2A first retrieves a set of semantically similar texts from a generic text corpus using a pre-trained multi-modal model.
With both the question and the retrieved texts, a LLM can be directly used to yield a desired answer.
arXiv Detail & Related papers (2023-06-15T20:56:20Z) - Speculative Decoding with Big Little Decoder [108.95187338417541]
Big Little Decoder (BiLD) is a framework that can improve inference efficiency and latency for a wide range of text generation applications.
On an NVIDIA T4 GPU, our framework achieves a speedup of up to 2.12x speedup with minimal generation quality degradation.
Our framework is fully plug-and-play and can be applied without any modifications in the training process or model architecture.
arXiv Detail & Related papers (2023-02-15T18:55:29Z)
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.