Mohd Zaki
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Mohd Zaki has a total of 40 co-authors. Here are the top co-authors by number of shared publications:
- Naduvath Mana Anoop Krishnan
Department of Civil Engineering, Indian Institute of Technology Delhi, Hauz Khas, New Delhi 110016, India
9 shared publications - Mausam
Department of Computer Science and Engineering, Indian Institute of Technology Delhi, New Delhi, India
4 shared publications - Nitya Nand Gosvami
Department of Materials Science and Engineering Indian Institute of Technology Delhi New Delhi India
4 shared publications - Morten Mattrup Smedskjaer
Department of Chemistry and Bioscience Aalborg University Aalborg Denmark
2 shared publications N. M. Anoop Krishnan
2 shared publications- Sajid Mannan
Department of Civil and Environmental Engineering, Indian Institute of Technology Delhi, New Delhi, India
2 shared publications
Latest Publications
- Top Cited Papers
- 27 February 2026
- Published by Springer Nature in Nature Machine Intelligence
- Vol. 8 (3) , 435-448
A family of large language models for materials research with insights into model adaptability in continued pretraining
- 27 February 2026
- Published by Springer Nature in Nature Machine Intelligence
- Vol. 8 (3) , 435-448
Top Cited PapersA family of large language models for materials research with insights into model adaptability in continued pretraining
- Top Cited PapersOpen Access
- 14 October 2025
- Published by Springer Nature in Nature Communications
- Vol. 16 (1) , 1-15
Evaluating large language model agents for automation of atomic force microscopy
Large language models (LLMs) are transforming laboratory automation by enabling self-driving laboratories (SDLs) that could accelerate materials research. However, current SDL implementations rely on rigid protocols that fail to capture the adaptability and intuition of expert scientists in dynamic experimental settings. Here, we show that LLM agents can automate atomic force microscopy (AFM) through our Artificially Intelligent Lab Assistant (AILA) framework. Further, we develop AFMBench—a comprehensive evaluation suite challenging LLM agents across the complete scientific workflow from experimental design to results analysis. We find that state-of-the-art LLMs struggle with basic tasks and coordination scenarios. Notably, models excelling at materials science question-answering perform poorly in laboratory settings, showing that domain knowledge does not translate to experimental capabilities. Additionally, we observe that LLM agents can deviate from instructions, a phenomenon referred to as sleepwalking, raising safety alignment concerns for SDL applications. Our ablations reveal that multi-agent frameworks significantly outperform single-agent approaches, though both remain sensitive to minor changes in instruction formatting or prompting. Finally, we evaluate AILA’s effectiveness in increasingly advanced experiments—AFM calibration, feature detection, mechanical property measurement, graphene layer counting, and indenter detection. These findings establish the necessity for benchmarking and robust safety protocols before deploying LLM agents as autonomous laboratory assistants across scientific disciplines.
- 14 October 2025
- Published by Springer Nature in Nature Communications
- Vol. 16 (1) , 1-15
Top Cited PapersOpen AccessEvaluating large language model agents for automation of atomic force microscopy
Large language models (LLMs) are transforming laboratory automation by enabling self-driving laboratories (SDLs) that could accelerate materials research. However, current SDL implementations rely on rigid protocols that fail to capture the adaptability and intuition of expert scientists in dynamic experimental settings. Here, we show that LLM agents can automate atomic force microscopy (AFM) through our Artificially Intelligent Lab Assistant (AILA) framework. Further, we develop AFMBench—a comprehensive evaluation suite challenging LLM agents across the complete scientific workflow from experimental design to results analysis. We find that state-of-the-art LLMs struggle with basic tasks and coordination scenarios. Notably, models excelling at materials science question-answering perform poorly in laboratory settings, showing that domain knowledge does not translate to experimental capabilities. Additionally, we observe that LLM agents can deviate from instructions, a phenomenon referred to as sleepwalking, raising safety alignment concerns for SDL applications. Our ablations reveal that multi-agent frameworks significantly outperform single-agent approaches, though both remain sensitive to minor changes in instruction formatting or prompting. Finally, we evaluate AILA’s effectiveness in increasingly advanced experiments—AFM calibration, feature detection, mechanical property measurement, graphene layer counting, and indenter detection. These findings establish the necessity for benchmarking and robust safety protocols before deploying LLM agents as autonomous laboratory assistants across scientific disciplines.
