Cover Image

AstroMLab 4: Benchmark-Topping Performance in Astronomy Q&A with a 70B-Parameter Domain-Specialized Reasoning Model

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	de Haan, Tijmen, Ting, Yuan-Sen, Ghosal, Tirthankar, Nguyen, Tuan Dung, Accomazzi, Alberto, Herron, Emily, Lama, Vanessa, Pan, Rui, Wells, Azton, Ramachandra, Nesar
Format:	Preprint
Published:	2025
Subjects:	Instrumentation and Methods for Astrophysics Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

AstroMLab 1: Who Wins Astronomy Jeopardy!?
by: Ting, Yuan-Sen, et al.
Published: (2024)

AstroMLab 3: Achieving GPT-4o Level Performance in Astronomy with a Specialized 8B-Parameter Large Language Model
by: de Haan, Tijmen, et al.
Published: (2024)

AstroMLab 2: AstroLLaMA-2-70B Model and Benchmarking Specialised LLMs for Astronomy
by: Pan, Rui, et al.
Published: (2024)

AstroMLab 5: Structured Summaries and Concept Extraction for 400,000 Astrophysics Papers
by: Ting, Yuan-Sen, et al.
Published: (2025)

Predicting New Concept-Object Associations in Astronomy by Mining the Literature
by: Li, Jinchu, et al.
Published: (2026)

Teaching LLMs to Speak Spectroscopy
by: Ramachandra, Nesar, et al.
Published: (2025)

Multi-modal Foundation Model for Cosmological Simulation Data
by: Xia, Bin, et al.
Published: (2025)

Johnson Noise Suppression in AC-Biased Transition-Edge Sensor Bolometers: A Thévenin-Equivalent Circuit Analysis
by: de Haan, Tijmen
Published: (2025)

cosmosage: A Natural-Language Assistant for Cosmologists
by: de Haan, Tijmen
Published: (2024)

The Compressive Knowledge Graph Hypothesis: Which Graph Facts Matter for Scientific Hypothesis Generation?
by: Sourav, Shashwat, et al.
Published: (2026)

Development of SQUID Array Amplifiers for the LiteBIRD CMB Satellite
by: Boyd, S. T. P., et al.
Published: (2025)

MNTES: Modeling Nonlinearity of TES detectors for Enhanced Cosmic Microwave Background measurements with LiteBIRD
by: de Haan, Tijmen, et al.
Published: (2024)

Benchmarking AI-evolved cosmological structure formation
by: Dong, Xiaofeng, et al.
Published: (2025)

Enhancing Interpretability in Generative Modeling: Statistically Disentangled Latent Spaces Guided by Generative Factors in Scientific Datasets
by: Ganguli, Arkaprabha, et al.
Published: (2025)

AstroPT: Scaling Large Observation Models for Astronomy
by: Smith, Michael J., et al.
Published: (2024)

Reducing Model Error Using Optimised Galaxy Selection: Weak Lensing Cluster Mass Estimation
by: Rau, Markus Michael, et al.
Published: (2024)

Astro-COLIBRI: Empowering Citizen Scientists in Time Domain Astronomy
by: Schüssler, Fabian, et al.
Published: (2024)

OntoPortal-Astro, a Semantic Artefact Catalogue for Astronomy
by: Cecconi, Baptiste, et al.
Published: (2025)

AstroLLaMA-Chat: Scaling AstroLLaMA with Conversational and Diverse Datasets
by: Perkowski, Ernest, et al.
Published: (2024)

Decades of Transformation: Evolution of the NASA Astrophysics Data System's Infrastructure
by: Accomazzi, Alberto
Published: (2024)

ORCHID: Orchestrated Retrieval-Augmented Classification with Human-in-the-Loop Intelligent Decision-Making for High-Risk Property
by: Mahbub, Maria, et al.
Published: (2025)

AstroVisBench: A Code Benchmark for Scientific Computing and Visualization in Astronomy
by: Joseph, Sebastian Antony, et al.
Published: (2025)

AstroConcepts: A Large-Scale Multi-Label Classification Corpus for Astrophysics
by: Alkan, Atilla Kaan, et al.
Published: (2026)

Can Large Language Models Unlock Novel Scientific Research Ideas?
by: Kumar, Sandeep, et al.
Published: (2024)

AstroSpy: On detecting Fake Images in Astronomy via Joint Image-Spectral Representations
by: Alam, Mohammed Talha, et al.
Published: (2024)

AstroMMBench: A Benchmark for Evaluating Multimodal Large Language Models Capabilities in Astronomy
by: Shi, Jinghang, et al.
Published: (2025)

pathfinder: A Semantic Framework for Literature Review and Knowledge Discovery in Astronomy
by: Iyer, Kartheik G., et al.
Published: (2024)

Astro-NER -- Astronomy Named Entity Recognition: Is GPT a Good Domain Expert Annotator?
by: Evans, Julia, et al.
Published: (2024)

AstroRAG -- A Pagerank-Based Retrieval-Augmented Generation Pipeline for Question Answering in Astronomy
by: Wang, Zhifeng, et al.
Published: (2026)

Galaxies and Their Environment at $z \gtrsim 10$ -- I: Primordial Chemical Enrichment, Accretion, Cooling, and Virialization of Gas in Dark Matter Halos
by: Hicks, William M., et al.
Published: (2024)

The Smithsonian/NASA Astrophysics Data System Status Report
by: Accomazzi, Alberto, et al.
Published: (2010)

Intelligent Manufacturing Support: Specialized LLMs for Composite Material Processing and Equipment Operation
by: Kapoor, Gunnika, et al.
Published: (2025)

AstroQ: Automated Scheduling of Cadenced Astronomical Observations
by: Lubin, Jack
Published: (2025)

AstroQ: Automated Scheduling of Cadenced Astronomical Observations
by: Lubin, Jack, et al.
Published: (2025)

Statistical Machine Learning for Astronomy -- A Textbook
by: Ting, Yuan-Sen
Published: (2025)

BLUEPRINT Rebuilding a Legacy: Multimodal Retrieval for Complex Engineering Drawings and Documents
by: Seefried, Ethan, et al.
Published: (2026)

'Quis custodiet ipsos custodes?' Who will watch the watchmen? On Detecting AI-generated peer-reviews
by: Kumar, Sandeep, et al.
Published: (2024)

A Systematic Review of Key Retrieval-Augmented Generation (RAG) Systems: Progress, Gaps, and Future Directions
by: Oche, Agada Joseph, et al.
Published: (2025)

Findings of the Third Automatic Minuting (AutoMin) Challenge
by: Shinde, Kartik, et al.
Published: (2025)

Uncovering Physical Drivers of Dark Matter Halo Structures with Auxiliary-Variable-Guided Generative Models
by: Ganguli, Arkaprabha, et al.
Published: (2026)