Addressing the challenge of generating personalized feedback for programming assignments is demanding due to several factors, like the complexity of code syntax or different ways to correctly solve a task. In this experimental study, we automated the process of feedback generation by employing OpenAI's GPT-3.5 model to generate personalized hints for students solving programming assignments on an automated assessment platform. Students rated the usefulness of GPT-generated hints positively. The experimental group (with GPT hints enabled) relied less on the platform's regular feedback but performed better in terms of percentage of successful submissions across consecutive attempts for tasks, where GPT hints were enabled. For tasks where the GPT feedback was made unavailable, the experimental group needed significantly less time to solve assignments. Furthermore, when GPT hints were unavailable, students in the experimental condition were initially less likely to solve the assignment correctly. This suggests potential over-reliance on GPT-generated feedback. However, students in the experimental condition were able to correct reasonably rapidly, reaching the same percentage correct after seven submission attempts. The availability of GPT hints did not significantly impact students' affective state.

Continual learning (CL) has emerged as an important avenue of research in recent years, at the intersection of Machine Learning (ML) and Human-Robot Interaction (HRI), to allow robots to continually learn in their environments over long-term interactions with humans. Most research in continual learning, however, has been robot-centered to develop continual learning algorithms that can quickly learn new information on static datasets. In this paper, we take a human-centered approach to continual learning, to understand how humans teach continual learning robots over the long term and if there are variations in their teaching styles. We conducted an in-person study with 40 participants that interacted with a continual learning robot in 200 sessions. In this between-participant study, we used two different CL models deployed on a Fetch mobile manipulator robot. An extensive qualitative and quantitative analysis of the data collected in the study shows that there is significant variation among the teaching styles of individual users indicating the need for personalized adaptation to their distinct teaching styles. The results also show that although there is a difference in the teaching styles between expert and non-expert users, the style does not have an effect on the performance of the continual learning robot. Finally, our analysis shows that the constrained experimental setups that have been widely used to test most continual learning techniques are not adequate, as real users interact with and teach continual learning robots in a variety of ways. Our code is available at https://github.com/aliayub7/cl_hri.

Large language models show impressive results on few-shot NLP tasks. However, these models are memory and computation-intensive. Meta-training allows one to leverage smaller models for few-shot generalization in a domain-general and task-agnostic manner; however, these methods alone results in models that may not have sufficient parameterization or knowledge to adapt quickly to a large variety of tasks. To overcome this issue, we propose meta-training with demonstration retrieval, where we use a dense passage retriever to retrieve semantically similar labeled demonstrations to each example for more varied supervision. By separating external knowledge from model parameters, we can use meta-training to train parameter-efficient models that generalize well on a larger variety of tasks. We construct a meta-training set from UnifiedQA and CrossFit, and propose a demonstration bank based on UnifiedQA tasks. To our knowledge, our work is the first to combine retrieval with meta-training, to use DPR models to retrieve demonstrations, and to leverage demonstrations from many tasks simultaneously, rather than randomly sampling demonstrations from the training set of the target task. Our approach outperforms a variety of targeted parameter-efficient and retrieval-augmented few-shot methods on QA, NLI, and text classification tasks (including SQuAD, QNLI, and TREC). Our approach can be meta-trained and fine-tuned quickly on a single GPU.

Classifier-Free Guidance (CFG) [37] has recently emerged in text-to-image generation as a lightweight technique to encourage prompt-adherence in generations. In this work, we demonstrate that CFG can be used broadly as an inference-time technique in pure language modeling. We show that CFG (1) improves the performance of Pythia, GPT-2 and LLaMA-family models across an array of tasks: Q&A, reasoning, code generation, and machine translation, achieving SOTA on LAMBADA with LLaMA-7B over PaLM-540B; (2) brings improvements equivalent to a model with twice the parameter-count; (3) can stack alongside other inference-time methods like Chain-of-Thought and Self-Consistency, yielding further improvements in difficult tasks; (4) can be used to increase the faithfulness and coherence of assistants in challenging form-driven and content-driven prompts: in a human evaluation we show a 75% preference for GPT4All using CFG over baseline.

Reliable real-world deployment of reinforcement learning (RL) methods requires a nuanced understanding of their strengths and weaknesses and how they compare to those of humans. Human-machine systems are becoming more prevalent and the design of these systems relies on a task-oriented understanding of both human learning (HL) and RL. Thus, an important line of research is characterizing how the structure of a learning task affects learning performance. While increasingly complex benchmark environments have led to improved RL capabilities, such environments are difficult to use for the dedicated study of task structure. To address this challenge we present a learning environment built to support rigorous study of the impact of task structure on HL and RL. We demonstrate the environment's utility for such study through example experiments in task structure that show performance differences between humans and RL algorithms.

