Related papers: Predictive Analytics for Collaborators Answers, Co…

We propose BlackOut, an approximation algorithm to efficiently train massive recurrent neural network language models (RNNLMs) with million word vocabularies. BlackOut is motivated by using a discriminative loss, and we describe a new…

One of the most challenging problems facing NLP today is evaluation. Some of the most pressing issues pertain to benchmark saturation, data contamination, and diversity in the quality of test examples. To address these concerns, we propose…

For tasks like code synthesis from natural language, code retrieval, and code summarization, data-driven models have shown great promise. However, creating these models require parallel data between natural language (NL) and code with…

We introduce SWE-PRBench, a benchmark of 350 pull requests with human-annotated ground truth for evaluating AI code review quality. Evaluated against an LLM-as-judge framework validated at kappa=0.75, 8 frontier models detect only 15-31% of…

Recent neural models of code, such as OpenAI Codex and AlphaCode, have demonstrated remarkable proficiency at code generation due to the underlying attention mechanism. However, it often remains unclear how the models actually process code,…

Recent approaches to training algorithm selectors in the black-box optimisation domain have advocated for the use of training data that is algorithm-centric in order to encapsulate information about how an algorithm performs on an instance,…

Student repetition in secondary education imposes significant resource burdens, particularly in resource-constrained contexts. Addressing this challenge, this study introduces a unified machine learning framework that simultaneously…

We investigate the convergence and convergence rate of stochastic training algorithms for Neural Networks (NNs) that have been inspired by Dropout (Hinton et al., 2012). With the goal of avoiding overfitting during training of NNs, dropout…

The adoption of Large Language Models (LLMs) for code generation in data science offers substantial potential for enhancing tasks such as data manipulation, statistical analysis, and visualization. However, the effectiveness of these models…

Deep learning based recommendation systems form the backbone of most personalized cloud services. Though the computer architecture community has recently started to take notice of deep recommendation inference, the resulting solutions have…

Cyberbullying is a prevalent and growing social problem due to the surge of social media technology usage. Minorities, women, and adolescents are among the common victims of cyberbullying. Despite the advancement of NLP technologies, the…

Classical optimization algorithms--hill climbing, simulated annealing, population-based methods--generate candidate solutions via random perturbations. We replace the random proposal generator with an LLM agent that reasons about evaluation…

Collaborative bandit learning, i.e., bandit algorithms that utilize collaborative filtering techniques to improve sample efficiency in online interactive recommendation, has attracted much research attention as it enjoys the best of both…

Measuring collaborative problem solving (CPS) synergy remains challenging in learning analytics, as classical manual coding cannot capture emergent system-level dynamics. This study introduces a computational framework that integrates…

A major challenge in training deep neural networks is overfitting, i.e. inferior performance on unseen test examples compared to performance on training examples. To reduce overfitting, stochastic regularization methods have shown superior…

Programming assistants powered by large language models have improved dramatically, yet existing benchmarks still evaluate them in narrow code-generation settings. Recent efforts such as InfiBench and StackEval rely on Stack Overflow…

Understanding why students stopout will help in understanding how students learn in MOOCs. In this report, part of a 3 unit compendium, we describe how we build accurate predictive models of MOOC student stopout. We document a scalable,…

Deep neural networks (DNNs) have become integral to a wide range of scientific and practical applications due to their flexibility and strong predictive performance. Despite their accuracy, however, DNNs frequently exhibit poor calibration,…

Ensembles are popular methods for solving practical supervised learning problems. They reduce the risk of having underperforming models in production-grade software. Although critical, methods for learning heterogeneous regression ensembles…

Dropout is a widely used regularization trick to resolve the overfitting issue in large feedforward neural networks trained on a small dataset, which performs poorly on the held-out test subset. Although the effectiveness of this…