Genetic Algorithms have established their capability for solving many complex optimization problems. Even as good solutions are produced, the user's understanding of a problem is not necessarily improved, which can lead to a lack of confidence in the results. To mitigate this issue, explainability aims to give insight to the user by presenting them with the knowledge obtained by the algorithm. In this paper we introduce Partial Solutions in order to improve the explainability of solutions to combinatorial optimization problems. Partial Solutions represent beneficial traits found by analyzing a population, and are presented to the user for explainability, but also provide an explicit model from which new solutions can be generated. We present an algorithm that assembles a collection of Partial Solutions chosen to strike a balance between high fitness, simplicity and atomicity. Experiments with standard benchmarks show that the proposed algorithm is able to find Partial Solutions which improve explainability at reasonable computational cost without affecting search performance.

The growing enrollments in computer science courses and increase in class sizes necessitate scalable, automated tutoring solutions to adequately support student learning. While Large Language Models (LLMs) like GPT-3.5 have demonstrated potential in assisting students through question-answering, educators have significant concerns about students misusing LLMs or LLMs misleading students with inaccurate answers. This paper introduces CourseAssist, a novel LLM-based tutoring system tailored for computer science education. Unlike generic LLM systems, CourseAssist leverages retrieval-augmented generation along with user intent classification and post-processing to ensure that responses align with specific course learning goals, thereby addressing the pedagogical appropriateness of LLMs in educational settings. I evaluate CourseAssist against a baseline of GPT 3.5 using a dataset of 50 question-answer pairs from a programming languages course, focusing on the criteria of usefulness, accuracy, and pedagogical appropriateness. Evaluation results show that CourseAssist significantly outperforms the baseline, demonstrating its potential to serve as an effective learning assistant. This work not only highlights the importance of deliberate design considerations in LLM-based educational tools but also opens up avenues for future research, particularly in understanding user interactions with such systems in real-world scenarios and integrating human educators into LLM-based tutoring systems.

Recent large language models (LLMs) have shown indications of mathematical reasoning ability. However it has not been clear how they would fare on more challenging competition-level problems. And while self-generated verbalizations of intermediate reasoning steps (i.e., chain-of-thought prompting) have been shown to be helpful, whether LLMs can make use of helpful side information such as problem-specific hints has not been investigated before. In this paper, we propose a challenging benchmark dataset for enabling such analyses. The Concept and Hint-Annotated Math Problems (CHAMP) consists of high school math competition problems, annotated with concepts, or general math facts, and hints, or problem-specific tricks. These annotations allow us to explore the effects of additional information, such as relevant hints, misleading concepts, or related problems. This benchmark is difficult, with the best model only scoring 58.1% in standard settings. With concepts and hints, performance sometimes improves, indicating that some models can make use of such side information. We further annotate model-generated solutions for their correctness. Using this corpus, we find that models often arrive at the correct final answer through wrong reasoning steps. In addition, we test whether models are able to verify these solutions, and find that most models struggle. The dataset and code are available on the project website.

Generative AI like ChatGPT is truly exciting, and it's easy to be seduced by the technology's potential to produce, well, almost any sort of output. The opportunity in generative AI is enormous but requires careful analysis of where the best applications lie. Healthcare, in particular, requires this assessment – this isn't an industry known for fast change, and the risks of inappropriately deploying new technology can be huge. For instance, consider the hype around IBM's Watson Health a few years ago; this AI was going to figure out complex cancers! It didn't, and it was sold off cheaply in parts last year. This includes what people need to stop doing in order to start embracing the new solution.

Machine learned models often must abide by certain requirements (e.g., fairness or legal). This has spurred interested in developing approaches that can provably verify whether a model satisfies certain properties. This paper introduces a generic algorithm called Veritas that enables tackling multiple different verification tasks for tree ensemble models like random forests (RFs) and gradient boosting decision trees (GBDTs). This generality contrasts with previous work, which has focused exclusively on either adversarial example generation or robustness checking. Veritas formulates the verification task as a generic optimization problem and introduces a novel search space representation. Veritas offers two key advantages. First, it provides anytime lower and upper bounds when the optimization problem cannot be solved exactly. In contrast, many existing methods have focused on exact solutions and are thus limited by the verification problem being NP-complete. Second, Veritas produces full (bounded suboptimal) solutions that can be used to generate concrete examples. We experimentally show that Veritas outperforms the previous state of the art by (a) generating exact solutions more frequently, (b) producing tighter bounds when (a) is not possible, and (c) offering orders of magnitude speed ups. Subsequently, Veritas enables tackling more and larger real-world verification scenarios.