University admission at many highly selective institutions uses a holistic review process, where all aspects of the application, including protected attributes (e.g., race, gender), grades, essays, and recommendation letters are considered, to compose an excellent and diverse class. In this study, we empirically evaluate how influential protected attributes are for predicting admission decisions using a machine learning (ML) model, and in how far textual information (e.g., personal essay, teacher recommendation) may substitute for the loss of protected attributes in the model. Using data from 14,915 applicants to an undergraduate admission office at a selective U.S. institution in the 2022-2023 cycle, we find that the exclusion of protected attributes from the ML model leads to substantially reduced admission-prediction performance. The inclusion of textual information via both a TF-IDF representation and a Latent Dirichlet allocation (LDA) model partially restores model performance, but does not appear to provide a full substitute for admitting a similarly diverse class. In particular, while the text helps with gender diversity, the proportion of URM applicants is severely impacted by the exclusion of protected attributes, and the inclusion of new attributes generated from the textual information does not recover this performance loss.

We evaluated the capability of a generative pre-trained transformer (GPT-4) to automatically generate high-quality learning objectives (LOs) in the context of a practically oriented university course on Artificial Intelligence. Discussions of opportunities (e.g., content generation, explanation) and risks (e.g., cheating) of this emerging technology in education have intensified, but to date there has not been a study of the models' capabilities in supporting the course design and authoring of LOs. LOs articulate the knowledge and skills learners are intended to acquire by engaging with a course. To be effective, LOs must focus on what students are intended to achieve, focus on specific cognitive processes, and be measurable. Thus, authoring high-quality LOs is a challenging and time consuming (i.e., expensive) effort. We evaluated 127 LOs that were automatically generated based on a carefully crafted prompt (detailed guidelines on high-quality LOs authoring) submitted to GPT-4 for conceptual modules and projects of an AI Practitioner course. We analyzed the generated LOs if they follow certain best practices such as beginning with action verbs from Bloom's taxonomy in regards to the level of sophistication intended. Our analysis showed that the generated LOs are sensible, properly expressed (e.g., starting with an action verb), and that they largely operate at the appropriate level of Bloom's taxonomy, respecting the different nature of the conceptual modules (lower levels) and projects (higher levels). Our results can be leveraged by instructors and curricular designers wishing to take advantage of the state-of-the-art generative models to support their curricular and course design efforts.

Many techniques in machine learning attempt explicitly or implicitly to infer a low-dimensional manifold structure of an underlying physical phenomenon from measurements without an explicit model of the phenomenon or the measurement apparatus. This paper presents a cautionary tale regarding the discrepancy between the geometry of measurements and the geometry of the underlying phenomenon in a benign setting. The deformation in the metric illustrated in this paper is mathematically straightforward and unavoidable in the general case, and it is only one of several similar effects. While this is not always problematic, we provide an example of an arguably standard and harmless data processing procedure where this effect leads to an incorrect answer to a seemingly simple question. Although we focus on manifold learning, these issues apply broadly to dimensionality reduction and unsupervised learning.

We investigate how to enhance answer precision in frequently asked questions posed by distributed users using cloud-based Large Language Models (LLMs). Our study focuses on a typical situations where users ask similar queries that involve identical mathematical reasoning steps and problem-solving procedures. Due to the unsatisfactory accuracy of LLMs' zero-shot prompting with standalone questions, we propose to improve the distributed synonymous questions using Self-Consistency (SC) and Chain-of-Thought (CoT) techniques. Specifically, we first retrieve synonymous questions from a crowd-sourced database and create a federated question pool. We call these federated synonymous questions with the same or different parameters SP-questions or DP-questions, respectively. We refer to our methods as Fed-SP-SC and Fed-DP-CoT, which can generate significantly more accurate answers for all user queries without requiring sophisticated model-tuning. Through extensive experiments, we demonstrate that our proposed methods can significantly enhance question accuracy by fully exploring the synonymous nature of the questions and the consistency of the answers.

Mixed Integer programs (MIPs) are typically solved by the Branch-and-Bound algorithm. Recently, Learning to imitate fast approximations of the expert strong branching heuristic has gained attention due to its success in reducing the running time for solving MIPs. However, existing learning-to-branch methods assume that the entire training data is available in a single session of training. This assumption is often not true, and if the training data is supplied in continual fashion over time, existing techniques suffer from catastrophic forgetting. In this work, we study the hitherto unexplored paradigm of Lifelong Learning to Branch on Mixed Integer Programs. To mitigate catastrophic forgetting, we propose LIMIP, which is powered by the idea of modeling an MIP instance in the form of a bipartite graph, which we map to an embedding space using a bipartite Graph Attention Network. This rich embedding space avoids catastrophic forgetting through the application of knowledge distillation and elastic weight consolidation, wherein we learn the parameters key towards retaining efficacy and are therefore protected from significant drift. We evaluate LIMIP on a series of NP-hard problems and establish that in comparison to existing baselines, LIMIP is up to 50% better when confronted with lifelong learning.