- Open Access
- 19 December 2024
- Published by Springer Nature in Research Square
Autonomous Microscopy Experiments through Large Language Model Agents
The emergence of large language models (LLMs) has accelerated the development of self-driving laboratories (SDLs) for materials research. Despite their transformative potential, current SDL implementations rely on rigid, predefined protocols that limit their adaptability to dynamic experimental scenarios across different labs. A significant challenge persists in measuring how effectively AI agents can replicate the adaptive decision-making and experimental intuition of expert scientists. Here, we introduce AILA (Artificially Intelligent Lab Assistant), a framework that automates atomic force microscopy (AFM) through LLM-driven agents. Using AFM as an experimental testbed, we develop AFMBench—a comprehensive evaluation suite that challenges AI agents based on language models like GPT-4o and GPT-3.5 to perform tasks spanning the scientific workflow: from experimental design to results analysis. Our systematic assessment shows that state-of-the-art language models struggle even with basic tasks such as documentation retrieval, leading to a significant decline in performance in multi-agent coordination scenarios.Further, we observe that LLMs exhibit a tendency to not adhere to instructions or even divagate to additional tasks beyond the original request, raising serious concerns regarding safety alignment aspects of AI agents for SDLs. Finally, we demonstrate the application of AILA on increasingly complex experiments open-ended experiments: automated AFM calibration, high-resolution feature detection, and mechanical property measurement. Our findings emphasize the necessity for stringent benchmarking protocols before deploying AI agents as laboratory assistants across scientific disciplines.
- 19 December 2024
- Published by Springer Nature in Research Square
Open AccessAutonomous Microscopy Experiments through Large Language Model Agents
The emergence of large language models (LLMs) has accelerated the development of self-driving laboratories (SDLs) for materials research. Despite their transformative potential, current SDL implementations rely on rigid, predefined protocols that limit their adaptability to dynamic experimental scenarios across different labs. A significant challenge persists in measuring how effectively AI agents can replicate the adaptive decision-making and experimental intuition of expert scientists. Here, we introduce AILA (Artificially Intelligent Lab Assistant), a framework that automates atomic force microscopy (AFM) through LLM-driven agents. Using AFM as an experimental testbed, we develop AFMBench—a comprehensive evaluation suite that challenges AI agents based on language models like GPT-4o and GPT-3.5 to perform tasks spanning the scientific workflow: from experimental design to results analysis. Our systematic assessment shows that state-of-the-art language models struggle even with basic tasks such as documentation retrieval, leading to a significant decline in performance in multi-agent coordination scenarios.Further, we observe that LLMs exhibit a tendency to not adhere to instructions or even divagate to additional tasks beyond the original request, raising serious concerns regarding safety alignment aspects of AI agents for SDLs. Finally, we demonstrate the application of AILA on increasingly complex experiments open-ended experiments: automated AFM calibration, high-resolution feature detection, and mechanical property measurement. Our findings emphasize the necessity for stringent benchmarking protocols before deploying AI agents as laboratory assistants across scientific disciplines.
- Top Cited PapersOpen Access
- 18 March 2024
- Published by Royal Society of Chemistry (RSC) in Digital Discovery
- Vol. 3 (5) , 1021-1037
Reconstructing the materials tetrahedron: challenges in materials information extraction
Quantifying challenges towards information extraction from scientific articles to complete the materials science tetrahedron.
- 18 March 2024
- Published by Royal Society of Chemistry (RSC) in Digital Discovery
- Vol. 3 (5) , 1021-1037
Top Cited PapersOpen AccessReconstructing the materials tetrahedron: challenges in materials information extraction
Quantifying challenges towards information extraction from scientific articles to complete the materials science tetrahedron.
- Open Access
- 20 December 2023
- Published by Royal Society of Chemistry (RSC) in Digital Discovery
- Vol. 3 (2) , 313-327
MaScQA: investigating materials science knowledge of large language models
Information extraction and textual comprehension from materials literature are vital for developing an exhaustive knowledge base that enables accelerated materials discovery. Language models have demonstrated their capability to answer domain-specific questions and retrieve information from knowledge bases. However, there are no benchmark datasets in the materials science domain that can be used to evaluate the understanding of the key concepts by these language models. In this work, we curate a dataset of 650 challenging questions from the materials domain that require the knowledge and skills of a materials science student who has cleared their undergraduate degree. We classify these questions based on their structure and the materials science domain-based subcategories. Further, we evaluate the performance of LLaMA-2-70B, GPT-3.5, and GPT-4 models on solving these questions via zero-shot and chain of thought prompting. It is observed that GPT-4 gives the best performance (∼62% accuracy) as compared to other models. Interestingly, in contrast to the general observation, no significant improvement in accuracy is observed with the chain of thought prompting. To evaluate the limitations, we performed an error analysis, which revealed conceptual errors (∼72%) as the major contributor compared to computational errors (∼28%) towards the reduced performance of the LLMs. We also compared GPT-4 with human performance and observed that GPT-4 is better than an average student and comes close to passing the exam. We also show applications of the best performing model (GPT-4) on composition–extraction from tables of materials science research papers and code writing tasks. While GPT-4 performs poorly on composition extraction, it outperforms all other models on the code writing task. We hope that the dataset, analysis, and applications discussed in this work will promote further research in developing better materials science domain-specific LLMs and strategies for information extraction.
