Related papers: Efficient Story Point Estimation With Comparative …

Effective coordination of agents actions in partially-observable domains is a major challenge of multi-agent systems research. To address this, many researchers have developed techniques that allow the agents to make decisions based on…

Interactive reinforcement learning has shown promise in learning complex robotic tasks. However, the process can be human-intensive due to the requirement of a large amount of interactive feedback. This paper presents a new method that uses…

Pre-trained vision and language models such as CLIP have witnessed remarkable success in connecting images and texts with a primary focus on English texts. Despite recent efforts to extend CLIP to support other languages, disparities in…

Most machine learning techniques are based upon statistical learning theory, often simplified for the sake of computing speed. This paper is focused on the uncertainty aspect of mathematical modeling in machine learning. Regression analysis…

Recent prompt-based approaches allow pretrained language models to achieve strong performances on few-shot finetuning by reformulating downstream tasks as a language modeling problem. In this work, we demonstrate that, despite its…

Learning to rank is a key component of many e-commerce search engines. In learning to rank, one is interested in optimising the global ordering of a list of items according to their utility for users.Popular approaches learn a scoring…

Zero-shot text classification typically relies on prompt engineering, but the inherent prompt brittleness of large language models undermines its reliability. Minor changes in prompt can cause significant discrepancies in model performance.…

Learning under one-sided feedback (i.e., where we only observe the labels for examples we predicted positively on) is a fundamental problem in machine learning -- applications include lending and recommendation systems. Despite this, there…

The amount of dialogue history to include in a conversational agent is often underestimated and/or set in an empirical and thus possibly naive way. This suggests that principled investigations into optimal context windows are urgently…

Large language models (LMs) are typically adapted to improve performance on new contexts (\eg text prompts that define new tasks or domains) through fine-tuning or prompting. However, there is an accuracy compute tradeoff -- fine-tuning…

Machine learning and deep learning models are pivotal in educational contexts, particularly in predicting student success. Despite their widespread application, a significant gap persists in comprehending the factors influencing these…

While reaching for NLP systems that maximize accuracy, other important metrics of system performance are often overlooked. Prior models are easily forgotten despite their possible suitability in settings where large computing resources are…

Reinforcement learning with evaluation metrics as rewards is widely used to enhance specific capabilities of language models. However, for tasks such as factually consistent summarisation, existing metrics remain underdeveloped, limiting…

Multilingual pretrained language models (MPLMs) have demonstrated substantial performance improvements in zero-shot cross-lingual transfer across various natural language understanding tasks by finetuning MPLMs on task-specific labelled…

Selecting an appropriate pre-trained source model is a critical, yet computationally expensive, task in transfer learning. Model Transferability Estimation (MTE) methods address this by providing efficient proxy metrics to rank models…

The acquisition of complex knowledge and competences raises difficult challenges for the supporting tools within the corporate environment, which digital storytelling presents a potential solution. Traditionally, a driving goal of digital…

Modern language models often exhibit powerful but brittle behavior, leading to the development of larger and more diverse benchmarks to reliably assess their behavior. Here, we suggest that model performance can be benchmarked and…

The superior performance of some of today's state-of-the-art deep learning models is to some extent owed to extensive (self-)supervised contrastive pretraining on large-scale datasets. In contrastive learning, the network is presented with…

With the emergence of large-scale pre-trained neural networks, methods to adapt such "foundation" models to data-limited downstream tasks have become a necessity. Fine-tuning, preference optimization, and transfer learning have all been…

Language model pretraining involves training on extensive corpora, where data quality plays a pivotal role. In this work, we aim to directly estimate the contribution of data during pretraining and select pretraining data in an efficient…