Summary of a Haystack: A Challenge to Long-Context LLMs and RAG Systems

• URL: http://arxiv.org/abs/2407.01370v1
• Date: Mon, 1 Jul 2024 15:23:42 GMT
• Title: Summary of a Haystack: A Challenge to Long-Context LLMs and RAG Systems
• Authors: Philippe Laban, Alexander R. Fabbri, Caiming Xiong, Chien-Sheng Wu,
• Abstract summary: We design a procedure to synthesize Haystacks of documents, ensuring that specific textitinsights repeat across documents. The "Summary of a Haystack" (SummHay) task then requires a system to process the Haystack and generate, given a query, a summary that identifies the relevant insights and precisely cites the source documents.
• Score: 124.82815637571413
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: LLMs and RAG systems are now capable of handling millions of input tokens or more. However, evaluating the output quality of such systems on long-context tasks remains challenging, as tasks like Needle-in-a-Haystack lack complexity. In this work, we argue that summarization can play a central role in such evaluation. We design a procedure to synthesize Haystacks of documents, ensuring that specific \textit{insights} repeat across documents. The "Summary of a Haystack" (SummHay) task then requires a system to process the Haystack and generate, given a query, a summary that identifies the relevant insights and precisely cites the source documents. Since we have precise knowledge of what insights should appear in a haystack summary and what documents should be cited, we implement a highly reproducible automatic evaluation that can score summaries on two aspects - Coverage and Citation. We generate Haystacks in two domains (conversation, news), and perform a large-scale evaluation of 10 LLMs and corresponding 50 RAG systems. Our findings indicate that SummHay is an open challenge for current systems, as even systems provided with an Oracle signal of document relevance lag our estimate of human performance (56\%) by 10+ points on a Joint Score. Without a retriever, long-context LLMs like GPT-4o and Claude 3 Opus score below 20% on SummHay. We show SummHay can also be used to study enterprise RAG systems and position bias in long-context models. We hope future systems can equal and surpass human performance on SummHay.

Related papers

• DOCBENCH: A Benchmark for Evaluating LLM-based Document Reading Systems [99.17123445211115]
  We introduce DocBench, a benchmark to evaluate large language model (LLM)-based document reading systems. Our benchmark involves the recruitment of human annotators and the generation of synthetic questions. It includes 229 real documents and 1,102 questions, spanning across five different domains and four major types of questions.
  arXiv  Detail & Related papers  (2024-07-15T13:17:42Z)
• Attribute or Abstain: Large Language Models as Long Document Assistants [58.32043134560244]
  LLMs can help humans working with long documents, but are known to hallucinate. Existing approaches to attribution have only been evaluated in RAG settings, where the initial retrieval confounds LLM performance. This is crucially different from the long document setting, where retrieval is not needed, but could help. We present LAB, a benchmark of 6 diverse long document tasks with attribution, and experiments with different approaches to attribution on 5 LLMs of different sizes.
  arXiv  Detail & Related papers  (2024-07-10T16:16:02Z)
• Harnessing Multi-Role Capabilities of Large Language Models for Open-Domain Question Answering [40.2758450304531]
  Open-domain question answering (ODQA) has emerged as a pivotal research spotlight in information systems. We propose a framework that formulates the ODQA process into three basic steps: query expansion, document selection, and answer generation. We introduce a novel prompt optimization algorithm to refine role-playing prompts and steer LLMs to produce higher-quality evidence and answers.
  arXiv  Detail & Related papers  (2024-03-08T11:09:13Z)
• DAPR: A Benchmark on Document-Aware Passage Retrieval [57.45793782107218]
  We propose and name this task emphDocument-Aware Passage Retrieval (DAPR) While analyzing the errors of the State-of-The-Art (SoTA) passage retrievers, we find the major errors (53.5%) are due to missing document context. Our created benchmark enables future research on developing and comparing retrieval systems for the new task.
  arXiv  Detail & Related papers  (2023-05-23T10:39:57Z)
• DAMO-NLP at SemEval-2023 Task 2: A Unified Retrieval-augmented System for Multilingual Named Entity Recognition [94.90258603217008]
  The MultiCoNER RNum2 shared task aims to tackle multilingual named entity recognition (NER) in fine-grained and noisy scenarios. Previous top systems in the MultiCoNER RNum1 either incorporate the knowledge bases or gazetteers. We propose a unified retrieval-augmented system (U-RaNER) for fine-grained multilingual NER.
  arXiv  Detail & Related papers  (2023-05-05T16:59:26Z)
• Visconde: Multi-document QA with GPT-3 and Neural Reranking [4.9069311006119865]
  This paper proposes a question-answering system that can answer questions whose supporting evidence is spread over multiple documents. The system, called Visconde, uses a three-step pipeline to perform the task: decompose, retrieve, and aggregate.
  arXiv  Detail & Related papers  (2022-12-19T17:39:07Z)
• Text Summarization with Latent Queries [60.468323530248945]
  We introduce LaQSum, the first unified text summarization system that learns Latent Queries from documents for abstractive summarization with any existing query forms. Under a deep generative framework, our system jointly optimize a latent query model and a conditional language model, allowing users to plug-and-play queries of any type at test time. Our system robustly outperforms strong comparison systems across summarization benchmarks with different query types, document settings, and target domains.
  arXiv  Detail & Related papers  (2021-05-31T21:14:58Z)
• Hurdles to Progress in Long-form Question Answering [34.805039943215284]
  We show that the task formulation raises fundamental challenges regarding evaluation and dataset creation. We first design a new system that relies on sparse attention and contrastive retriever learning to achieve state-of-the-art performance.
  arXiv  Detail & Related papers  (2021-03-10T20:32:30Z)

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.