InfoSynth: Information-Guided Benchmark Synthesis for LLMs

• URL: http://arxiv.org/abs/2601.00575v1
• Date: Fri, 02 Jan 2026 05:26:27 GMT
• Title: InfoSynth: Information-Guided Benchmark Synthesis for LLMs
• Authors: Ishir Garg, Neel Kolhe, Xuandong Zhao, Dawn Song,
• Abstract summary: Large language models (LLMs) have demonstrated significant advancements in reasoning and code generation.<n>Traditional benchmark creation relies on manual human effort, a process that is both expensive and time-consuming.<n>This work introduces Info Synth, a novel framework for automatically generating and evaluating reasoning benchmarks.
• Score: 69.80981631587501
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Large language models (LLMs) have demonstrated significant advancements in reasoning and code generation. However, efficiently creating new benchmarks to evaluate these capabilities remains a challenge. Traditional benchmark creation relies on manual human effort, a process that is both expensive and time-consuming. Furthermore, existing benchmarks often contaminate LLM training data, necessitating novel and diverse benchmarks to accurately assess their genuine capabilities. This work introduces InfoSynth, a novel framework for automatically generating and evaluating reasoning benchmarks guided by information-theoretic principles. We propose metrics based on KL-divergence and entropy to quantify benchmark novelty and diversity without relying on costly model evaluations. Building on this framework, we develop an end-to-end pipeline that synthesizes robust Python coding problems from seed datasets using genetic algorithms and iterative code feedback. Our method generates accurate test cases and solutions to new problems 97% of the time, and the synthesized benchmarks consistently exhibit higher novelty and diversity compared to their seed datasets. Moreover, our algorithm provides a method for controlling the novelty/diversity and difficulty of generated problems. InfoSynth offers a scalable, self-verifying pipeline for constructing high-quality, novel and diverse benchmarks for LLMs. Project Page: https://ishirgarg.github.io/infosynth_web/

Related papers

• CoT-Self-Instruct: Building high-quality synthetic prompts for reasoning and non-reasoning tasks [59.69339605157168]
  CoT-Self-Instruct is a synthetic data generation method that instructs LLMs to first reason and plan via Chain-of-Thought.<n>In verifiable reasoning, our synthetic data significantly outperforms existing training datasets.<n>For non-verifiable instruction-following tasks, our method surpasses the performance of both human and standard Self-Instruct training data.
  arXiv  Detail & Related papers  (2025-07-31T17:38:50Z)
• OIBench: Benchmarking Strong Reasoning Models with Olympiad in Informatics [13.049841309304922]
  This paper introduces OIBench, a high-quality, private, and challenging olympiad-level informatics dataset comprising 250 carefully curated original problems.<n>We detail the construction methodology of the benchmark, ensuring a comprehensive assessment across various programming paradigms and complexities.<n>We propose Time/Space Completion Curves for finer-grained efficiency analysis and enable direct human-model comparisons.
  arXiv  Detail & Related papers  (2025-06-12T08:33:38Z)
• Grounding Synthetic Data Evaluations of Language Models in Unsupervised Document Corpora [9.871701356351542]
  Language Models (LMs) continue to advance, improving response quality and coherence.<n>A plethora of evaluation benchmarks have been constructed to assess model quality, response appropriateness, and reasoning capabilities.<n>We propose a methodology for automating the construction of fact-based synthetic data model evaluations grounded in document populations.
  arXiv  Detail & Related papers  (2025-05-13T18:50:03Z)
• Scaling Laws of Synthetic Data for Language Models [125.41600201811417]
  We introduce SynthLLM, a scalable framework that transforms pre-training corpora into diverse, high-quality synthetic datasets.<n>Our approach achieves this by automatically extracting and recombining high-level concepts across multiple documents using a graph algorithm.
  arXiv  Detail & Related papers  (2025-03-25T11:07:12Z)
• UnitCoder: Scalable Iterative Code Synthesis with Unit Test Guidance [65.01483640267885]
  Large Language Models (LLMs) have demonstrated remarkable capabilities in various tasks, yet code generation remains a major challenge.<n>We introduce UnitCoder, a systematic pipeline leveraging model-generated unit tests to guide and validate the code generation process.<n>Our work presents a scalable approach that leverages model-generated unit tests to guide the synthesis of high-quality code data from pre-training corpora.
  arXiv  Detail & Related papers  (2025-02-17T05:37:02Z)
• SnipGen: A Mining Repository Framework for Evaluating LLMs for Code [51.07471575337676]
  Language Models (LLMs) are trained on extensive datasets that include code repositories.<n> evaluating their effectiveness poses significant challenges due to the potential overlap between the datasets used for training and those employed for evaluation.<n>We introduce SnipGen, a comprehensive repository mining framework designed to leverage prompt engineering across various downstream tasks for code generation.
  arXiv  Detail & Related papers  (2025-02-10T21:28:15Z)
• BenchAgents: Multi-Agent Systems for Structured Benchmark Creation [23.653678381444276]
  BenchAgents is a framework that automates the creation of evaluation benchmarks.<n>We use BenchAgents to create benchmarks to evaluate capabilities related to planning, constraint satisfaction, and causal reasoning.<n>We then use these benchmarks to study state-of-the-art models and extract new insights into common failure modes and model differences.
  arXiv  Detail & Related papers  (2024-10-29T22:56:18Z)
• Skip the Benchmark: Generating System-Level High-Level Synthesis Data using Generative Machine Learning [8.416553728391309]
  High-Level Synthesis (HLS) Design Space Exploration (DSE) is a widely accepted approach for exploring optimal hardware solutions during the HLS process. Several HLS benchmarks and datasets are available for the research community to evaluate their methodologies. This paper proposes a novel approach, called Vaegan, that employs generative machine learning to generate synthetic data that is robust enough to support complex system-level HLS DSE experiments.
  arXiv  Detail & Related papers  (2024-04-23T05:32:22Z)
• TSGM: A Flexible Framework for Generative Modeling of Synthetic Time Series [61.436361263605114]
  Time series data are often scarce or highly sensitive, which precludes the sharing of data between researchers and industrial organizations. We introduce Time Series Generative Modeling (TSGM), an open-source framework for the generative modeling of synthetic time series.
  arXiv  Detail & Related papers  (2023-05-19T10:11:21Z)
• PDEBENCH: An Extensive Benchmark for Scientific Machine Learning [20.036987098901644]
  We introduce PDEBench, a benchmark suite of time-dependent simulation tasks based on Partial Differential Equations (PDEs) PDEBench comprises both code and data to benchmark the performance of novel machine learning models against both classical numerical simulations and machine learning baselines.
  arXiv  Detail & Related papers  (2022-10-13T17:03:36Z)
• Synthetic Benchmarks for Scientific Research in Explainable Machine Learning [14.172740234933215]
  We release XAI-Bench: a suite of synthetic datasets and a library for benchmarking feature attribution algorithms. Unlike real-world datasets, synthetic datasets allow the efficient computation of conditional expected values. We demonstrate the power of our library by benchmarking popular explainability techniques across several evaluation metrics and identifying failure modes for popular explainers.
  arXiv  Detail & Related papers  (2021-06-23T17:10:21Z)

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.