Metraipolis › archive › dc_be27104f810a

Quantifying out-of-distribution data severity with Wasserstein distances: benchmarking large language models for alloy property prediction — arXiv:2611.03767

Source: arXiv (en)
Original: https://arxiv.org/abs/2611.03767
License (as archived): CC0-1.0
Archived: 2026-11-04T12:39:19.904Z
SHA-256 of the archived text: 7e87ee960d6ff825e15f67d3a41c7285e759f536f7d8dff4432077333db1dd0a
Stable URL of this page: https://metraipolis.com/documento/dc_be27104f810a

How to cite

Quantifying out-of-distribution data severity with Wasserstein distances: benchmarking large language models for alloy property prediction — arXiv:2611.03767 — arXiv (en), https://arxiv.org/abs/2611.03767 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_be27104f810a (Metraipolis archive dc_be27104f810a, sha256 7e87ee960d6ff825e15f67d3a41c7285e759f536f7d8dff4432077333db1dd0a)

BibTeX

@misc{dcbe27104f810a,
  title = {Quantifying out-of-distribution data severity with Wasserstein distances: benchmarking large language models for alloy property prediction — arXiv:2611.03767},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.03767},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_be27104f810a; sha256 7e87ee960d6ff825e15f67d3a41c7285e759f536f7d8dff4432077333db1dd0a},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.03767. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

As general-purpose Large Language Models (LLMs), such as Gemini and DeepSeek, exhibit increasingly advanced reasoning capabilities, a critical question arises: how do their property prediction abilities compare to those of domain-specific pretrained materials models? In this study, we evaluate predictions for Ti, steels, high-entropy alloy (HEA) and Al, demonstrating that general-purpose LLMs surprisingly outperform SteelBERT, MatSciBERT, and SciBERT. To further enhance performance, we introduce a hybrid approach that utilizes numerical priors from a prior model, such as CatBoost or SteelBERT, to guide the general LLMs (Deepseek V3.1, Gemini-2.5-Flash). By inputting these initial estimates from a prior model as prompts, the LLM acts as a reasoning corrector, achieving accuracy superior to the prior model and "unguided mode". Furthermore, we investigate the impact of data strategy using a similarity-based metric, revealing that data quality dominates quantity; using merely 5% of high-similarity reference data of training set as input yields performance similar to the results of using 100% of training set. Additionally, the LLMs demonstrate excellent uncertainty calibration, where self-reported "high" confidence strongly correlates with minimal deviation from ground truth. Our findings suggest that synergizing general-purpose LLMs with prior model numerical baselines and high-quality data curation creates a cost-effective and accurate paradigm for materials discovery, reducing the need for expensive domain-specific pretraining.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (cs.LG) ; Materials Science (cond-mat.mtrl-sci).
Pagina del lavoro: https://arxiv.org/abs/2611.03767 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-11-04T12:29:47.246Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).