DataPuzzle: Breaking Free from the Hallucinated Promise of LLMs in Data Analysis

• URL: http://arxiv.org/abs/2504.10036v2
• Date: Sun, 28 Sep 2025 05:12:23 GMT
• Title: DataPuzzle: Breaking Free from the Hallucinated Promise of LLMs in Data Analysis
• Authors: Zhengxuan Zhang, Zhuowen Liang, Yin Wu, Teng Lin, Yuyu Luo, Nan Tang,
• Abstract summary: Large language models (LLMs) are increasingly applied to multi-modal data analysis.<n>The prevailing Prompt-to-Answer'' paradigm treats LLMs as black-box analysts.<n>We propose DataPuzzle, a conceptual multi-agent framework that decomposes complex questions.
• Score: 10.98270220152657
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large language models (LLMs) are increasingly applied to multi-modal data analysis -- not necessarily because they offer the most precise answers, but because they provide fluent, flexible interfaces for interpreting complex inputs. Yet this fluency often conceals a deeper structural failure: the prevailing ``Prompt-to-Answer'' paradigm treats LLMs as black-box analysts, collapsing evidence, reasoning, and conclusions into a single, opaque response. The result is brittle, unverifiable, and frequently misleading. We argue for a fundamental shift: from generation to structured extraction, from monolithic prompts to modular, agent-based workflows. LLMs should not serve as oracles, but as collaborators -- specialized in tasks like extraction, translation, and linkage -- embedded within transparent workflows that enable step-by-step reasoning and verification. We propose DataPuzzle, a conceptual multi-agent framework that decomposes complex questions, structures information into interpretable forms (e.g. tables, graphs), and coordinates agent roles to support transparent and verifiable analysis. This framework serves as an aspirational blueprint for restoring visibility and control in LLM-driven analytics -- transforming opaque answers into traceable processes, and brittle fluency into accountable insight. This is not a marginal refinement; it is a call to reimagine how we build trustworthy, auditable analytic systems in the era of large language models. Structure is not a constraint -- it is the path to clarity.

Related papers

• Farther the Shift, Sparser the Representation: Analyzing OOD Mechanisms in LLMs [100.02824137397464]
  We investigate how Large Language Models adapt their internal representations when encountering inputs of increasing difficulty.<n>We reveal a consistent and quantifiable phenomenon: as task difficulty increases, the last hidden states of LLMs become substantially sparser.<n>This sparsity--difficulty relation is observable across diverse models and domains.
  arXiv  Detail & Related papers  (2026-03-03T18:48:15Z)
• Step-Level Sparse Autoencoder for Reasoning Process Interpretation [48.99201531966593]
  Large Language Models (LLMs) have achieved strong complex reasoning capabilities through Chain-of-Thought (CoT) reasoning.<n>We propose step-level sparse autoencoder (SSAE), which serves as an analytical tool to disentangle different aspects of LLMs' reasoning steps into sparse features.<n> Experiments on multiple base models and reasoning tasks show the effectiveness of the extracted features.
  arXiv  Detail & Related papers  (2026-03-03T14:25:02Z)
• Diagnosing Structural Failures in LLM-Based Evidence Extraction for Meta-Analysis [0.8193467416247519]
  Review and meta-analyses rely on converting narrative articles into structured, numerically grounded study records.<n>Despite rapid advances in large language models (LLMs), it remains unclear whether they can meet the structural requirements of this process.<n>We propose a structural, diagnostic framework that evaluates LLM-based evidence extraction as a progression of schema-constrained queries.
  arXiv  Detail & Related papers  (2026-02-11T14:09:43Z)
• LLM Agents for Interactive Workflow Provenance: Reference Architecture and Evaluation Methodology [3.470217255779291]
  We introduce an evaluation methodology, reference architecture, and open-source implementation that leverages interactive Large Language Model (LLM) agents for runtime data analysis.<n>Our approach uses a lightweight, metadata-driven design that translates natural language into structured provenance queries.<n> Evaluations across LLaMA, GPT, Gemini, and Claude, covering diverse query classes and a real-world chemistry workflow, show that modular design, prompt tuning, and Retrieval-Augmented Generation (RAG) enable accurate and insightful agent responses.
  arXiv  Detail & Related papers  (2025-09-17T13:51:29Z)
• Reasoning-enhanced Query Understanding through Decomposition and Interpretation [87.56450566014625]
  ReDI is a Reasoning-enhanced approach for query understanding through Decomposition and Interpretation.<n>We compiled a large-scale dataset of real-world complex queries from a major search engine.<n> Experiments on BRIGHT and BEIR demonstrate that ReDI consistently surpasses strong baselines in both sparse and dense retrieval paradigms.
  arXiv  Detail & Related papers  (2025-09-08T10:58:42Z)
• DeepSieve: Information Sieving via LLM-as-a-Knowledge-Router [57.28685457991806]
  DeepSieve is an agentic RAG framework that incorporates information sieving via LLM-as-a-knowledge-router.<n>Our design emphasizes modularity, transparency, and adaptability, leveraging recent advances in agentic system design.
