Recent breakthroughs in large language models (LLMs) exemplified by the impressive mathematical and scientific reasoning capabilities of the o1 model have spotlighted the critical importance of high-quality training data in advancing LLM performance across STEM disciplines. While the mathematics community has benefited from a growing body of curated datasets, the scientific domain at the higher education level has long suffered from a scarcity of comparable resources. To address this gap, we present SCP-116K, a new large-scale dataset of 116,756 high-quality problem-solution pairs, automatically extracted from heterogeneous sources using a streamlined and highly generalizable pipeline. Our approach involves stringent filtering to ensure the scientific rigor and educational level of the extracted materials, while maintaining adaptability for future expansions or domain transfers. By openly releasing both the dataset and the extraction pipeline, we seek to foster research on scientific reasoning, enable comprehensive performance evaluations of new LLMs, and lower the barrier to replicating the successes of advanced models like o1 in the broader science community. We believe SCP-116K will serve as a critical resource, catalyzing progress in high-level scientific reasoning tasks and promoting further innovations in LLM development. The dataset and code are publicly available at https://github.com/AQA6666/SCP-116K-open.

Large Language Models (LLMs) have demonstrated remarkable capabilities across various domains. Math Word Problems (MWPs) serve as a crucial benchmark for evaluating LLMs' reasoning abilities. While most research primarily focuses on improving accuracy, it often neglects understanding and addressing the underlying patterns of errors. Current error classification methods rely on static and predefined categories, which limit their ability to capture the full spectrum of error patterns in mathematical reasoning. To enable systematic error analysis, we collect error samples from 15 different LLMs of varying sizes across four distinct MWP datasets using multiple sampling strategies. Based on this extensive collection, we introduce MWPES-300K, a comprehensive dataset containing 304,865 error samples that cover diverse error patterns and reasoning paths. To reduce human bias and enable fine-grained analysis of error patterns, we propose a novel framework for automated dynamic error classification in mathematical reasoning. Experimental results demonstrate that dataset characteristics significantly shape error patterns, which evolve from basic to complex manifestations as model capabilities increase. With deeper insights into error patterns, we propose error-aware prompting that incorporates common error patterns as explicit guidance, leading to significant improvements in mathematical reasoning performance.

Short-reading comprehension questions help students understand text structure but lack effective feedback. Students struggle to identify and correct errors, while manual feedback creation is labor-intensive. This highlights the need for automated feedback linking responses to a scoring rubric for deeper comprehension. Despite advances in Natural Language Processing (NLP), research has focused on automatic grading, with limited work on feedback generation. To address this, we propose a system that generates feedback for student responses. Our contributions are twofold. First, we introduce the first system for feedback on short-answer reading comprehension. These answers are derived from the text, requiring structural understanding. We propose an "answer diagnosis graph," integrating the text's logical structure with feedback templates. Using this graph and NLP techniques, we estimate students' comprehension and generate targeted feedback. Second, we evaluate our feedback through an experiment with Japanese high school students (n=39). They answered two 70-80 word questions and were divided into two groups with minimal academic differences. One received a model answer, the other system-generated feedback. Both re-answered the questions, and we compared score changes. A questionnaire assessed perceptions and motivation. Results showed no significant score improvement between groups, but system-generated feedback helped students identify errors and key points in the text. It also significantly increased motivation. However, further refinement is needed to enhance text structure understanding.

As the use of Generative AI (GenAI) tools becomes more prevalent in interpersonal communication, understanding their impact on social perceptions is crucial. According to signaling theory, GenAI may undermine the credibility of social signals conveyed in writing, since it reduces the cost of writing and makes it hard to verify the authenticity of messages. Using a pre-registered large-scale online experiment (N = 647; Prolific), featuring scenarios in a range of communication contexts (personal vs. professional; close others vs. strangers), we explored how senders' use of GenAI influenced recipients' impressions of senders, both when GenAI use was known or uncertain. Consistent with past work, we found strong negative effects on social impressions when disclosing that a message was AI-generated, compared to when the same message was human-written. However, under the more realistic condition when potential GenAI use was not explicitly highlighted, recipients did not exhibit any skepticism towards senders, and these "uninformed" impressions were virtually indistinguishable from those of fully human-written messages. Even when we highlighted the potential (but uncertain) use of GenAI, recipients formed overly positive impressions. These results are especially striking given that 46% of our sample admitted having used such tools for writing messages, just within the past two weeks. Our findings put past work in a new light: While social judgments can be substantially affected when GenAI use is explicitly disclosed, this information may not be readily available in more realistic communication settings, making recipients blissfully ignorant about others' potential use of GenAI.

