Related papers: Value Profiles for Encoding Human Variation
Predictive modeling applications increasingly use data representing people's behavior, opinions, and interactions. Fine-grained behavior data often has different structure from traditional data, being very high-dimensional and sparse.…
We introduce a method for decentralized person re-identification in robot swarms that leverages natural language as the primary representational modality. Unlike traditional approaches that rely on opaque visual embeddings --…
Current works in the generation of personalized dialogue primarily contribute to the agent presenting a consistent personality and driving a more informative response. However, we found that the generated responses from most previous models…
Providing user-understandable explanations to justify recommendations could help users better understand the recommended items, increase the system's ease of use, and gain users' trust. A typical approach to realize it is natural language…
User behavior data in recommender systems are driven by the complex interactions of many latent factors behind the users' decision making processes. The factors are highly entangled, and may range from high-level ones that govern user…
Variation in speech is often quantified by comparing phonetic transcriptions of the same utterance. However, manually transcribing speech is time-consuming and error prone. As an alternative, therefore, we investigate the extraction of…
Most pretrained language models rely on subword tokenization, which processes text as a sequence of subword tokens. However, different granularities of text, such as characters, subwords, and words, can contain different kinds of…
People naturally vary in their annotations for subjective questions and some of this variation is thought to be due to the person's sociodemographic characteristics. LLMs have also been used to label data, but recent work has shown that…
To learn semantic attributes, existing methods typically train one discriminative model for each word in a vocabulary of nameable properties. However, this "one model per word" assumption is problematic: while a word might have a precise…
Adapting large language models to individual users remains challenging due to the tension between fine-grained personalization and scalable deployment. We present CARD, a hierarchical framework that achieves effective personalization…
Identifying customer segments in retail banking portfolios with different risk profiles can improve the accuracy of credit scoring. The Variational Autoencoder (VAE) has shown promising results in different research domains, and it has been…
Large language models (LLMs) are known to generate biased responses where the opinions of certain groups and populations are underrepresented. Here, we present a novel approach to achieve controllable generation of specific viewpoints using…
Modeling users for the purpose of identifying their preferences and then personalizing services on the basis of these models is a complex task, primarily due to the need to take into consideration various explicit and implicit signals,…
Value alignment is the task of creating autonomous systems whose values align with those of humans. Past work has shown that stories are a potentially rich source of information on human values; however, past work has been limited to…
Data curation methods typically assign samples a single quality score. We argue this scalar framing is fundamentally limited: when training requires multiple distinct capabilities, a monolithic scorer cannot maximize useful signals for all…
Leveraging persona information of users in Neural Response Generators (NRG) to perform personalized conversations has been considered as an attractive and important topic in the research of conversational agents over the past few years.…
Recent advancements in neural language modelling make it possible to rapidly generate vast amounts of human-sounding text. The capabilities of humans and automatic discriminators to detect machine-generated text have been a large source of…
Transformer-based language models often achieve strong results on mathematical reasoning benchmarks while remaining fragile on basic numerical understanding and arithmetic operations. A central limitation is that numbers are processed as…
Learning data representations that reflect the customers' creditworthiness can improve marketing campaigns, customer relationship management, data and process management or the credit risk assessment in retail banks. In this research, we…
Time series data is prevalent in a wide variety of real-world applications and it calls for trustworthy and explainable models for people to understand and fully trust decisions made by AI solutions. We consider the problem of building…