相关论文: Generating Plausible Distractors for Multiple-Choi…

Denoising diffusion probabilistic models (DDPMs) are a recent family of generative models that achieve state-of-the-art results. In order to obtain class-conditional generation, it was suggested to guide the diffusion process by gradients…

A machine learning model, under the influence of observed or unobserved confounders in the training data, can learn spurious correlations and fail to generalize when deployed. For image classifiers, augmenting a training dataset using…

The problem of designing learners that provide guarantees that their predictions are provably correct is of increasing importance in machine learning. However, learning theoretic guarantees have only been considered in very specific…

Previous multi-task dense prediction studies developed complex pipelines such as multi-modal distillations in multiple stages or searching for task relational contexts for each task. The core insight beyond these methods is to maximize the…

Mathematical reasoning presents a significant challenge for Large Language Models (LLMs) as it requires ensuring the correctness of each reasoning step. Researchers have been strengthening the mathematical reasoning abilities of LLMs…

Most of the existing works for dialogue generation are data-driven models trained directly on corpora crawled from websites. They mainly focus on improving the model architecture to produce better responses but pay little attention to…

Existing text generation methods tend to produce repeated and "boring" expressions. To tackle this problem, we propose a new text generation model, called Diversity-Promoting Generative Adversarial Network (DP-GAN). The proposed model…

As creative writing tasks do not have singular correct answers, large language models (LLMs) trained to perform these tasks should be able to generate diverse valid outputs. However, LLM post-training often focuses on improving generation…

Discriminative learning machines often need a large set of labeled samples for training. Active learning (AL) settings assume that the learner has the freedom to ask an oracle to label its desired samples. Traditional AL algorithms…

An important goal of online platforms is to enable content discovery, i.e. allow users to find a catalog entity they were not familiar with. A pre-requisite to discover an entity, e.g. a book, with a search engine is that the entity is…

The increase in academic dishonesty cases among college students has raised concern, particularly due to the shift towards online learning caused by the pandemic. We aim to develop and implement a method capable of generating tailored…

We address the product question generation task. For a given product description, our goal is to generate questions that reflect potential user information needs that are either missing or not well covered in the description. Moreover, we…

When students are unsure of the correct answer to a multiple-choice question (MCQ), guessing is common practice. The availability heuristic, proposed by A. Tversky and D. Kahneman in 1973, suggests that the ease with which relevant…

Generating high quality question-answer pairs is a hard but meaningful task. Although previous works have achieved great results on answer-aware question generation, it is difficult to apply them into practical application in the education…

The development of Automatic Question Generation (QG) models has the potential to significantly improve educational practices by reducing the teacher workload associated with creating educational content. This paper introduces a novel…

Machine learning pipelines often rely on optimization procedures to make discrete decisions (e.g., sorting, picking closest neighbors, or shortest paths). Although these discrete decisions are easily computed, they break the…

Technology enables a more sustainable and universally accessible educational model. However, technology has brought a paradox into students' lives: it helps them engage in learning activities, but it is also a source of distraction. During…

An advantage of Large Language Models (LLMs) is their contextualization capability - providing different responses based on student inputs like solution strategy or prior discussion, to potentially better engage students than standard…

Neural dialogue response generation has gained much popularity in recent years. Maximum Likelihood Estimation (MLE) objective is widely adopted in existing dialogue model learning. However, models trained with MLE objective function are…

The remarkable success of contrastive-learning-based multimodal models has been greatly driven by training on ever-larger datasets with expensive compute consumption. Sample selection as an alternative efficient paradigm plays an important…