arXiv subjects

Mikhail L. Zheludkevich

Publications and source records attributed to Mikhail L. Zheludkevich.

4 recordsLinked to original sources

arXiv2026

Do LLMs Know When They Are Wrong About Molecules? In-Context Property Prediction with Self-Reported Uncertainty

Large language models (LLMs) are used in many domains, but molecular property prediction with them is still little explored. In this work we evaluate the capability of 7 frontier LLMs to predict molecular properties together with a self-reported uncertainty from in-context examples, and compare them with classical baselines trained on the same molecules. We use 4 datasets and screen each for contamination of the training data of the LLMs: three are clean, and the fourth, ESOL, is memorised by most of the models and serves as a comparison. On the clean datasets every LLM improves with the context, at 30 examples the most accurate one beats every baseline. The requested reasoning effort changes accuracy little. The self-reported uncertainty ranks the prediction errors weakly, with Spearman rank correlations of up to 0.46, about the level reached by the uncertainties of the baselines. Combining uncertainty and prediction, on lipophilicity the most certain half of the best LLM is the most accurate at small context sizes; on BACE and antiviral, and on lipophilicity at large context sizes, the best LLMs are on par with the best baseline. On the contaminated ESOL dataset the LLMs show no improvement with the context size, as expected for a memorised dataset, and their stated uncertainty is smaller on the molecules whose value they recall.

cs.LG↗

arXiv2026

Molecular Déjà Vu: Digit-Level Retrieval of Molecular Properties in Frontier Language Models

Large language models (LLMs) are increasingly employed to predict molecular properties. However, prediction error alone cannot distinguish prediction from retrieval of published values. We audit 22 frontier models on 12 molecular regression datasets in a zero-shot setting, assessed against a molecule-blind reference derived from each dataset's labels. Significant retrieval is concentrated on 5 datasets, with isolated flagged LLMs elsewhere. Increasing the reasoning setting raises the number of flagged model--dataset combinations from 47 to 89 of 264. An in-context blinding experiment reduces retrieval but leaves a quarter of the combinations flagged. Blinding changes model rankings and increases errors. Because blinding also removes chemically interpretable structure, the error increase can only be partially attributed to reduced retrieval.

cs.AI↗

arXiv2026

In-Context Molecular Property Prediction with LLMs: A Blinding Study on Memorization and Knowledge Conflicts

The capabilities of large language models (LLMs) have expanded beyond natural language processing to scientific prediction tasks, including molecular property prediction. However, their effectiveness in in-context learning remains ambiguous, particularly given the potential for training data contamination in widely used benchmarks. This paper investigates whether LLMs perform genuine in-context regression on molecular properties or instead rely on verbatim retrieval of memorized target values. Furthermore, we analyze the interplay between pre-trained knowledge and in-context information through a series of progressively blinded experiments. We evaluate nine LLM variants across three families (GPT-4.1, GPT-5, Gemini 2.5) on three MoleculeNet datasets (Delaney solubility, Lipophilicity, QM7 atomization energy) using a systematic blinding approach that iteratively reduces available information, complemented by 0-, 60-, and 1000-shot in-context sample sizes as an additional control for information access. To validate the memorization analysis and the blinding experiments, we add a positive and a negative control for the memorization experiments and structural reference baselines for the multi-shot experiments as well as bootstrap confidence intervals for all results. We find no evidence of verbatim retrieval on the legacy benchmarks and show that blinding exposes conflicts between pre-trained knowledge and in-context information. This work provides a principled framework for evaluating molecular property prediction under controlled information access.

cs.LG↗

arXiv2020

In situ kinetics studies of Zn-Al LDH intercalation with corrosion related species

Kinetics parameters for three anion exchange reactions - Zn-LDH-NO3 - Zn-LDH-Cl, Zn-LDH-NO3 - Zn-LDH-SO4 and Zn-LDH-NO3 - Zn-LDH-VOx - were obtained by in situ synchrotron study. The first and the second ones are two-stage reactions; the first stage is characterized by the two-dimensional diffusion-controlled reaction following deceleratory nucleation and the second stage is a one-dimensional diffusion-controlled reaction also with a decelerator nucleation effect. In the case of exchange NO3 - Cl host anions are completely released, while in the case of NO3 - SO42 the reaction ends without complete release of nitrate anions. The exchange of Zn-LDH-NO3 - Zn-LDH-VOx is one-stage reaction and goes much slower than the previous two cases. It is characterized by a one stage two-dimensional reaction and nucleation considered to be instantaneous in this case. As a result, at the end of this process there are two crystalline phases with different polyvanadate species, presumably V4O124 and V2O74, nitrate anions were not completely released. The rate of replacing NO3 anions by guest ones can be represented as Cl > SO42 > VOxy.

cond-mat.mtrl-sci↗