The paper investigates whether domain-specific fine‑tuning benefits open‑ended scientific reasoning in astronomy. Using a curated 300‑question QA benchmark from 2017–2026 Olympiad‑style materials, the authors compare open‑weight, API‑served general‑purpose, multimodal, and astronomy‑specialized language models. Results show that strong general‑purpose models set the highest correctness baseline, but variations in metric agreement, judge sensitivity, benchmark composition, and modality suggest that domain specialization is task‑ and deployment‑dependent and that domain‑specific evaluation is crucial for scientific workflows.
arXiv:2609.24246v1 Announce Type: new Abstract: Large language models (LLMs) have shown remarkable progress in natural language understanding, yet their effectiveness in specialized fields like astro...
arXiv:2604. 13201v2 Announce Type: replace-cross Abstract: Large language models are emerging as scientific assistants, but evaluating their ability to reason from empirical data remains challenging.
The paper introduces AstroVLBench, a benchmark of 4,100 expert‑verified instances covering optical imaging, radio interferometry, multi‑wavelength photometry, time‑domain light curves, and optical spectroscopy. Six leading vision‑language models were evaluated, revealing that performance varies strongly with modality and is not predicted by general benchmark rankings. Mechanistic ablations identified three bottlenecks: prompt grounding depends on model and task, presenting one‑dimensional data as tables rather than plots improves light‑curve classification, and a significant fraction of correct predictions are supported by physically inconsistent reasoning.
arXiv:2606. 13020v1 Announce Type: new Abstract: Three paradigmatic forms of inference recur across scientific reasoning: deduction, induction, and causal abduction.
arXiv:2609.16519v1 Announce Type: new Abstract: Scientific research increasingly relies on large, heterogeneous data sources, motivating interest in retrieval-augmented generation (RAG) systems that...
arXiv:2509. 21028v4 Announce Type: replace Abstract: We introduce SciTrek, a synthetic question-answering dataset for assessing and improving long-context numerical reasoning in large language models (LLMs).
The paper presents the first large‑scale benchmark for uncertainty quantification (UQ) calibration in long‑form scientific question answering, evaluating four UQ methods on 685,000 responses from up to 20 large language models across seven datasets. It shows that instruction tuning leads to token‑level probability polarization, undermining token‑level uncertainty signals, while reasoning model families differ in how they handle this effect. Only semantic consistency—consistency of the final answer—provides well‑calibrated outputs, demonstrating that semantic calibration remains robust in multi‑step, dependency‑rich reasoning.
Scientific research increasingly relies on large, heterogeneous data sources, motivating interest in retrieval-augmented generation (RAG) systems that provide natural language access to scientific kno...
The paper introduces Code Consistency Preference Optimization Verification (CCPO), a method that generates computationally sound solutions with dependency graphs to improve execution-consistent preference optimization for language models. By building a scientific reasoning dataset and extracting reasoning steps, prerequisites, and derivability relationships, the authors compute execution consistency scores that are used to fine‑tune models such as Llama‑3‑8B and DeepSeekMath‑7B, achieving significant performance gains on MATH (+17.0%) and GSM8K (+15.1%). The extended Scientific Feasibility Control framework further boosts accuracy on PhyX physics reasoning to 50.1%, surpassing existing models while maintaining high scientific validity and reducing law violations.
The paper introduces a pipeline that automatically creates ontology‑grounded multiple‑choice question benchmarks for evaluating large language models (LLMs) on logical reasoning tasks in scientific AI. By using OWL 2 ontologies, correct answers are guaranteed by design and distractors are generated and formally verified as incorrect through an OWL reasoner. Experiments on three ontologies—Pizza, PMDco, and DOID—yielded 112, 2,491, and 15,216 MCQs, respectively, with high natural‑language quality and challenging zero‑shot performance for six LLMs.
The paper introduces a benchmark of 250 expert-curated questions on inertial confinement fusion to evaluate language models on scientific fluency, physical reasoning, and quantitative analysis. It compares various closed‑source, open‑source, and a specialized model called Prospero, showing that Prospero improves by 10.7 percentage points and that frontier models still make critical physics errors. Retrieval assistance helps smaller models but not frontier ones, and two stress tests highlight the need for expert assessment of physical assumptions.
While Text-to-Image (T2I) models have shown remarkable success in generating photorealistic visual content, they still struggle with the rigorous semantic alignment and logical reasoning required for scientific imagery. Inspired by Peirce's Semiotic Triad, we introduce Scientific Image Reasoning (SciIR), a comprehensive resource for training and evaluation of scientific image generation.