There are two common ways in which developers are incorporating proprietary and domain-specific data when building applications of Large Language Models (LLMs): Retrieval-Augmented Generation (RAG) and Fine-Tuning. RAG augments the prompt with the external data, while fine-Tuning incorporates the additional knowledge into the model itself. However, the pros and cons of both approaches are not well understood. In this paper, we propose a pipeline for fine-tuning and RAG, and present the tradeoffs of both for multiple popular LLMs, including Llama2-13B, GPT-3.5, and GPT-4. Our pipeline consists of multiple stages, including extracting information from PDFs, generating questions and answers, using them for fine-tuning, and leveraging GPT-4 for evaluating the results. We propose metrics to assess the performance of different stages of the RAG and fine-Tuning pipeline. We conduct an in-depth study on an agricultural dataset. Agriculture as an industry has not seen much penetration of AI, and we study a potentially disruptive application - what if we could provide location-specific insights to a farmer? Our results show the effectiveness of our dataset generation pipeline in capturing geographic-specific knowledge, and the quantitative and qualitative benefits of RAG and fine-tuning. We see an accuracy increase of over 6 p.p. when fine-tuning the model and this is cumulative with RAG, which increases accuracy by 5 p.p. further. In one particular experiment, we also demonstrate that the fine-tuned model leverages information from across geographies to answer specific questions, increasing answer similarity from 47% to 72%. Overall, the results point to how systems built using LLMs can be adapted to respond and incorporate knowledge across a dimension that is critical for a specific industry, paving the way for further applications of LLMs in other industrial domains.

Optimization of expensive, noisy, black-box functions commonly occurs in designing sustainable process systems; we review some motivating applications in Section 2 below. In principle, one can apply any type of derivativefree optimization (DFO) method [2] to tackle such problems; however, these methods may require a large number of evaluations to converge. When evaluations of f are expensive, we desire an intelligent sample selection strategy that accounts for all available information to select future samples. The BO framework provides a systematic and versatile way to identify highly informative design candidates using minimal function evaluations. This article reviews recent advances in BO methods and highlights their relevance to design of next-generation sustainable energy and process systems. We also offer some perspectives on future research directions and associated challenges.

This paper presents a modeling effort to explore the underlying physics of temperature evolution during additive friction stir deposition (AFSD) by a human-AI teaming approach. AFSD is an emerging solid-state additive manufacturing technology that deposits materials without melting. However, both process modeling and modeling of the AFSD tool are at an early stage. In this paper, a human-AI teaming approach is proposed to combine models based on first principles with AI. The resulting human-informed machine learning method, denoted as AFSD-Physics, can effectively learn the governing equations of temperature evolution at the tool and the build from in-process measurements. Experiments are designed and conducted to collect in-process measurements for the deposition of aluminum 7075 with a total of 30 layers. The acquired governing equations are physically interpretable models with low computational cost and high accuracy. Model predictions show good agreement with the measurements. Experimental validation with new process parameters demonstrates the model's generalizability and potential for use in tool temperature control and process optimization.

In the rapidly evolving field of scientific research, efficiently extracting key information from the burgeoning volume of scientific papers remains a formidable challenge. This paper introduces an innovative framework designed to automate the extraction of vital data from scientific PDF documents, enabling researchers to discern future research trajectories more readily. AutoIE uniquely integrates four novel components: (1) A multi-semantic feature fusion-based approach for PDF document layout analysis; (2) Advanced functional block recognition in scientific texts; (3) A synergistic technique for extracting and correlating information on molecular sieve synthesis; (4) An online learning paradigm tailored for molecular sieve literature. Our SBERT model achieves high Marco F1 scores of 87.19 and 89.65 on CoNLL04 and ADE datasets. In addition, a practical application of AutoIE in the petrochemical molecular sieve synthesis domain demonstrates its efficacy, evidenced by an impressive 78\% accuracy rate. This research paves the way for enhanced data management and interpretation in molecular sieve synthesis. It is a valuable asset for seasoned experts and newcomers in this specialized field.

Robotic hands are an important tool for replacing humans in handling toxic or radioactive materials. However, these are usually highly expensive, and in many cases, once they are contaminated, they cannot be re-used. Some solutions cope with this challenge by 3D printing parts of a tendon-based hand. However, fabrication requires additional assembly steps. Therefore, a novice user may have difficulties fabricating a hand upon contamination of the previous one. We propose the Print-N-Grip (PNG) hand which is a tendon-based underactuated mechanism able to adapt to the shape of objects. The hand is fabricated through one-shot 3D printing with no additional engineering effort, and can accommodate a number of fingers as desired by the practitioner. Due to its low cost, the PNG hand can easily be detached from a universal base for disposing upon contamination, and replaced by a newly printed one. In addition, the PNG hand is scalable such that one can effortlessly resize the computerized model and print. We present the design of the PNG hand along with experiments to show the capabilities and high durability of the hand.

