Writing in the Margins: Better Inference Pattern for Long Context Retrieval

• URL: http://arxiv.org/abs/2408.14906v1
• Date: Tue, 27 Aug 2024 09:34:38 GMT
• Title: Writing in the Margins: Better Inference Pattern for Long Context Retrieval
• Authors: Melisa Russak, Umar Jamil, Christopher Bryant, Kiran Kamble, Axel Magnuson, Mateusz Russak, Waseem AlShikh,
• Abstract summary: Writing in the Margins (WiM) is an inference pattern designed to optimize the handling of long input sequences in retrieval-oriented tasks. We show how the proposed pattern fits into an interactive retrieval design that provides end-users with ongoing updates about the progress of context processing.
• Score: 0.9404560827144429
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: In this paper, we introduce Writing in the Margins (WiM), a new inference pattern for Large Language Models designed to optimize the handling of long input sequences in retrieval-oriented tasks. This approach leverages the chunked prefill of the key-value cache to perform segment-wise inference, which enables efficient processing of extensive contexts along with the generation and classification of intermediate information ("margins") that guide the model towards specific tasks. This method increases computational overhead marginally while significantly enhancing the performance of off-the-shelf models without the need for fine-tuning. Specifically, we observe that WiM provides an average enhancement of 7.5% in accuracy for reasoning skills (HotpotQA, MultiHop-RAG) and more than a 30.0% increase in the F1-score for aggregation tasks (CWE). Additionally, we show how the proposed pattern fits into an interactive retrieval design that provides end-users with ongoing updates about the progress of context processing, and pinpoints the integration of relevant information into the final response. We release our implementation of WiM using Hugging Face Transformers library at https://github.com/writer/writing-in-the-margins.

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)
• Recycled Attention: Efficient inference for long-context language models [54.00118604124301]
  We propose Recycled Attention, an inference-time method which alternates between full context attention and attention over a subset of input tokens. When performing partial attention, we recycle the attention pattern of a previous token that has performed full attention and attend only to the top K most attended tokens. Compared to previously proposed inference-time acceleration method which attends only to local context or tokens with high accumulative attention scores, our approach flexibly chooses tokens that are relevant to the current decoding step.
  arXiv  Detail & Related papers  (2024-11-08T18:57:07Z)
• Enhancing Question Answering Precision with Optimized Vector Retrieval and Instructions [1.2425910171551517]
  Question-answering (QA) is an important application of Information Retrieval (IR) and language models. We propose an innovative approach to improve QA task performances by integrating optimized vector retrievals and instruction methodologies.
  arXiv  Detail & Related papers  (2024-11-01T21:14:04Z)
• Better RAG using Relevant Information Gain [1.5604249682593647]
  A common way to extend the memory of large language models (LLMs) is by retrieval augmented generation (RAG) We propose a novel simple optimization metric based on relevant information gain, a probabilistic measure of the total information relevant to a query for a set of retrieved results. When used as a drop-in replacement for the retrieval component of a RAG system, this method yields state-of-the-art performance on question answering tasks.
  arXiv  Detail & Related papers  (2024-07-16T18:09:21Z)
• Fine-Tuning or Fine-Failing? Debunking Performance Myths in Large Language Models [0.8399688944263842]
  Large Language Models (LLMs) have the capability to understand and generate human-like text from input queries. This study extends this concept to the integration of LLMs within Retrieval-Augmented Generation (RAG) pipelines. We evaluate the impact of fine-tuning on the LLMs' capacity for data extraction and contextual understanding.
  arXiv  Detail & Related papers  (2024-06-17T04:35:17Z)
• Efficient Training of Language Models to Fill in the Middle [17.118891860985123]
  We show that autoregressive language models can learn to infill text after we apply a straightforward transformation to the dataset. We use these ablations to prescribe strong default settings and best practices to train FIM models. We have released our best infilling model trained with best practices in our API, and release our infilling benchmarks to aid future research.
  arXiv  Detail & Related papers  (2022-07-28T17:40:47Z)
• Long Document Summarization with Top-down and Bottom-up Inference [113.29319668246407]
  We propose a principled inference framework to improve summarization models on two aspects. Our framework assumes a hierarchical latent structure of a document where the top-level captures the long range dependency. We demonstrate the effectiveness of the proposed framework on a diverse set of summarization datasets.
  arXiv  Detail & Related papers  (2022-03-15T01:24:51Z)
• Meeting Summarization with Pre-training and Clustering Methods [6.47783315109491]
  HMNetcitehmnet is a hierarchical network that employs both a word-level transformer and a turn-level transformer, as the baseline. We extend the locate-then-summarize approach of QMSumciteqmsum with an intermediate clustering step. We compare the performance of our baseline models with BART, a state-of-the-art language model that is effective for summarization.
  arXiv  Detail & Related papers  (2021-11-16T03:14:40Z)
• Efficient Nearest Neighbor Language Models [114.40866461741795]
  Non-parametric neural language models (NLMs) learn predictive distributions of text utilizing an external datastore. We show how to achieve up to a 6x speed-up in inference speed while retaining comparable performance.
  arXiv  Detail & Related papers  (2021-09-09T12:32:28Z)
• X2Parser: Cross-Lingual and Cross-Domain Framework for Task-Oriented Compositional Semantic Parsing [51.81533991497547]
  Task-oriented compositional semantic parsing (TCSP) handles complex nested user queries. We present X2 compared a transferable Cross-lingual and Cross-domain for TCSP. We propose to predict flattened intents and slots representations separately and cast both prediction tasks into sequence labeling problems.
  arXiv  Detail & Related papers  (2021-06-07T16:40:05Z)
• Unsupervised Paraphrasing with Pretrained Language Models [85.03373221588707]
  We propose a training pipeline that enables pre-trained language models to generate high-quality paraphrases in an unsupervised setting. Our recipe consists of task-adaptation, self-supervision, and a novel decoding algorithm named Dynamic Blocking. We show with automatic and human evaluations that our approach achieves state-of-the-art performance on both the Quora Question Pair and the ParaNMT datasets.
  arXiv  Detail & Related papers  (2020-10-24T11:55:28Z)

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.