SPARK: Skeleton-Guided Reasoning Synthesis from Large-Scale Scientific Literature

• URL: http://arxiv.org/abs/2608.30214v1
• Date: Mon, 31 Aug 2026 03:55:30 GMT
• Title: SPARK: Skeleton-Guided Reasoning Synthesis from Large-Scale Scientific Literature
• Abstract summary: We introduce SPARK, a paper-oriented synthesis framework built on Sci-Base.<n> SPARK distills each paper into a compact reasoning skeleton capturing its central claims and supporting evidence.<n>We construct Spark-234K, a scientific reasoning dataset with substantially higher difficulty and diversity than existing resources.
• Score: 26.176405135367038
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Scientific reasoning remains challenging for open-source models, largely due to the lack of high-quality scientific reasoning data. Existing datasets are often dominated by factual recall or formulaic problem solving, with limited emphasis on mechanism understanding, evidence-grounded reasoning, and hypothesis evaluation. To address this, we introduce SPARK (Scientific Paper Abstracted Reasoning sKeleton), a paper-oriented synthesis framework built on Sci-Base, a large-scale corpus of research papers spanning 10 scientific disciplines. Instead of directly converting papers into question-answer pairs, SPARK treats the claim-evidence-derivation structure of a paper as the fundamental unit of reasoning synthesis. Specifically, SPARK (1) distills each paper into a compact reasoning skeleton capturing its central claims and supporting evidence, enabling self-contained question generation, and (2) synthesizes reasoning tasks from four scientific perspectives: mechanistic reasoning, hypothesis falsification, quantitative derivation, and boundary calibration. A final consistency verification stage further removes unsupported or contradictory outputs. Using this framework, we construct Spark-234K, a scientific reasoning dataset with substantially higher difficulty and diversity than existing resources. Experiments show that Spark-234K consistently outperforms existing scientific reasoning datasets while achieving stronger performance with significantly fewer training samples.

Related papers

• Replications, Revisions, and Reanalyses: Managing Empirical Evidence in Software Engineering [6.147136878250444]
  validity of variance theories stems from the synthesis of multiple pieces of evidence.<n>Research synthesis in SE is rare and if done mostly limited to purely narrative syntheses.<n>We apply method engineering to construct a framework for research synthesis from proven, individual method fragments.
  arXiv  Detail & Related papers  (2026-09-05T08:57:53Z)
• Accurate, Interdisciplinary and Transparent Structure-property Understanding with Deep Native Structural Reasoning [103.788281428856]
  We introduce SciReasoner, a scientific foundation model for native structural reasoning across proteins, small molecules and inorganic crystals.<n>SciReasoner discretizes coordinates, topologies and periodic connectivities into a unified structure-aware vocabulary.<n>Across 86 benchmarks, SciReasoner achieves state-of-the-art performance on 67 tasks.
  arXiv  Detail & Related papers  (2026-07-08T17:59:59Z)
• SciR: A Controllable Benchmark for Scientific Reasoning in LLMs [14.183744057358547]
  SciR is a benchmark that combines multi-paradigm reasoning with controllable scientific rendering.<n>To our knowledge, SciR is the first multi-paradigm scientific-reasoning benchmark with parametric control on both extraction and inference difficulty.
  arXiv  Detail & Related papers  (2026-06-11T07:54:22Z)
• PaperMind: Benchmarking Agentic Reasoning and Critique over Scientific Papers in Multimodal LLMs [68.27437550335709]
  We introduce PaperMind, a benchmark designed to evaluate integrated and agent-oriented scientific reasoning over research papers.<n>PaperMind is constructed from real scientific papers across seven domains, including agriculture, biology, chemistry, computer science, medicine, physics, and economics.<n>By analyzing model behavior across multiple tasks, PaperMind enables a diagnostic evaluation of integrated scientific reasoning behaviors.
  arXiv  Detail & Related papers  (2026-04-23T05:42:39Z)
• CoT-Evo: Evolutionary Distillation of Chain-of-Thought for Scientific Reasoning [63.44477226386808]
  Chain-of-thought (CoT) distillation from advanced large language models (LLMs) has proven effective in general reasoning tasks.<n>But it struggles in scientific domains where even advanced models often produce incorrect or superficial reasoning.<n>We propose CoT-Evo, an evolutionary CoT distillation framework to overcome this problem.
  arXiv  Detail & Related papers  (2025-10-15T05:29:56Z)
• Demystifying Scientific Problem-Solving in LLMs by Probing Knowledge and Reasoning [53.82037883518254]
  We introduce SciReas, a diverse suite of existing benchmarks for scientific reasoning tasks.<n>We then propose KRUX, a probing framework for studying the distinct roles of reasoning and knowledge in scientific tasks.
  arXiv  Detail & Related papers  (2025-08-26T17:04:23Z)
• The Next Phase of Scientific Fact-Checking: Advanced Evidence Retrieval from Complex Structured Academic Papers [11.88478056313921]
  The problem is inherently more complex than general fact-checking since it must accommodate the evolving nature of scientific knowledge.<n>Existing approaches focus on simplified versions of the problem based on small-scale datasets consisting of abstracts.<n>This paper examines the limitations of current scientific fact-checking systems and reveals the potential features and resources that could be exploited to advance their performance.
  arXiv  Detail & Related papers  (2025-06-25T21:29:33Z)
• Atomic Reasoning for Scientific Table Claim Verification [83.14588611859826]
  Non-experts are susceptible to misleading claims based on scientific tables due to their high information density and perceived credibility.<n>Existing table claim verification models, including state-of-the-art large language models (LLMs), often struggle with precise fine-grained reasoning.<n>Inspired by Cognitive Load Theory, we propose that enhancing a model's ability to interpret table-based claims involves reducing cognitive load.
  arXiv  Detail & Related papers  (2025-06-08T02:46:22Z)
• Context-Aware Reasoning On Parametric Knowledge for Inferring Causal Variables [49.31233968546582]
  We introduce a novel benchmark where the objective is to complete a partial causal graph.<n>We show the strong ability of LLMs to hypothesize the backdoor variables between a cause and its effect.<n>Unlike simple memorization of fixed associations, our task requires the LLM to reason according to the context of the entire graph.
  arXiv  Detail & Related papers  (2024-09-04T10:37:44Z)

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.