Related papers: Bayesian WeakS-to-Strong from Text Classification …

Recent advancements in large language models (LLMs) have led to their increased application across various tasks, with reinforcement learning from human feedback (RLHF) being a crucial part of their training to align responses with user…

Learning from imbalanced data is one of the most significant challenges in real-world classification tasks. In such cases, neural networks performance is substantially impaired due to preference towards the majority class. Existing…

We state the problem of inverse reinforcement learning in terms of preference elicitation, resulting in a principled (Bayesian) statistical formulation. This generalises previous work on Bayesian inverse reinforcement learning and allows us…

We present an approach for weakly supervised learning of human actions. Given a set of videos and an ordered list of the occurring actions, the goal is to infer start and end frames of the related action classes within the video and to…

We consider problems of making sequences of decisions to accomplish tasks, interacting via the medium of language. These problems are often tackled with reinforcement learning approaches. We find that these models do not generalize well…

We present a semantics of a probabilistic while-language with soft conditioning and continuous distributions which handles programs diverging with positive probability. To this end, we extend the probabilistic guarded command language…

Well-designed prompts can guide text-to-image models to generate amazing images. However, the performant prompts are often model-specific and misaligned with user input. Instead of laborious human engineering, we propose prompt adaptation,…

Multimodal models often over-rely on dominant modalities, failing to achieve optimal performance. While prior work focuses on modifying training objectives or optimization procedures, data-centric solutions remain underexplored. We propose…

Despite large-scale pre-trained language models have achieved striking results for text classificaion, recent work has raised concerns about the challenge of shortcut learning. In general, a keyword is regarded as a shortcut if it creates a…

We study the problem of generating counterfactual text for a classifier as a means for understanding and debugging classification. Given a textual input and a classification model, we aim to minimally alter the text to change the model's…

While perception tasks such as visual object recognition and text understanding play an important role in human intelligence, the subsequent tasks that involve inference, reasoning and planning require an even higher level of intelligence.…

The burgeoning capabilities of large language models (LLMs) have underscored the need for alignment to ensure these models act in accordance with human values and intentions. Existing alignment frameworks present constraints either in the…

The large size and complex decision mechanisms of state-of-the-art text classifiers make it difficult for humans to understand their predictions, leading to a potential lack of trust by the users. These issues have led to the adoption of…

Weak supervision combines the advantages of training on real data with the ability to exploit signal properties. However, training a neural network using weak supervision often requires an excessive amount of signal data, which severely…

This paper proposes a novel framework to reinforce classification models using language-guided generated counterfactual images. Deep learning classification models are often trained using datasets that mirror real-world scenarios. In this…

Training deep neural networks requires many training samples, but in practice, training labels are expensive to obtain and may be of varying quality, as some may be from trusted expert labelers while others might be from heuristics or other…

Generic generation and manipulation of text is challenging and has limited success compared to recent deep generative modeling in visual domain. This paper aims at generating plausible natural language sentences, whose attributes are…

Despite their outstanding performance, large language models (LLMs) suffer notorious flaws related to their preference for simple, surface-level textual relations over full semantic complexity of the problem. This proposal investigates a…

The meteoric rise in text generation capability has been accompanied by parallel growth in interest in machine-generated text detection: the capability to identify whether a given text was generated using a model or written by a person.…

Large language models (LLMs) are revolutionizing every aspect of society. They are increasingly used in problem-solving tasks to substitute human assessment and reasoning. LLMs are trained on what humans write and are thus exposed to human…