FABLE: A Novel Data-Flow Analysis Benchmark on Procedural Text for Large Language Model Evaluation

• URL: http://arxiv.org/abs/2505.24258v1
• Date: Fri, 30 May 2025 06:32:34 GMT
• Title: FABLE: A Novel Data-Flow Analysis Benchmark on Procedural Text for Large Language Model Evaluation
• Authors: Vishal Pallagani, Nitin Gupta, John Aydin, Biplav Srivastava,
• Abstract summary: We introduce FABLE, a benchmark designed to assess large language models' understanding of data flow using structured, procedural text.<n>We evaluate three types of LLMs: a reasoning-focused model (DeepSeek-R1 8B), a general-purpose model (LLaMA 3.1 8B), and a code-specific model (Granite Code 8B)<n>Results show that the reasoning model achieves higher accuracy, but at the cost of over 20 times slower inference compared to the other models.
• Score: 5.866040886735852
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Understanding how data moves, transforms, and persists, known as data flow, is fundamental to reasoning in procedural tasks. Despite their fluency in natural and programming languages, large language models (LLMs), although increasingly being applied to decisions with procedural tasks, have not been systematically evaluated for their ability to perform data-flow reasoning. We introduce FABLE, an extensible benchmark designed to assess LLMs' understanding of data flow using structured, procedural text. FABLE adapts eight classical data-flow analyses from software engineering: reaching definitions, very busy expressions, available expressions, live variable analysis, interval analysis, type-state analysis, taint analysis, and concurrency analysis. These analyses are instantiated across three real-world domains: cooking recipes, travel routes, and automated plans. The benchmark includes 2,400 question-answer pairs, with 100 examples for each domain-analysis combination. We evaluate three types of LLMs: a reasoning-focused model (DeepSeek-R1 8B), a general-purpose model (LLaMA 3.1 8B), and a code-specific model (Granite Code 8B). Each model is tested using majority voting over five sampled completions per prompt. Results show that the reasoning model achieves higher accuracy, but at the cost of over 20 times slower inference compared to the other models. In contrast, the general-purpose and code-specific models perform close to random chance. FABLE provides the first diagnostic benchmark to systematically evaluate data-flow reasoning and offers insights for developing models with stronger procedural understanding.

Related papers

• 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.<n>LLMs promise to democratize data science by enabling those with limited programming expertise to conduct data analyses.<n>Analysts in many real-world settings must often exercise fine-grained control over specific analysis steps.<n>This paper introduces Flowco, a new mixed-initiative system to address these challenges.
  arXiv  Detail & Related papers  (2025-04-18T19:01:27Z)
• AutoLogi: Automated Generation of Logic Puzzles for Evaluating Reasoning Abilities of Large Language Models [86.83875864328984]
  We propose an automated method for synthesizing open-ended logic puzzles, and use it to develop a bilingual benchmark, AutoLogi.<n>Our approach features program-based verification and controllable difficulty levels, enabling more reliable evaluation that better distinguishes models' reasoning abilities.
  arXiv  Detail & Related papers  (2025-02-24T07:02:31Z)
• AIRepr: An Analyst-Inspector Framework for Evaluating Reproducibility of LLMs in Data Science [5.064778712920176]
  Large language models (LLMs) are increasingly used to automate data analysis through executable code generation.<n>We present $itAIRepr, an $itA$nalyst - $itI$nspector framework for automatically evaluating and improving the $itRepr$oducibility of LLM-generated data analysis.
  arXiv  Detail & Related papers  (2025-02-23T01:15:50Z)
• Self-supervised Analogical Learning using Language Models [59.64260218737556]
  We propose SAL, a self-supervised analogical learning framework.<n> SAL mimics the human analogy process and trains models to explicitly transfer high-quality symbolic solutions.<n>We show that the resulting models outperform base language models on a wide range of reasoning benchmarks.
  arXiv  Detail & Related papers  (2025-02-03T02:31:26Z)
• CoddLLM: Empowering Large Language Models for Data Analytics [38.23203246023766]
  Large Language Models (LLMs) have the potential to revolutionize data analytics.<n>We unveil a new data recipe for post-Turbo synthesiss.<n>We posttrain a new foundation model, named CoddLLM, based on MistralNeMo-12B.
  arXiv  Detail & Related papers  (2025-02-01T06:03:55Z)
• ProcessBench: Identifying Process Errors in Mathematical Reasoning [62.80402845414901]
  We introduce ProcessBench for measuring the ability to identify erroneous steps in mathematical reasoning.<n>ProcessBench consists of 3,400 test cases, primarily focused on competition- and Olympiad-level math problems.<n>We conduct extensive evaluation on ProcessBench, involving two types of models: process reward models (PRMs) and critic models.
  arXiv  Detail & Related papers  (2024-12-09T15:11:40Z)
• 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)
• UQE: A Query Engine for Unstructured Databases [71.49289088592842]
  We investigate the potential of Large Language Models to enable unstructured data analytics. We propose a new Universal Query Engine (UQE) that directly interrogates and draws insights from unstructured data collections.
  arXiv  Detail & Related papers  (2024-06-23T06:58:55Z)
• LLMDFA: Analyzing Dataflow in Code with Large Language Models [8.92611389987991]
  This paper presents LLMDFA, a compilation-free and customizable dataflow analysis framework. We decompose the problem into several subtasks and introduce a series of novel strategies. On average, LLMDFA achieves 87.10% precision and 80.77% recall, surpassing existing techniques with F1 score improvements of up to 0.35.
  arXiv  Detail & Related papers  (2024-02-16T15:21:35Z)
• Text2Analysis: A Benchmark of Table Question Answering with Advanced Data Analysis and Unclear Queries [67.0083902913112]
  We develop the Text2Analysis benchmark, incorporating advanced analysis tasks. We also develop five innovative and effective annotation methods. We evaluate five state-of-the-art models using three different metrics.
  arXiv  Detail & Related papers  (2023-12-21T08:50:41Z)
• Assessing and Enhancing the Robustness of Large Language Models with Task Structure Variations for Logical Reasoning [25.496627355906966]
  We develop three new logical reasoning datasets named "ReClor-plus", "LogiQA-plus" and "LogiQAv2-plus"<n>Experiments show that these simple augmentations greatly hinder the models' performance.<n>Applying logic-driven data augmentation for fine-tuning and prompting can enhance generalisation in both discriminative and generative models.
  arXiv  Detail & Related papers  (2023-10-13T22:29:15Z)

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.