Tim Paek

Rik Koncel-Kedziorski, Brihi Joshi, Tim Paek

As the adoption of language models advances, so does the need to better represent individual users to the model. Are there aspects of an individual's belief system that a language model can utilize for improved alignment? Following prior research, we investigate this question in the domain of opinion prediction by developing PrimeX, a dataset of public opinion survey data from 858 US residents with two additional sources of belief information: written explanations from the respondents for why they hold specific opinions, and the Primal World Belief survey for assessing respondent worldview. We provide an extensive initial analysis of our data and show the value of belief explanations and worldview for personalizing language models. Our results demonstrate how the additional belief information in PrimeX can benefit both the NLP and psychological research communities, opening up avenues for further study.

Brihi Joshi, Xiang Ren, Swabha Swayamdipta et al.

Language models prompted with a user description or persona are being used to predict the user's preferences and opinions. However, existing approaches to building personas mostly rely on a user's demographic attributes and/or prior judgments, but not on any underlying reasoning behind a user's judgments. We introduce PB&J (Psychology of Behavior and Judgments), a framework that improves LM personas by incorporating potential rationales for why the user could have made a certain judgment. Our rationales are generated by a language model to explicitly reason about a user's behavior on the basis of their experiences, personality traits, or beliefs. Our method employs psychological scaffolds: structured frameworks such as the Big 5 Personality Traits or Primal World Beliefs to help ground the generated rationales in existing theories. Experiments on public opinion and movie preference prediction tasks demonstrate that language model personas augmented with PB&J rationales consistently outperform personas conditioned only on user demographics and / or judgments, including those that use a model's default chain-of-thought, which is not grounded in psychological theories. Additionally, our PB&J personas perform competitively with those using human-written rationales, suggesting the potential of synthetic rationales guided by existing theories.

Tim Paek, Eric J. Horvitz

Conversations abound with uncetainties of various kinds. Treating conversation as inference and decision making under uncertainty, we propose a task independent, multimodal architecture for supporting robust continuous spoken dialog called Quartet. We introduce four interdependent levels of analysis, and describe representations, inference procedures, and decision strategies for managing uncertainties within and between the levels. We highlight the approach by reviewing interactions between a user and two spoken dialog systems developed using the Quartet architecture: Prsenter, a prototype system for navigating Microsoft PowerPoint presentations, and the Bayesian Receptionist, a prototype system for dealing with tasks typically handled by front desk receptionists at the Microsoft corporate campus.