The design of functional materials with desired properties is essential in driving technological advances in areas like energy storage, catalysis, and carbon capture. Generative models provide a new paradigm for materials design by directly generating entirely novel materials given desired property constraints. Despite recent progress, current generative models have low success rate in proposing stable crystals, or can only satisfy a very limited set of property constraints. Here, we present MatterGen, a model that generates stable, diverse inorganic materials across the periodic table and can further be fine-tuned to steer the generation towards a broad range of property constraints. To enable this, we introduce a new diffusion-based generative process that produces crystalline structures by gradually refining atom types, coordinates, and the periodic lattice. We further introduce adapter modules to enable fine-tuning towards any given property constraints with a labeled dataset. Compared to prior generative models, structures produced by MatterGen are more than twice as likely to be novel and stable, and more than 15 times closer to the local energy minimum. After fine-tuning, MatterGen successfully generates stable, novel materials with desired chemistry, symmetry, as well as mechanical, electronic and magnetic properties. Finally, we demonstrate multi-property materials design capabilities by proposing structures that have both high magnetic density and a chemical composition with low supply-chain risk. We believe that the quality of generated materials and the breadth of MatterGen's capabilities represent a major advancement towards creating a universal generative model for materials design.

Semi-autogenous grinding (SAG) mills play a pivotal role in the grinding circuit of mineral processing plants. Accurate prediction of SAG mill throughput as a crucial performance metric is of utmost importance. The potential of applying genetic programming (GP) for this purpose has yet to be thoroughly investigated. This study introduces an enhanced GP approach entitled multi-equation GP (MEGP) for more accurate prediction of SAG mill throughput. In the new proposed method multiple equations, each accurately predicting mill throughput for specific clusters of training data are extracted. These equations are then employed to predict mill throughput for test data using various approaches. To assess the effect of distance measures, four different distance measures are employed in MEGP method. Comparative analysis reveals that the best MEGP approach achieves an average improvement of 10.74% in prediction accuracy compared with standard GP. In this approach, all extracted equations are utilized and both the number of data points in each data cluster and the distance to clusters are incorporated for calculating the final prediction. Further investigation of distance measures indicates that among four different metrics employed including Euclidean, Manhattan, Chebyshev, and Cosine distance, the Euclidean distance measure yields the most accurate results for the majority of data splits.

Discovery of new materials has a documented history of propelling human progress for centuries and more. The behaviour of a material is a function of its composition, structure, and properties, which further depend on its processing and testing conditions. Recent developments in deep learning and natural language processing have enabled information extraction at scale from published literature such as peer-reviewed publications, books, and patents. However, this information is spread in multiple formats, such as tables, text, and images, and with little or no uniformity in reporting style giving rise to several machine learning challenges. Here, we discuss, quantify, and document these challenges in automated information extraction (IE) from materials science literature towards the creation of a large materials science knowledge base. Specifically, we focus on IE from text and tables and outline several challenges with examples. We hope the present work inspires researchers to address the challenges in a coherent fashion, providing a fillip to IE towards a materials knowledge base.

Unlike routine tasks where consistency is prized, in creativity and innovation the goal is to create a diverse set of ideas. This paper delves into the burgeoning interest in employing Artificial Intelligence (AI) to enhance the productivity and quality of the idea generation process. While previous studies have found that the average quality of AI ideas is quite high, prior research also has pointed to the inability of AI-based brainstorming to create sufficient dispersion of ideas, which limits novelty and the quality of the overall best idea. Our research investigates methods to increase the dispersion in AI-generated ideas. Using GPT-4, we explore the effect of different prompting methods on Cosine Similarity, the number of unique ideas, and the speed with which the idea space gets exhausted. We do this in the domain of developing a new product development for college students, priced under $50. In this context, we find that (1) pools of ideas generated by GPT-4 with various plausible prompts are less diverse than ideas generated by groups of human subjects (2) the diversity of AI generated ideas can be substantially improved using prompt engineering (3) Chain-of-Thought (CoT) prompting leads to the highest diversity of ideas of all prompts we evaluated and was able to come close to what is achieved by groups of human subjects. It also was capable of generating the highest number of unique ideas of any prompt we studied.

The tabulation of commonly used letters, as determined by letter frequency, was later utilized to improve typewriter keyboard arrangement by minimizing hand motion [5]. Statistical characteristics of different letters of the English alphabet was further studied in the context of different sentence structures [6]. The letters'B', 'S', 'M', 'H', 'C' were found to most frequently occur as the initial letters of proper nouns, while'E', 'A', 'R', 'N' were the most frequently used letters when the entire proper noun is considered. For entire text documents, the most commonly used letters were found to be'E', 'T', 'A', 'O', 'N'. Interestingly, 95% of the English vocabulary was found to be represented by 13 letters of the alphabet. Our manuscript expanded upon the statistical study of the English alphabet by evaluating letter frequency in the context of different categories of writings. We analyzed news articles, novels, plays, and scientific articles for letter frequency and distribution. As a result, we determined the information density of the letters of the alphabet. Additionally, we developed a metric called "distance, d" to act as a simple algorithm for recognizing writing category.