Related papers: Value Profiles for Encoding Human Variation

Human decision making can be challenging to predict because decisions are affected by a number of complex factors. Adding to this complexity, decision-making processes can differ considerably between individuals, and methods aimed at…

Large language models are increasingly used to represent human opinions, values, or beliefs, and their steerability towards these ideals is an active area of research. Existing work focuses predominantly on aligning marginal response…

Recent calls for pluralistic alignment emphasize that AI systems should address the diverse needs of all people. Yet, efforts in this space often require sorting people into fixed buckets of pre-specified diversity-defining dimensions…

We present a study on how and where personas -- defined by distinct sets of human characteristics, values, and beliefs -- are encoded in the representation space of large language models (LLMs). Using a range of dimension reduction and…

People can view the same image differently: they focus on different regions, objects, and details in varying orders and describe them in distinct linguistic styles. This leads to substantial variability in image descriptions. However,…

There is an intricate relation between the properties of an image and how humans behave while describing the image. This behavior shows ample variation, as manifested in human signals such as eye movements and when humans start to describe…

The performance of text classification has improved tremendously using intelligently engineered neural-based models, especially those injecting categorical metadata as additional information, e.g., using user/product information for…

Considering that words with different characteristic in the text have different importance for classification, grouping them together separately can strengthen the semantic expression of each part. Thus we propose a new text representation…

We explore the question of whether the representations learned by classifiers can be used to enhance the quality of generative models. Our conjecture is that labels correspond to characteristics of natural data which are most salient to…

In this paper, we introduce personalized word embeddings, and examine their value for language modeling. We compare the performance of our proposed prediction model when using personalized versus generic word representations, and study how…

The ability to modulate vocal sounds and generate speech is one of the features which set humans apart from other living beings. The human voice can be characterized by several attributes such as pitch, timbre, loudness, and vocal tone. It…

Despite their high predictive accuracies, current machine learning systems often exhibit systematic biases stemming from annotation artifacts or insufficient support for certain classes in the dataset. Recent work proposes automatic methods…

Large Language Models (LLMs) have achieved remarkable success across diverse natural language tasks, yet the reward models employed for aligning LLMs often encounter challenges of reward hacking, where the approaches predominantly rely on…

Recommender systems have been studied extensively due to their practical use in many real-world scenarios. Despite this, generating effective recommendations with sparse user ratings remains a challenge. Side information associated with…

An emerging definition of fairness in machine learning requires that models are oblivious to demographic user information, e.g., a user's gender or age should not influence the model. Personalized recommender systems are particularly prone…

Natural-language user profiles have recently attracted attention not only for improved interpretability, but also for their potential to make recommender systems more steerable. By enabling direct editing, natural-language profiles allow…

Understanding citizens' values in participatory systems is crucial for citizen-centric policy-making. We envision a hybrid participatory system where participants make choices and provide motivations for those choices, and AI agents…

Large language models (LLMs) are increasingly used to simulate human opinions and survey responses, but their ability to reproduce population responses across cultures remains limited. Existing persona-based prompting methods typically rely…

It is increasingly considered that human speech perception and production both rely on articulatory representations. In this paper, we investigate whether this type of representation could improve the performances of a deep generative model…

As more information becomes available electronically, tools for finding information of interest to users becomes increasingly important. The goal of the research described here is to build a system for generating comprehensible user…