- 20 December 2023
- Published by Royal Society of Chemistry (RSC) in Digital Discovery
- Vol. 3 (2) , 313-327
Open AccessMaScQA: investigating materials science knowledge of large language models
Information extraction and textual comprehension from materials literature are vital for developing an exhaustive knowledge base that enables accelerated materials discovery. Language models have demonstrated their capability to answer domain-specific questions and retrieve information from knowledge bases. However, there are no benchmark datasets in the materials science domain that can be used to evaluate the understanding of the key concepts by these language models. In this work, we curate a dataset of 650 challenging questions from the materials domain that require the knowledge and skills of a materials science student who has cleared their undergraduate degree. We classify these questions based on their structure and the materials science domain-based subcategories. Further, we evaluate the performance of LLaMA-2-70B, GPT-3.5, and GPT-4 models on solving these questions via zero-shot and chain of thought prompting. It is observed that GPT-4 gives the best performance (∼62% accuracy) as compared to other models. Interestingly, in contrast to the general observation, no significant improvement in accuracy is observed with the chain of thought prompting. To evaluate the limitations, we performed an error analysis, which revealed conceptual errors (∼72%) as the major contributor compared to computational errors (∼28%) towards the reduced performance of the LLMs. We also compared GPT-4 with human performance and observed that GPT-4 is better than an average student and comes close to passing the exam. We also show applications of the best performing model (GPT-4) on composition–extraction from tables of materials science research papers and code writing tasks. While GPT-4 performs poorly on composition extraction, it outperforms all other models on the code writing task. We hope that the dataset, analysis, and applications discussed in this work will promote further research in developing better materials science domain-specific LLMs and strategies for information extraction.
- Open Access
- 1 April 2023
- Published by IOP Publishing in Journal of Physics: Materials
- Vol. 6 (2) , 024003
Accelerated design of chalcogenide glasses through interpretable machine learning for composition–property relationships
Chalcogenide glasses (ChGs) possess various outstanding properties enabling essential applications, such as optical discs, infrared cameras, and thermal imaging systems. Despite their ubiquitous usage, these materials’ composition–property relationships remain poorly understood, impeding the pace of their discovery. Here, we use a large experimental dataset comprising ∼24 000 glass compositions made of 51 distinct elements from the periodic table to develop machine learning (ML) models for predicting 12 properties, namely, annealing point, bulk modulus, density, Vickers hardness, Littleton point, Young’s modulus, shear modulus, softening point, thermal expansion coefficient, glass transition temperature, liquidus temperature, and refractive index. These models are the largest regarding the compositional space and the number of properties covered for ChGs. Further, we use Shapley additive explanations, a game theory-based algorithm, to explain the properties’ compositional control by quantifying each element’s role toward model predictions. This work provides a powerful tool for interpreting the model’s prediction and designing new ChG compositions with targeted properties. Finally, using the trained ML models, we develop several glass-selection charts that can potentially aid in the rational design of novel ChGs for various applications.
- 1 April 2023
- Published by IOP Publishing in Journal of Physics: Materials
- Vol. 6 (2) , 024003
Open AccessAccelerated design of chalcogenide glasses through interpretable machine learning for composition–property relationships
Chalcogenide glasses (ChGs) possess various outstanding properties enabling essential applications, such as optical discs, infrared cameras, and thermal imaging systems. Despite their ubiquitous usage, these materials’ composition–property relationships remain poorly understood, impeding the pace of their discovery. Here, we use a large experimental dataset comprising ∼24 000 glass compositions made of 51 distinct elements from the periodic table to develop machine learning (ML) models for predicting 12 properties, namely, annealing point, bulk modulus, density, Vickers hardness, Littleton point, Young’s modulus, shear modulus, softening point, thermal expansion coefficient, glass transition temperature, liquidus temperature, and refractive index. These models are the largest regarding the compositional space and the number of properties covered for ChGs. Further, we use Shapley additive explanations, a game theory-based algorithm, to explain the properties’ compositional control by quantifying each element’s role toward model predictions. This work provides a powerful tool for interpreting the model’s prediction and designing new ChG compositions with targeted properties. Finally, using the trained ML models, we develop several glass-selection charts that can potentially aid in the rational design of novel ChGs for various applications.
