AstroSpecLM: A Spectrum-Language Model for Evidence-Grounded Astronomical Spectral Analysis

• URL: http://arxiv.org/abs/2609.07102v1
• Date: Mon, 07 Sep 2026 06:44:01 GMT
• Title: AstroSpecLM: A Spectrum-Language Model for Evidence-Grounded Astronomical Spectral Analysis
• Abstract summary: This paper presents AstroSpecLM, a spectrum-language model that connects one-dimensional DESI spectra with Qwen3-4B to answer questions.<n>We first distill each spectrum into a compact set of catalog- and spectrum-derived facts, then use these facts as references to generate instruction-following conversations.<n>Our results indicate that grounding a language model in one-dimensional scientific spectra is feasible, and that fact-mediated instruction data yields a model capable of both prediction and explanation.
• Score: 2.6513685737789463
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Astronomical spectra encode rich physical information, but drawing scientific conclusions from spectral features typically requires expert interpretation. This paper presents AstroSpecLM, a spectrum-language model that connects one-dimensional DESI spectra with Qwen3-4B to answer questions and provide explanations grounded in spectral evidence. Instead of generating question-answer pairs directly from templates or raw catalog fields, we first distill each spectrum into a compact set of catalog- and spectrum-derived facts, then use these facts as references to generate instruction-following conversations. The resulting model is competitive with specialist supervised baselines on classification and redshift estimation, while additionally producing natural-language explanations that reference specific spectral features. Our results indicate that grounding a language model in one-dimensional scientific spectra is feasible, and that fact-mediated instruction data yields a model capable of both prediction and explanation.

Related papers

• Spectral Model eXplainer: a chemically-grounded explainability framework for spectral-based machine learning models [0.6487259764989486]
  This study introduces the Spectral Model eXplainer (SMX), a post-hoc, global, model-agnostic XAI framework that explains spectral classifiers through expert-informed spectral zones.<n>SMX summarizes each zone via PCA, defines quantile-based logical predicates, estimates relevance with perturbations, and aggregates bag-wise rankings in a directed weighted graph.
  arXiv  Detail & Related papers  (2026-05-04T15:01:04Z)
• Universal Spectral Tokenization via Self-Supervised Panchromatic Representation Learning [39.14992490784682]
  Sequential scientific data span many resolutions and domains, and unifying them into a common representation is a key step toward developing foundation models for the sciences.<n>We present a deep learning model that jointly learns from heterogeneous spectra in a self-supervised manner.<n>For the first time, we demonstrate that a single model can unify spectral data across resolutions and domains.
  arXiv  Detail & Related papers  (2025-10-20T18:00:00Z)
• DiffSpectra: Molecular Structure Elucidation from Spectra using Diffusion Models [68.19129717255053]
  We present DiffSpectra, a generative framework that formulates molecular structure elucidation as a conditional generation process.<n>Our experiments demonstrate that DiffSpectra accurately elucidates molecular structures, achieving 40.76% top-1 and 99.49% top-10 accuracy.
  arXiv  Detail & Related papers  (2025-07-09T13:57:20Z)
• SpecCLIP: Aligning and Translating Spectroscopic Measurements for Stars [6.314253302704276]
  We present SpecCLIP, a foundation model framework that extends LLM-inspired methodologies to stellar spectral analysis.<n>By training foundation models on large-scale spectral datasets, our goal is to learn robust and informative embeddings that support diverse downstream applications.<n>We demonstrate that fine-tuning these models on moderate-sized labeled datasets improves adaptability to tasks such as stellar- parameter estimation and chemical-abundance determination.
  arXiv  Detail & Related papers  (2025-07-02T17:49:52Z)
• CARL: Camera-Agnostic Representation Learning for Spectral Image Analysis [69.02751635551724]
  Spectral imaging offers promising applications across diverse domains, including medicine and urban scene understanding.<n> variability in channel dimensionality and captured wavelengths among spectral cameras impede the development of AI-driven methodologies.<n>We introduce CARL, a model for Camera-Agnostic Representation Learning across RGB, multispectral, and hyperspectral imaging modalities.
  arXiv  Detail & Related papers  (2025-04-27T13:06:40Z)
• SpecReX: Explainable AI for Raman Spectroscopy [4.541069830146568]
  We introduce SpecReX, specifically adapted to explaining Raman spectra.<n>SpecReX uses the theory of actual causality to rank causal responsibility in a spectrum.<n>We establish that SpecReX localizes to the known differences between classes.
  arXiv  Detail & Related papers  (2025-03-18T10:49:15Z)
• SpectralNeRF: Physically Based Spectral Rendering with Neural Radiance Field [70.15900280156262]
  We propose an end-to-end Neural Radiance Field (NeRF)-based architecture for high-quality physically based rendering from a novel spectral perspective. SpectralNeRF is superior to recent NeRF-based methods when synthesizing new views on synthetic and real datasets.
  arXiv  Detail & Related papers  (2023-12-14T07:19:31Z)
• Specformer: Spectral Graph Neural Networks Meet Transformers [51.644312964537356]
  Spectral graph neural networks (GNNs) learn graph representations via spectral-domain graph convolutions. We introduce Specformer, which effectively encodes the set of all eigenvalues and performs self-attention in the spectral domain. By stacking multiple Specformer layers, one can build a powerful spectral GNN.
  arXiv  Detail & Related papers  (2023-03-02T07:36:23Z)
• Unsupervised Spectral Unmixing For Telluric Correction Using A Neural Network Autoencoder [58.720142291102135]
  We present a neural network autoencoder approach for extracting a telluric transmission spectrum from a large set of high-precision observed solar spectra from the HARPS-N radial velocity spectrograph.
  arXiv  Detail & Related papers  (2021-11-17T12:54:48Z)
• Spectra of Perfect State Transfer Hamiltonians on Fractal-Like Graphs [62.997667081978825]
  We study the spectral features, on fractal-like graphs, of Hamiltonians which exhibit the special property of perfect quantum state transfer. The essential goal is to develop the theoretical framework for understanding the interplay between perfect quantum state transfer, spectral properties, and the geometry of the underlying graph.
  arXiv  Detail & Related papers  (2020-03-25T02:46:14Z)
• Persistent spectral based machine learning (PerSpect ML) for drug design [0.0]
  We propose persistent spectral based machine learning (PerSpect ML) models for drug design. We consider 11 persistent spectral variables and use them as the feature for machine learning models in protein-ligand binding affinity prediction. Our results, for all these databases, are better than all existing models, as far as we know.
  arXiv  Detail & Related papers  (2020-02-03T07:14:21Z)

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.