  arXiv  Detail & Related papers  (2025-07-29T17:55:23Z)
• Beyond Isolated Dots: Benchmarking Structured Table Construction as Deep Knowledge Extraction [80.88654868264645]
  Arranged and Organized Extraction Benchmark designed to evaluate ability of large language models to comprehend fragmented documents.<n>AOE includes 11 carefully crafted tasks across three diverse domains, requiring models to generate context-specific schema tailored to varied input queries.<n>Results show that even the most advanced models struggled significantly.
  arXiv  Detail & Related papers  (2025-07-22T06:37:51Z)
• IDA-Bench: Evaluating LLMs on Interactive Guided Data Analysis [60.32962597618861]
  IDA-Bench is a novel benchmark evaluating large language models in multi-round interactive scenarios.<n>Agent performance is judged by comparing its final numerical output to the human-derived baseline.<n>Even state-of-the-art coding agents (like Claude-3.7-thinking) succeed on 50% of the tasks, highlighting limitations not evident in single-turn tests.
  arXiv  Detail & Related papers  (2025-05-23T09:37:52Z)
• TAIJI: MCP-based Multi-Modal Data Analytics on Data Lakes [25.05627023905607]
  We envision a new multi-modal data analytics system based on the Model Context Protocol (MCP)<n>First, we define a semantic operator hierarchy tailored for querying multi-modal data in data lakes.<n>Next, we introduce an MCP-based execution framework, in which each MCP server hosts specialized foundation models optimized for specific data modalities.
  arXiv  Detail & Related papers  (2025-05-16T14:03:30Z)
• Flowco: Rethinking Data Analysis in the Age of LLMs [2.1874189959020427]
  Large language models (LLMs) are now capable of generating such code for simple, routine analyses. LLMs promise to democratize data science by enabling those with limited programming expertise to conduct data analyses. Analysts in many real-world settings must often exercise fine-grained control over specific analysis steps. This paper introduces Flowco, a new mixed-initiative system to address these challenges.
  arXiv  Detail & Related papers  (2025-04-18T19:01:27Z)
• Beyond Quacking: Deep Integration of Language Models and RAG into DuckDB [44.057784044659726]
  Large language models (LLMs) have made it easier to prototype such retrieval and reasoning data pipelines.<n>This often involves orchestrating data systems, managing data movement, and handling low-level details.<n>We introduce FlockMTL: an extension for abstractions that integrates deeply LLM capabilities and retrieval-augmented generation.
  arXiv  Detail & Related papers  (2025-04-01T19:48:17Z)
• DatawiseAgent: A Notebook-Centric LLM Agent Framework for Automated Data Science [4.1431677219677185]
  DatawiseAgent is a notebook-centric agent framework that unifies interactions among user, agent and the computational environment.<n>It orchestrates four stages, including DSF-like planning, incremental execution, self-ging, and post-filtering.<n>It consistently outperforms or matches state-of-the-art methods across multiple model settings.
  arXiv  Detail & Related papers  (2025-03-10T08:32:33Z)
• Are Large Language Models Good Data Preprocessors? [5.954202581988127]
  High-quality textual training data is essential for the success of multimodal data processing tasks.<n> outputs from image captioning models like BLIP and GIT often contain errors and anomalies that are difficult to rectify using rule-based methods.
  arXiv  Detail & Related papers  (2025-02-24T02:57:21Z)
• Mitigating Forgetting in LLM Fine-Tuning via Low-Perplexity Token Learning [61.99353167168545]
  We show that fine-tuning with LLM-generated data improves target task performance and reduces non-target task degradation.<n>This is the first work to provide an empirical explanation based on token perplexity reduction to mitigate catastrophic forgetting in LLMs after fine-tuning.
  arXiv  Detail & Related papers  (2025-01-24T08:18:56Z)
• Empowering Large Language Models in Wireless Communication: A Novel Dataset and Fine-Tuning Framework [81.29965270493238]
  We develop a specialized dataset aimed at enhancing the evaluation and fine-tuning of large language models (LLMs) for wireless communication applications. The dataset includes a diverse set of multi-hop questions, including true/false and multiple-choice types, spanning varying difficulty levels from easy to hard. We introduce a Pointwise V-Information (PVI) based fine-tuning method, providing a detailed theoretical analysis and justification for its use in quantifying the information content of training data.
  arXiv  Detail & Related papers  (2025-01-16T16:19:53Z)
• Multi-Task Learning with LLMs for Implicit Sentiment Analysis: Data-level and Task-level Automatic Weight Learning [18.836998294161834]
  Implicit sentiment analysis presents significant challenges due to the absence of salient cue words.<n>We introduce MT-ISA, a novel MTL framework that enhances ISA by leveraging the generation and reasoning capabilities of large language models.<n>We introduce data-level and task-level automatic weight learning (AWL), which dynamically identifies relationships and prioritizes more reliable data and critical tasks.
