CMDBench: A Benchmark for Coarse-to-fine Multimodal Data Discovery in Compound AI Systems

• URL: http://arxiv.org/abs/2406.00583v1
• Date: Sun, 2 Jun 2024 01:10:41 GMT
• Title: CMDBench: A Benchmark for Coarse-to-fine Multimodal Data Discovery in Compound AI Systems
• Authors: Yanlin Feng, Sajjadur Rahman, Aaron Feng, Vincent Chen, Eser Kandogan,
• Abstract summary: Compound AI systems (CASs) that employ LLMs as agents to accomplish knowledge-intensive tasks have garnered significant interest within database and AI communities. silos of multimodal data sources make it difficult to identify appropriate data sources for accomplishing the task at hand. We propose CMDBench, a benchmark modeling the complexity of enterprise data platforms.
• Score: 10.71630696651595
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Compound AI systems (CASs) that employ LLMs as agents to accomplish knowledge-intensive tasks via interactions with tools and data retrievers have garnered significant interest within database and AI communities. While these systems have the potential to supplement typical analysis workflows of data analysts in enterprise data platforms, unfortunately, CASs are subject to the same data discovery challenges that analysts have encountered over the years -- silos of multimodal data sources, created across teams and departments within an organization, make it difficult to identify appropriate data sources for accomplishing the task at hand. Existing data discovery benchmarks do not model such multimodality and multiplicity of data sources. Moreover, benchmarks of CASs prioritize only evaluating end-to-end task performance. To catalyze research on evaluating the data discovery performance of multimodal data retrievers in CASs within a real-world setting, we propose CMDBench, a benchmark modeling the complexity of enterprise data platforms. We adapt existing datasets and benchmarks in open-domain -- from question answering and complex reasoning tasks to natural language querying over structured data -- to evaluate coarse- and fine-grained data discovery and task execution performance. Our experiments reveal the impact of data retriever design on downstream task performance -- a 46% drop in task accuracy on average -- across various modalities, data sources, and task difficulty. The results indicate the need to develop optimization strategies to identify appropriate LLM agents and retrievers for efficient execution of CASs over enterprise data.

Related papers

• Data Proportion Detection for Optimized Data Management for Large Language Models [32.62631669919273]
  We introduce a new topic, textitdata proportion detection, which enables the automatic estimation of pre-training data proportions. We provide rigorous theoretical proofs, practical algorithms, and preliminary experimental results for data proportion detection.
  arXiv  Detail & Related papers  (2024-09-26T04:30:32Z)
• DSBench: How Far Are Data Science Agents to Becoming Data Science Experts? [58.330879414174476]
  We introduce DSBench, a benchmark designed to evaluate data science agents with realistic tasks. This benchmark includes 466 data analysis tasks and 74 data modeling tasks, sourced from Eloquence and Kaggle competitions. Our evaluation of state-of-the-art LLMs, LVLMs, and agents shows that they struggle with most tasks, with the best agent solving only 34.12% of data analysis tasks and achieving a 34.74% Relative Performance Gap (RPG)
  arXiv  Detail & Related papers  (2024-09-12T02:08:00Z)
• CRAFT Your Dataset: Task-Specific Synthetic Dataset Generation Through Corpus Retrieval and Augmentation [51.2289822267563]
  We propose Corpus Retrieval and Augmentation for Fine-Tuning (CRAFT), a method for generating synthetic datasets. We use large-scale public web-crawled corpora and similarity-based document retrieval to find other relevant human-written documents. We demonstrate that CRAFT can efficiently generate large-scale task-specific training datasets for four diverse tasks.
  arXiv  Detail & Related papers  (2024-09-03T17:54:40Z)
• Distributed In-Context Learning under Non-IID Among Clients [38.868357555845435]
  In-context learning (ICL) provides a promising solution for few-shot adaptation by retrieving a set of data points relevant to a query. In this paper, we show that test queries will have different preferences among clients because of non-IIDness. We introduce a novel approach to tackle the distributed non-IID ICL problem when a data usage budget is present.
  arXiv  Detail & Related papers  (2024-07-31T20:06:25Z)
• DiscoveryBench: Towards Data-Driven Discovery with Large Language Models [50.36636396660163]
  We present DiscoveryBench, the first comprehensive benchmark that formalizes the multi-step process of data-driven discovery. Our benchmark contains 264 tasks collected across 6 diverse domains, such as sociology and engineering. Our benchmark, thus, illustrates the challenges in autonomous data-driven discovery and serves as a valuable resource for the community to make progress.
  arXiv  Detail & Related papers  (2024-07-01T18:58:22Z)
• Data-Centric AI in the Age of Large Language Models [51.20451986068925]
  This position paper proposes a data-centric viewpoint of AI research, focusing on large language models (LLMs) We make the key observation that data is instrumental in the developmental (e.g., pretraining and fine-tuning) and inferential stages (e.g., in-context learning) of LLMs. We identify four specific scenarios centered around data, covering data-centric benchmarks and data curation, data attribution, knowledge transfer, and inference contextualization.
  arXiv  Detail & Related papers  (2024-06-20T16:34:07Z)
• DACO: Towards Application-Driven and Comprehensive Data Analysis via Code Generation [83.30006900263744]
  Data analysis is a crucial analytical process to generate in-depth studies and conclusive insights. We propose to automatically generate high-quality answer annotations leveraging the code-generation capabilities of LLMs. Our DACO-RL algorithm is evaluated by human annotators to produce more helpful answers than SFT model in 57.72% cases.
  arXiv  Detail & Related papers  (2024-03-04T22:47:58Z)
• Can Large Language Models Serve as Data Analysts? A Multi-Agent Assisted Approach for Qualitative Data Analysis [6.592797748561459]
  Large Language Models (LLMs) have enabled collaborative human-bot interactions in Software Engineering (SE) We introduce a new dimension of scalability and accuracy in qualitative research, potentially transforming data interpretation methodologies in SE.
  arXiv  Detail & Related papers  (2024-02-02T13:10:46Z)
• STAR: Boosting Low-Resource Information Extraction by Structure-to-Text Data Generation with Large Language Models [56.27786433792638]
  STAR is a data generation method that leverages Large Language Models (LLMs) to synthesize data instances. We design fine-grained step-by-step instructions to obtain the initial data instances. Our experiments show that the data generated by STAR significantly improve the performance of low-resource event extraction and relation extraction tasks.
  arXiv  Detail & Related papers  (2023-05-24T12:15:19Z)
• GAN-based Tabular Data Generator for Constructing Synopsis in Approximate Query Processing: Challenges and Solutions [0.0]
  Approximate Query Processing (AQP) is a technique for providing approximate answers to aggregate queries based on a summary of the data (synopsis) This study explores the novel utilization of Generative Adversarial Networks (GANs) in the generation of tabular data that can be employed in AQP for synopsis construction. Our findings demonstrate that advanced GAN variations exhibit a promising capacity to generate high-fidelity synopses, potentially transforming the efficiency and effectiveness of AQP in data-driven systems.
  arXiv  Detail & Related papers  (2022-12-18T05:11:04Z)

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.