Related papers: Value Profiles for Encoding Human Variation
One of today's most significant societal challenges is building AI systems whose behaviour, or the behaviour it enables within communities of interacting agents (human and artificial), aligns with human values. To address this challenge, we…
When human annotators are given a choice about what to label in an image, they apply their own subjective judgments on what to ignore and what to mention. We refer to these noisy "human-centric" annotations as exhibiting human reporting…
The expression of emotion is highly individualistic. However, contemporary speech emotion recognition (SER) systems typically rely on population-level models that adopt a `one-size-fits-all' approach for predicting emotion. Moreover,…
Humans often hold different perspectives on the same issues. In many NLP tasks, annotation disagreement can reflect valid subjective perspectives. Modeling annotator perspectives and understanding their relationship with other human…
Most approaches to human attribute and action recognition in still images are based on image representation in which multi-scale local features are pooled across scale into a single, scale-invariant encoding. Both in bag-of-words and the…
People can be characterized by their demographic information and personality traits. Characterizing people accurately can help predict their preferences, and aid recommendations and advertising. A growing number of studies infer people's…
In attempts to "explain" predictions of machine learning models, researchers have proposed hundreds of techniques for attributing predictions to features that are deemed important. While these attributions are often claimed to hold the…
Decision making is a process that is extremely prone to different biases. In this paper we consider learning fair representations that aim at removing nuisance (sensitive) information from the decision process. For this purpose, we propose…
Aligning large language models (LLMs) with human values and intents critically involves the use of human or AI feedback. While dense feedback annotations are expensive to acquire and integrate, sparse feedback presents a structural design…
Interpreting the performance results of models that attempt to realize user behavior in platforms that employ recommenders is a big challenge that researchers and practitioners continue to face. Although current evaluation tools possess the…
As large language models (LLMs) are deployed globally, creating pluralistic systems that can accommodate the diverse preferences and values of users worldwide becomes essential. We introduce EVALUESTEER, a benchmark to measure LLMs' and…
Most conventional recommendation methods (e.g., matrix factorization) represent user profiles as high-dimensional vectors. Unfortunately, these vectors lack interpretability and steerability, and often perform poorly in cold-start settings.…
Online user reviews describing various products and services are now abundant on the web. While the information conveyed through review texts and ratings is easily comprehensible, there is a wealth of hidden information in them that is not…
Variational Graph Autoencoders (VGAEs) are powerful models for unsupervised learning of node representations from graph data. In this work, we systematically analyze modeling node attributes in VGAEs and show that attribute decoding is…
Predicting the next utterance in dialogue is contingent on encoding of users' input text to generate appropriate and relevant response in data-driven approaches. Although the semantic and syntactic quality of the language generated is…
Automated decision making is used routinely throughout our everyday life. Recommender systems decide which jobs, movies, or other user profiles might be interesting to us. Spell checkers help us to make good use of language. Fraud detection…
Biased datasets are ubiquitous and present a challenge for machine learning. For a number of categories on a dataset that are equally important but some are sparse and others are common, the learning algorithms will favor the ones with more…
Many applications can benefit from personalized image generation models, including image enhancement, video conferences, just to name a few. Existing works achieved personalization by fine-tuning one model for each person. While being…
Disentangling the encodings of neural models is a fundamental aspect for improving interpretability, semantic control and downstream task performance in Natural Language Processing. Currently, most disentanglement methods are unsupervised…
Latent variable models like the Variational Auto-Encoder (VAE) are commonly used to learn representations of images. However, for downstream tasks like semantic classification, the representations learned by VAE are less competitive than…