Related papers: Reducing the Cost: Cross-Prompt Pre-Finetuning for…
Reinforcement learning enhances the reasoning capabilities of large language models but often involves high computational costs due to rollout-intensive optimization. Online prompt selection presents a plausible solution by prioritizing…
Automated speaking assessment (ASA) typically involves automatic speech recognition (ASR) and hand-crafted feature extraction from the ASR transcript of a learner's speech. Recently, self-supervised learning (SSL) has shown stellar…
Evaluating student responses, from long essays to short factual answers, is a key challenge in educational NLP. Automated Essay Scoring (AES) focuses on holistic writing qualities such as coherence and argumentation, while Automatic Short…
Answer Sentence Selection (AS2) is a core component for building an accurate Question Answering pipeline. AS2 models rank a set of candidate sentences based on how likely they answer a given question. The state of the art in AS2 exploits…
Significant progress has been made in deep-learning based Automatic Essay Scoring (AES) systems in the past two decades. However, little research has been put to understand and interpret the black-box nature of these deep-learning based…
Self-supervised learning (SSL) has allowed substantial progress in Automatic Speech Recognition (ASR) performance in low-resource settings. In this context, it has been demonstrated that larger self-supervised feature extractors are crucial…
While the self-attention mechanism has been widely used in a wide variety of tasks, it has the unfortunate property of a quadratic cost with respect to the input length, which makes it difficult to deal with long inputs. In this paper, we…
It is common knowledge that the quantity and quality of the training data play a significant role in the creation of a good machine learning model. In this paper, we take it one step further and demonstrate that the way the training…
Prompt optimization has become a practical way to improve the performance of Large Language Models (LLMs) without retraining. However, most existing frameworks treat evaluation as a black box, relying solely on outcome scores without…
Reinforcement learning with verifiable rewards has significantly advanced reasoning in large language models (LLMs), but such signals remain coarse, offering only binary correctness feedback. This limitation often results in inefficiencies,…
This study centers on overcoming the challenge of selecting the best annotators for each query in Active Learning (AL), with the objective of minimizing misclassifications. AL recognizes the challenges related to cost and time when…
Although automatic speech recognition (ASR) task has gained remarkable success by sequence-to-sequence models, there are two main mismatches between its training and testing that might lead to performance degradation: 1) The typically used…
In large language models (LLM)-based recommendation systems (LLM-RSs), accurately predicting user preferences by leveraging the general knowledge of LLMs is possible without requiring extensive training data. By converting recommendation…
Answer Sentence Selection (AS2) is an efficient approach for the design of open-domain Question Answering (QA) systems. In order to achieve low latency, traditional AS2 models score question-answer pairs individually, ignoring any…
Speech recognition and speech synthesis models are typically trained separately, each with its own set of learning objectives, training data, and model parameters, resulting in two distinct large networks. We propose a parameter-efficient…
Research on holistic Automated Essay Scoring (AES) is long-dated; yet, there is a notable lack of attention for assessing essays according to individual traits. In this work, we propose TRATES, a novel trait-specific and rubric-based…
A binary decision task, like yes-no questions or answer verification, reflects a significant real-world scenario such as where users look for confirmation about the correctness of their decisions on specific issues. In this work, we observe…
Large language models exhibit strong reasoning capabilities, yet often rely on shortcuts such as surface pattern matching and answer memorization rather than genuine logical inference. We propose Shortcut-Aware Reasoning Training (SART), a…
Pre-trained large language models can perform natural language processing downstream tasks by conditioning on human-designed prompts. However, a prompt-based approach often requires "prompt engineering" to design different prompts,…
Automatic essay scoring (AES) refers to the process of scoring free text responses to given prompts, considering human grader scores as the gold standard. Writing such essays is an essential component of many language and aptitude exams.…