We present HardML, a benchmark designed to evaluate the knowledge and reasoning abilities in the fields of data science and machine learning. HardML comprises a diverse set of 100 challenging multiple-choice questions, handcrafted over a period of 6 months, covering the most popular and modern branches of data science and machine learning. These questions are challenging even for a typical Senior Machine Learning Engineer to answer correctly. To minimize the risk of data contamination, HardML uses mostly original content devised by the author. Current state-of-the-art AI models achieve a 30% error rate on this benchmark, which is about 3 times larger than the one achieved on the equivalent, well-known MMLU-ML. While HardML is limited in scope and not aiming to push the frontier--primarily due to its multiple-choice nature--it serves as a rigorous and modern testbed to quantify and track the progress of top AI. While plenty benchmarks and experimentation in LLM evaluation exist in other STEM fields like mathematics, physics and chemistry, the sub-fields of data science and machine learning remain fairly underexplored.

Intelligent Tutoring Systems (ITSs) have revolutionized education by offering personalized learning experiences. However, as goal-oriented learning, which emphasizes efficiently achieving specific objectives, becomes increasingly important in professional contexts, existing ITSs often struggle to deliver this type of targeted learning experience. In this paper, we propose GenMentor, an LLM-powered multi-agent framework designed to deliver goal-oriented, personalized learning within ITS. GenMentor begins by accurately mapping learners' goals to required skills using a fine-tuned LLM trained on a custom goal-to-skill dataset. After identifying the skill gap, it schedules an efficient learning path using an evolving optimization approach, driven by a comprehensive and dynamic profile of learners' multifaceted status. Additionally, GenMentor tailors learning content with an exploration-drafting-integration mechanism to align with individual learner needs. Extensive automated and human evaluations demonstrate GenMentor's effectiveness in learning guidance and content quality. Furthermore, we have deployed it in practice and also implemented it as an application. Practical human study with professional learners further highlights its effectiveness in goal alignment and resource targeting, leading to enhanced personalization. Supplementary resources are available at https://github.com/GeminiLight/gen-mentor.

In this work, we explore the capabilities of multiplexed gradient descent (MGD), a scalable and efficient perturbative zeroth-order training method for estimating the gradient of a loss function in hardware and training it via stochastic gradient descent. We extend the framework to include both weight and node perturbation, and discuss the advantages and disadvantages of each approach. We investigate the time to train networks using MGD as a function of network size and task complexity. Previous research has suggested that perturbative training methods do not scale well to large problems, since in these methods the time to estimate the gradient scales linearly with the number of network parameters. However, in this work we show that the time to reach a target accuracy--that is, actually solve the problem of interest--does not follow this undesirable linear scaling, and in fact often decreases with network size. Furthermore, we demonstrate that MGD can be used to calculate a drop-in replacement for the gradient in stochastic gradient descent, and therefore optimization accelerators such as momentum can be used alongside MGD, ensuring compatibility with existing machine learning practices. Our results indicate that MGD can efficiently train large networks on hardware, achieving accuracy comparable to backpropagation, thus presenting a practical solution for future neuromorphic computing systems.

This paper describes how to extend the usual one-level tag selection navigation paradigm in folksonomy-based digital collections to a multilevel browsing one, according to which it is possible to incrementally narrow down the set of selected objects in a collection by sequentially adding more and more filtering tags. For this purpose, we present a browsing strategy based on finite automata. Also, we provide some experimental results concerning the application of the approach in Clavy, a system for managing digital collections with reconfigurable structures in digital humanities and educational settings.

This study introduces an approach to Estonian text simplification using two model architectures: a neural machine translation model and a fine-tuned large language model (LLaMA). Given the limited resources for Estonian, we developed a new dataset, the Estonian Simplification Dataset, combining translated data and GPT-4.0-generated simplifications. We benchmarked OpenNMT, a neural machine translation model that frames text simplification as a translation task, and fine-tuned the LLaMA model on our dataset to tailor it specifically for Estonian simplification. Manual evaluations on the test set show that the LLaMA model consistently outperforms OpenNMT in readability, grammaticality, and meaning preservation. These findings underscore the potential of large language models for low-resource languages and provide a basis for further research in Estonian text simplification.

The integration of large language models (LLMs) into supply chain management (SCM) is revolutionizing the industry by improving decision-making, predictive analytics, and operational efficiency. This white paper explores the transformative impact of LLMs on various SCM functions, including demand forecasting, inventory management, supplier relationship management, and logistics optimization. By leveraging advanced data analytics and real-time insights, LLMs enable organizations to optimize resources, reduce costs, and improve responsiveness to market changes. Key findings highlight the benefits of integrating LLMs with emerging technologies such as IoT, blockchain, and robotics, which together create smarter and more autonomous supply chains. Ethical considerations, including bias mitigation and data protection, are taken into account to ensure fair and transparent AI practices. In addition, the paper discusses the need to educate the workforce on how to manage new AI-driven processes and the long-term strategic benefits of adopting LLMs. Strategic recommendations for SCM professionals include investing in high-quality data management, promoting cross-functional collaboration, and aligning LLM initiatives with overall business goals. The findings highlight the potential of LLMs to drive innovation, sustainability, and competitive advantage in the ever-changing supply chain management landscape.