  arXiv  Detail & Related papers  (2024-12-12T08:15:16Z)
• MAmmoTH-VL: Eliciting Multimodal Reasoning with Instruction Tuning at Scale [66.73529246309033]
  multimodal large language models (MLLMs) have shown significant potential in a broad range of multimodal tasks.<n>Existing instruction-tuning datasets only provide phrase-level answers without any intermediate rationales.<n>We introduce a scalable and cost-effective method to construct a large-scale multimodal instruction-tuning dataset with rich intermediate rationales.
  arXiv  Detail & Related papers  (2024-12-06T18:14:24Z)
• Web-Scale Visual Entity Recognition: An LLM-Driven Data Approach [56.55633052479446]
  Web-scale visual entity recognition presents significant challenges due to the lack of clean, large-scale training data. We propose a novel methodology to curate such a dataset, leveraging a multimodal large language model (LLM) for label verification, metadata generation, and rationale explanation. Experiments demonstrate that models trained on this automatically curated data achieve state-of-the-art performance on web-scale visual entity recognition tasks.
  arXiv  Detail & Related papers  (2024-10-31T06:55:24Z)
• Beyond Fine-Tuning: Effective Strategies for Mitigating Hallucinations in Large Language Models for Data Analytics [0.0]
  Large Language Models (LLMs) have become increasingly important in natural language processing, enabling advanced data analytics through natural language queries. These models often generate "hallucinations"-inaccurate or fabricated information-that can undermine their reliability in critical data-driven decision-making. This research focuses on mitigating hallucinations in LLMs, specifically within the context of data analytics.
  arXiv  Detail & Related papers  (2024-10-26T00:45:42Z)
• Enhancing LLM's Cognition via Structurization [41.13997892843677]
  Large language models (LLMs) process input contexts through a causal and sequential perspective. This paper presents a novel concept of context structurization. Specifically, we transform the plain, unordered contextual sentences into well-ordered and hierarchically structurized elements.
  arXiv  Detail & Related papers  (2024-07-23T12:33:58Z)
• Struct-X: Enhancing Large Language Models Reasoning with Structured Data [38.558614152006975]
  Struct-X operates through five key phases: read-model-fill-reflect-reason'' It encodes structured data into a topological space using graph embeddings. It fills in missing entity information with knowledge retrieval modules. The final phase involves constructing a topological network with selected tokens.
  arXiv  Detail & Related papers  (2024-07-17T13:06:25Z)
• SELF-GUIDE: Better Task-Specific Instruction Following via Self-Synthetic Finetuning [70.21358720599821]
  Large language models (LLMs) hold the promise of solving diverse tasks when provided with appropriate natural language prompts. We propose SELF-GUIDE, a multi-stage mechanism in which we synthesize task-specific input-output pairs from the student LLM. We report an absolute improvement of approximately 15% for classification tasks and 18% for generation tasks in the benchmark's metrics.
  arXiv  Detail & Related papers  (2024-07-16T04:41:58Z)
• DARG: Dynamic Evaluation of Large Language Models via Adaptive Reasoning Graph [70.79413606968814]
  We introduce Dynamic Evaluation of LLMs via Adaptive Reasoning Graph Evolvement (DARG) to dynamically extend current benchmarks with controlled complexity and diversity. Specifically, we first extract the reasoning graphs of data points in current benchmarks and then perturb the reasoning graphs to generate novel testing data. Such newly generated test samples can have different levels of complexity while maintaining linguistic diversity similar to the original benchmarks.
  arXiv  Detail & Related papers  (2024-06-25T04:27:53Z)
• Advancing Anomaly Detection: Non-Semantic Financial Data Encoding with LLMs [49.57641083688934]
  We introduce a novel approach to anomaly detection in financial data using Large Language Models (LLMs) embeddings. Our experiments demonstrate that LLMs contribute valuable information to anomaly detection as our models outperform the baselines.
  arXiv  Detail & Related papers  (2024-06-05T20:19:09Z)
• ReEval: Automatic Hallucination Evaluation for Retrieval-Augmented Large Language Models via Transferable Adversarial Attacks [91.55895047448249]
  This paper presents ReEval, an LLM-based framework using prompt chaining to perturb the original evidence for generating new test cases. We implement ReEval using ChatGPT and evaluate the resulting variants of two popular open-domain QA datasets. Our generated data is human-readable and useful to trigger hallucination in large language models.
  arXiv  Detail & Related papers  (2023-10-19T06:37:32Z)
• Check Your Facts and Try Again: Improving Large Language Models with External Knowledge and Automated Feedback [127.75419038610455]
  Large language models (LLMs) are able to generate human-like, fluent responses for many downstream tasks. This paper proposes a LLM-Augmenter system, which augments a black-box LLM with a set of plug-and-play modules.
  arXiv  Detail & Related papers  (2023-02-24T18:48:43Z)

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.