Pith. sign in

REVIEW 4 cited by

DARWIN Series: Domain Specific Large Language Models for Natural Science

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2308.13565 v1 pith:EX7UBVBX submitted 2023-08-25 cs.CL cond-mat.mtrl-sciphysics.app-ph

classification cs.CLcond-mat.mtrl-sciphysics.app-ph
keywords sciencescientificnaturalseriesdarwininstructionknowledgemodels
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Emerging tools bring forth fresh approaches to work, and the field of natural science is no different. In natural science, traditional manual, serial, and labour-intensive work is being augmented by automated, parallel, and iterative processes driven by artificial intelligence-based experimental automation and more. To add new capabilities in natural science, enabling the acceleration and enrichment of automation of the discovery process, we present DARWIN, a series of tailored LLMs for natural science, mainly in physics, chemistry, and material science. This series relies on open-source LLM, incorporating structured and unstructured scientific knowledge from public datasets and literature. We fine-tuned the models using over 60,000 instruction data points, emphasizing factual correctness. During the fine-tuning, we introduce the Scientific Instruction Generation (SIG) model, automating instruction generation from scientific texts. This eliminates the need for manual extraction or domain-specific knowledge graphs and efficiently injects scientific knowledge into the model. We also explore multi-task training strategies, revealing interconnections between scientific tasks. DARWIN series not only achieves state-of-the-art results on various scientific tasks but also diminishes reliance on closed-source AI models. Our research showcases the ability of LLM in the scientific domain, with the overarching goal of fostering prosperity within the broader AI for science community.

Discussion (0). Sign in to comment.

Forward citations

Cited by 4 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. OpenAlex reports about 33 citations worldwide. Full citation record

  1. Can Multimodal LLMs See Materials Clearly? A Multimodal Benchmark on Materials Characterization

    cs.CV 2025-09 conditional novelty 6.0 of 10

    A new 1,500-question benchmark shows multimodal LLMs score about 26 to 31 points below human experts on understanding materials characterization images.

  2. Toward Scientific Reasoning in LLMs: Training from Expert Discussions via Reinforcement Learning

    cs.AI 2025-05 conditional novelty 6.0 of 10

    Reinforcement learning on questions extracted from CRISPR expert forums improves LLM accuracy on a new benchmark (Genome-Bench) by over 15 percentage points.

  3. From Text to Discovery: How Large Language Models Are Reshaping Research Across Scientific and Humanistic Disciplines

    cs.DL 2026-06 unverdicted novelty 3.0 of 10

    LLMs accelerate research workflows from idea generation to writing but introduce challenges like hallucination, bias, opacity, and ten systemic risks requiring new governance frameworks.

  4. Research on Personalized Financial Product Recommendation by Integrating Large Language Models and Graph Neural Networks

    cs.IR 2025-06 reject novelty 2.0 of 10

    A hybrid LLM-plus-GNN recommender is claimed to beat collaborative filtering, LLM-only, and GNN-only baselines on financial product ranking, with NDCG@10 of 0.372.

Pith tools