相关论文: Practical Benefits of Feature Feedback Under Distr…

Physiological signals hold immense potential for ubiquitous emotion monitoring, presenting numerous applications in emotion recognition. However, harnessing this potential is hindered by significant challenges, particularly in the…

In this work, we propose and study annotated code search: the retrieval of code snippets paired with brief descriptions of their intent using natural language queries. On three benchmark datasets, we investigate how code retrieval systems…

Sample efficiency is a crucial property of language models with practical implications for training efficiency. In real-world text, information follows a long-tailed distribution. Yet, we expect models to learn and recall frequent and…

Shared artifacts and environments play a prominent role in shaping the collaboration between their users. This article describes this role and explains how annotations can provide a bridge between direct communication and collaboration…

While supervised learning has achieved significant success in computer vision tasks, acquiring high-quality annotated data remains a bottleneck. This paper explores both scholarly and non-scholarly works in AI-assistive deep learning image…

As the capabilities of large-scale pre-trained models evolve, understanding the determinants of their outputs becomes more important. Feature attribution aims to reveal which parts of the input elements contribute the most to model outputs.…

Incrementality is ubiquitous in human-human interaction and beneficial for human-computer interaction. It has been a topic of research in different parts of the NLP community, mostly with focus on the specific topic at hand even though…

What properties of a first-order search space support/hinder inference? What kinds of facts would be most effective to learn? Answering these questions is essential for understanding the dynamics of deductive reasoning and creating…

In Reinforcement Learning from Human Feedback (RLHF), it is crucial to learn suitable reward models from human feedback to align large language models (LLMs) with human intentions. However, human feedback can often be noisy, inconsistent,…

State abstraction has been an essential tool for dramatically improving the sample efficiency of reinforcement-learning algorithms. Indeed, by exposing and accentuating various types of latent structure within the environment, different…

Affective computing strives to unveil the unknown relationship between affect elicitation, manifestation of affect and affect annotations. The ground truth of affect, however, is predominately attributed to the affect labels which…

In this paper, we explore Annotation Artifacts - the phenomena wherein large pre-trained NLP models achieve high performance on benchmark datasets but do not actually "solve" the underlying task and instead rely on some dataset artifacts…

Interpretability is an important area of research for safe deployment of machine learning systems. One particular type of interpretability method attributes model decisions to input features. Despite active development, quantitative…

Conversational analysis systems are trained using noisy human labels and often require heavy preprocessing during multi-modal feature extraction. Using noisy labels in single-task learning increases the risk of over-fitting. Auxiliary tasks…

In this paper, we have defined a novel task of affective feedback synthesis that deals with generating feedback for input text & corresponding image in a similar way as humans respond towards the multimodal data. A feedback synthesis system…

Saliency post-hoc explainability methods are important tools for understanding increasingly complex NLP models. While these methods can reflect the model's reasoning, they may not align with human intuition, making the explanations not…

Tool-augmented language models, equipped with retrieval, memory, or external APIs, are reshaping AI, yet their theoretical advantages remain underexplored. In this paper, we address this question by demonstrating the benefits of in-tool…

Designing an effective reward function has long been a challenge in reinforcement learning, particularly for complex tasks in unstructured environments. To address this, various learning paradigms have emerged that leverage different forms…

Feature selection can facilitate the learning of mixtures of discrete random variables as they arise, e.g. in crowdsourcing tasks. Intuitively, not all workers are equally reliable but, if the less reliable ones could be eliminated, then…

Our research demonstrates the significant benefits of using fine-tuning with explanations to enhance the performance of language models. Unlike prompting, which maintains the model's parameters, fine-tuning allows the model to learn and…