- Open Access
Accelerated Design of Chalcogenide Glasses through Interpretable Machine Learning for Composition Property Relationships
Chalcogenide glasses possess several outstanding properties that enable several ground breaking applications, such as optical discs, infrared cameras, and thermal imaging systems. Despite the ubiquitous usage of these glasses, the composition property relationships in these materials remain poorly understood. Here, we use a large experimental dataset comprising approx 24000 glass compositions made of 51 distinct elements from the periodic table to develop machine learning models for predicting 12 properties, namely, annealing point, bulk modulus, density, Vickers hardness, Littleton point, Youngs modulus, shear modulus, softening point, thermal expansion coefficient, glass transition temperature, liquidus temperature, and refractive index. These models, by far, are the largest for chalcogenide glasses. Further, we use SHAP, a game theory based algorithm, to interpret the output of machine learning algorithms by analyzing the contributions of each element towards the models prediction of a property. This provides a powerful tool for experimentalists to interpret the models prediction and hence design new glass compositions with targeted properties. Finally, using the models, we develop several glass selection charts that can potentially aid in the rational design of novel chalcogenide glasses for various applications.
Open AccessAccelerated Design of Chalcogenide Glasses through Interpretable Machine Learning for Composition Property Relationships
Chalcogenide glasses possess several outstanding properties that enable several ground breaking applications, such as optical discs, infrared cameras, and thermal imaging systems. Despite the ubiquitous usage of these glasses, the composition property relationships in these materials remain poorly understood. Here, we use a large experimental dataset comprising approx 24000 glass compositions made of 51 distinct elements from the periodic table to develop machine learning models for predicting 12 properties, namely, annealing point, bulk modulus, density, Vickers hardness, Littleton point, Youngs modulus, shear modulus, softening point, thermal expansion coefficient, glass transition temperature, liquidus temperature, and refractive index. These models, by far, are the largest for chalcogenide glasses. Further, we use SHAP, a game theory based algorithm, to interpret the output of machine learning algorithms by analyzing the contributions of each element towards the models prediction of a property. This provides a powerful tool for experimentalists to interpret the models prediction and hence design new glass compositions with targeted properties. Finally, using the models, we develop several glass selection charts that can potentially aid in the rational design of novel chalcogenide glasses for various applications.
- 10 August 2022
- Published by Elsevier in Scripta Materialia
- Vol. 221
Interpretable Machine Learning Approach for Identifying the Tip Sharpness in Atomic Force Microscopy
- 10 August 2022
- Published by Elsevier in Scripta Materialia
- Vol. 221
Interpretable Machine Learning Approach for Identifying the Tip Sharpness in Atomic Force Microscopy
- Top Cited PapersOpen Access
- 3 May 2022
- Published by Springer Nature in npj Computational Materials
- Vol. 8 (1) , 1-11
MatSciBERT: A materials domain language model for text mining and information extraction
A large amount of materials science knowledge is generated and stored as text published in peer-reviewed scientific literature. While recent developments in natural language processing, such as Bidirectional Encoder Representations from Transformers (BERT) models, provide promising information extraction tools, these models may yield suboptimal results when applied on materials domain since they are not trained in materials science specific notations and jargons. Here, we present a materials-aware language model, namely, MatSciBERT, trained on a large corpus of peer-reviewed materials science publications. We show that MatSciBERT outperforms SciBERT, a language model trained on science corpus, and establish state-of-the-art results on three downstream tasks, named entity recognition, relation classification, and abstract classification. We make the pre-trained weights of MatSciBERT publicly accessible for accelerated materials discovery and information extraction from materials science texts.
- 3 May 2022
- Published by Springer Nature in npj Computational Materials
- Vol. 8 (1) , 1-11
Top Cited PapersOpen AccessMatSciBERT: A materials domain language model for text mining and information extraction
A large amount of materials science knowledge is generated and stored as text published in peer-reviewed scientific literature. While recent developments in natural language processing, such as Bidirectional Encoder Representations from Transformers (BERT) models, provide promising information extraction tools, these models may yield suboptimal results when applied on materials domain since they are not trained in materials science specific notations and jargons. Here, we present a materials-aware language model, namely, MatSciBERT, trained on a large corpus of peer-reviewed materials science publications. We show that MatSciBERT outperforms SciBERT, a language model trained on science corpus, and establish state-of-the-art results on three downstream tasks, named entity recognition, relation classification, and abstract classification. We make the pre-trained weights of MatSciBERT publicly accessible for accelerated materials discovery and information extraction from materials science texts.