Holistic Reasoning with Long-Context LMs: A Benchmark for Database Operations on Massive Textual Data

• URL: http://arxiv.org/abs/2410.11996v1
• Date: Tue, 15 Oct 2024 19:04:13 GMT
• Title: Holistic Reasoning with Long-Context LMs: A Benchmark for Database Operations on Massive Textual Data
• Authors: Seiji Maekawa, Hayate Iso, Nikita Bhutani,
• Abstract summary: We introduce HoloBench, a framework that brings database reasoning operations into text-based contexts. We show that the amount of information in the context has a bigger influence on LCLM performance than the context length. We find that tasks requiring the aggregation of multiple pieces of information show a noticeable drop in accuracy as context length increases.
• Score: 6.195658947075431
• License:
• Abstract: The rapid increase in textual information means we need more efficient methods to sift through, organize, and understand it all. While retrieval-augmented generation (RAG) models excel in accessing information from large document collections, they struggle with complex tasks that require aggregation and reasoning over information spanning across multiple documents--what we call holistic reasoning. Long-context language models (LCLMs) have great potential for managing large-scale documents, but their holistic reasoning capabilities remain unclear. In this work, we introduce HoloBench, a novel framework that brings database reasoning operations into text-based contexts, making it easier to systematically evaluate how LCLMs handle holistic reasoning across large documents. Our approach adjusts key factors such as context length, information density, distribution of information, and query complexity to evaluate LCLMs comprehensively. Our experiments show that the amount of information in the context has a bigger influence on LCLM performance than the actual context length. Furthermore, the complexity of queries affects performance more than the amount of information, particularly for different types of queries. Interestingly, queries that involve finding maximum or minimum values are easier for LCLMs and are less affected by context length, even though they pose challenges for RAG systems. However, tasks requiring the aggregation of multiple pieces of information show a noticeable drop in accuracy as context length increases. Additionally, we find that while grouping relevant information generally improves performance, the optimal positioning varies across models. Our findings surface both the advancements and the ongoing challenges in achieving a holistic understanding of long contexts.

Related papers

• Retrieval or Global Context Understanding? On Many-Shot In-Context Learning for Long-Context Evaluation [10.500629810624769]
  We study long-context language models evaluation through many-shot in-context learning (ICL) We identify the skills each ICL task requires, and examine models' long-context capabilities on them. We introduce a new many-shot ICL benchmark, MANYICLBENCH, designed to characterize LCLMs' retrieval and global context understanding capabilities separately.
  arXiv  Detail & Related papers  (2024-11-11T17:00:59Z)
• LLM$\times$MapReduce: Simplified Long-Sequence Processing using Large Language Models [73.13933847198395]
  We propose a training-free framework for processing long texts, utilizing a divide-and-conquer strategy to achieve comprehensive document understanding. The proposed LLM$times$MapReduce framework splits the entire document into several chunks for LLMs to read and then aggregates the intermediate answers to produce the final output.
  arXiv  Detail & Related papers  (2024-10-12T03:13:44Z)
• SEGMENT+: Long Text Processing with Short-Context Language Models [53.40059130780192]
  SEGMENT+ is a framework that enables LMs to handle extended inputs within limited context windows efficiently. SEGMENT+ utilizes structured notes and a filtering module to manage information flow, resulting in a system that is both controllable and interpretable.
  arXiv  Detail & Related papers  (2024-10-09T03:40:22Z)
• NeedleBench: Can LLMs Do Retrieval and Reasoning in 1 Million Context Window? [37.64593022203498]
  NeedleBench is a framework consisting of progressively more challenging tasks for assessing bilingual long-context capabilities. We use the framework to assess how well the leading open-source models can identify key information relevant to the question. We propose the Ancestral Trace Challenge to mimic the complexity of logical reasoning challenges that are likely to be present in real-world long-context tasks.
  arXiv  Detail & Related papers  (2024-07-16T17:59:06Z)
• Can Long-Context Language Models Subsume Retrieval, RAG, SQL, and More? [54.667202878390526]
  Long-context language models (LCLMs) have the potential to revolutionize our approach to tasks traditionally reliant on external tools like retrieval systems or databases. We introduce LOFT, a benchmark of real-world tasks requiring context up to millions of tokens designed to evaluate LCLMs' performance on in-context retrieval and reasoning. Our findings reveal LCLMs' surprising ability to rival state-of-the-art retrieval and RAG systems, despite never having been explicitly trained for these tasks.
  arXiv  Detail & Related papers  (2024-06-19T00:28:58Z)
• Automating Pharmacovigilance Evidence Generation: Using Large Language Models to Produce Context-Aware SQL [0.0]
  We utilize OpenAI's GPT-4 model within a retrieval-augmented generation (RAG) framework. Business context document is enriched with a business context document, to transform NLQs into Structured Query Language queries. Performance achieved a maximum of 85% when high complexity queries are excluded.
  arXiv  Detail & Related papers  (2024-06-15T17:07:31Z)
• TACT: Advancing Complex Aggregative Reasoning with Information Extraction Tools [51.576974932743596]
  Large Language Models (LLMs) often do not perform well on queries that require the aggregation of information across texts. TACT contains challenging instructions that demand stitching information scattered across one or more texts. We construct this dataset by leveraging an existing dataset of texts and their associated tables. We demonstrate that all contemporary LLMs perform poorly on this dataset, achieving an accuracy below 38%.
  arXiv  Detail & Related papers  (2024-06-05T20:32:56Z)
• Unsupervised Information Refinement Training of Large Language Models for Retrieval-Augmented Generation [128.01050030936028]
  We propose an information refinement training method named InFO-RAG. InFO-RAG is low-cost and general across various tasks. It improves the performance of LLaMA2 by an average of 9.39% relative points.
  arXiv  Detail & Related papers  (2024-02-28T08:24:38Z)
• Learning to Reduce: Optimal Representations of Structured Data in Prompting Large Language Models [42.16047343029512]
  Large Language Models (LLMs) have been widely used as general-purpose AI agents. We propose a framework, Learning to Reduce, that fine-tunes a language model to generate a reduced version of an input context. We show that our model achieves comparable accuracies in selecting the relevant evidence from an input context.
  arXiv  Detail & Related papers  (2024-02-22T00:41:23Z)
• Can Large Language Models Understand Real-World Complex Instructions? [54.86632921036983]
  Large language models (LLMs) can understand human instructions, but struggle with complex instructions. Existing benchmarks are insufficient to assess LLMs' ability to understand complex instructions. We propose CELLO, a benchmark for evaluating LLMs' ability to follow complex instructions systematically.
  arXiv  Detail & Related papers  (2023-09-17T04:18:39Z)

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.