Inference Scaling for Long-Context Retrieval Augmented Generation

• URL: http://arxiv.org/abs/2410.04343v1
• Date: Sun, 6 Oct 2024 03:42:15 GMT
• Title: Inference Scaling for Long-Context Retrieval Augmented Generation
• Authors: Zhenrui Yue, Honglei Zhuang, Aijun Bai, Kai Hui, Rolf Jagerman, Hansi Zeng, Zhen Qin, Dong Wang, Xuanhui Wang, Michael Bendersky,
• Abstract summary: In this work, we investigate inference scaling for retrieval augmented generation (RAG) We focus on two inference scaling strategies: in-context learning and iterative prompting. We demonstrate that scaling inference compute on long-context large language models achieves up to 58.9% gains on benchmark datasets.
• Score: 37.15479223789199
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The scaling of inference computation has unlocked the potential of long-context large language models (LLMs) across diverse settings. For knowledge-intensive tasks, the increased compute is often allocated to incorporate more external knowledge. However, without effectively utilizing such knowledge, solely expanding context does not always enhance performance. In this work, we investigate inference scaling for retrieval augmented generation (RAG), exploring strategies beyond simply increasing the quantity of knowledge. We focus on two inference scaling strategies: in-context learning and iterative prompting. These strategies provide additional flexibility to scale test-time computation (e.g., by increasing retrieved documents or generation steps), thereby enhancing LLMs' ability to effectively acquire and utilize contextual information. We address two key questions: (1) How does RAG performance benefit from the scaling of inference computation when optimally configured? (2) Can we predict the optimal test-time compute allocation for a given budget by modeling the relationship between RAG performance and inference parameters? Our observations reveal that increasing inference computation leads to nearly linear gains in RAG performance when optimally allocated, a relationship we describe as the inference scaling laws for RAG. Building on this, we further develop the computation allocation model to estimate RAG performance across different inference configurations. The model predicts optimal inference parameters under various computation constraints, which align closely with the experimental results. By applying these optimal configurations, we demonstrate that scaling inference compute on long-context LLMs achieves up to 58.9% gains on benchmark datasets compared to standard RAG.

Related papers

• Recursive Inference Scaling: A Winning Path to Scalable Inference in Language and Multimodal Systems [21.01887711305712]
  We introduce Recursive INference Scaling (RINS) as a complementary, plug-in recipe for scaling inference time. For a given fixed model architecture and training compute budget, RINS substantially improves language modeling performance. RINS delivers gains in multimodal systems, including a +2% improvement in 0-shot ImageNet accuracy for SigLIP-B/16.
  arXiv  Detail & Related papers  (2025-02-11T12:11:40Z)
• Value-Based Deep RL Scales Predictably [100.21834069400023]
  We show that value-based off-policy RL methods are predictable despite community lore regarding their pathological behavior. We validate our approach using three algorithms: SAC, BRO, and PQL on DeepMind Control, OpenAI gym, and IsaacGym.
  arXiv  Detail & Related papers  (2025-02-06T18:59:47Z)
• Learning Provably Improves the Convergence of Gradient Descent [9.82454981262489]
  We study the convergence of Learning to Optimize (L2O) problems by training-based solvers. An algorithm's tangent significantly enhances L2O's convergence. Our findings indicate 50% outperformance over the GD methods.
  arXiv  Detail & Related papers  (2025-01-30T02:03:30Z)
• Chain-of-Retrieval Augmented Generation [72.06205327186069]
  This paper introduces an approach for training o1-like RAG models that retrieve and reason over relevant information step by step before generating the final answer. Our proposed method, CoRAG, allows the model to dynamically reformulate the query based on the evolving state.
  arXiv  Detail & Related papers  (2025-01-24T09:12:52Z)
• Optimizing Sequential Recommendation Models with Scaling Laws and Approximate Entropy [104.48511402784763]
  Performance Law for SR models aims to theoretically investigate and model the relationship between model performance and data quality. We propose Approximate Entropy (ApEn) to assess data quality, presenting a more nuanced approach compared to traditional data quantity metrics.
  arXiv  Detail & Related papers  (2024-11-30T10:56:30Z)
• 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)
• AUCSeg: AUC-oriented Pixel-level Long-tail Semantic Segmentation [88.50256898176269]
  We develop a pixel-level AUC loss function and conduct a dependency-graph-based theoretical analysis of the algorithm's generalization ability. We also design a Tail-Classes Memory Bank to manage the significant memory demand.
  arXiv  Detail & Related papers  (2024-09-30T15:31:02Z)
• Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters [27.656263126925815]
  We study the scaling of inference-time computation in LLMs. We find that in both cases, the effectiveness of different approaches to scaling test-time compute critically varies depending on the difficulty of the prompt.
  arXiv  Detail & Related papers  (2024-08-06T17:35:05Z)
• Switchable Decision: Dynamic Neural Generation Networks [98.61113699324429]
  We propose a switchable decision to accelerate inference by dynamically assigning resources for each data instance. Our method benefits from less cost during inference while keeping the same accuracy.
  arXiv  Detail & Related papers  (2024-05-07T17:44:54Z)
• Target Variable Engineering [0.0]
  We compare the predictive performance of regression models trained to predict numeric targets vs. classifiers trained to predict their binarized counterparts. We find that regression requires significantly more computational effort to converge upon the optimal performance.
  arXiv  Detail & Related papers  (2023-10-13T23:12:21Z)

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.