Related papers: QADYNAMICS: Training Dynamics-Driven Synthetic QA …
While conversing with chatbots, humans typically tend to ask many questions, a significant portion of which can be answered by referring to large-scale knowledge graphs (KG). While Question Answering (QA) and dialog systems have been…
Commonsense reasoning is a critical aspect of human communication. Despite recent advances in conversational AI driven by large language models, commonsense reasoning remains a challenging task. In this work, we introduce SYNDICOM - a…
The ability of generative language models (GLMs) to generate text has improved considerably in the last few years, enabling their use for generative data augmentation. In this work, we propose CONDA, an approach to further improve GLMs'…
This paper provides preliminary results on exploring the task of performing turn-level data augmentation for dialogue system based on different types of commonsense relationships, and the automatic evaluation of the generated synthetic…
Our goal is a teachable reasoning system for question-answering (QA), where a user can interact with faithful answer explanations, and correct its errors so that the system improves over time. Our approach is to augment a QA model with a…
As question answering (QA) systems advance alongside the rapid evolution of foundation models, the need for robust, adaptable, and large-scale evaluation benchmarks becomes increasingly critical. Traditional QA benchmarks are often static…
Recently, dataset-generation-based zero-shot learning has shown promising results by training a task-specific model with a dataset synthesized from large pre-trained language models (PLMs). The final task-specific model often achieves…
Question Answering (QA) datasets have been instrumental in developing and evaluating Large Language Model (LLM) capabilities. However, such datasets are scarce for languages other than English due to the cost and difficulties of collection…
Cognitive diagnosis is a crucial task in computational education, aimed at evaluating students' proficiency levels across various knowledge concepts through exercises. Current models, however, primarily rely on students' answered exercises,…
Large language models (LLMs), while increasingly used in domains requiring factual rigor, often display a troubling behavior: sycophancy, the tendency to align with user beliefs regardless of correctness. This tendency is reinforced by…
The information in tables can be an important complement to text, making table-based question answering (QA) systems of great value. The intrinsic complexity of handling tables often adds an extra burden to both model design and data…
We equip a smaller Language Model to generalise to answering challenging compositional questions that have not been seen in training. To do so we propose a combination of multitask supervised pretraining on up to 93 tasks designed to…
In this paper, we present an approach for designing correct-by-design controllers for cyber-physical systems composed of multiple dynamically interconnected uncertain systems. We consider networked discrete-time uncertain nonlinear systems…
Question answering (QA) is a critical task for speech-based retrieval from knowledge sources, by sifting only the answers without requiring to read supporting documents. Specifically, open-domain QA aims to answer user questions on…
Question and answer generation is a data augmentation method that aims to improve question answering (QA) models given the limited amount of human labeled data. However, a considerable gap remains between synthetic and human-generated…
In spoken question answering, QA systems are designed to answer questions from contiguous text spans within the related speech transcripts. However, the most natural way that human seek or test their knowledge is via human conversations.…
This study explores the potential of using training dynamics as an automated alternative to human annotation for evaluating the quality of training data. The framework used is Data Maps, which classifies data points into categories such as…
Synthetic data has been proposed as a solution to address the issue of high-quality data scarcity in the training of large language models (LLMs). Studies have shown that synthetic data can effectively improve the performance of LLMs on…
This paper introduces zero-shot dialog generation (ZSDG), as a step towards neural dialog systems that can instantly generalize to new situations with minimal data. ZSDG enables an end-to-end generative dialog system to generalize to a new…
There have been growing concerns regarding the out-of-domain generalization ability of natural language processing (NLP) models, particularly in question-answering (QA) tasks. Current synthesized data augmentation methods for QA are…