Implicit Personalization in Language Models: A Systematic Study

TL;DR

This paper provides a comprehensive, mathematically rigorous analysis of Implicit Personalization in language models, exploring its ethical implications and offering case studies, methods, and recommendations for future research.

Contribution

It introduces a unified framework combining causal modeling and moral reasoning to study Implicit Personalization in language models.

Findings

Developed a structural causal model for IP

Introduced indirect intervention method for causal effect estimation

Presented ethical principles and diverse case studies

Abstract

Implicit Personalization (IP) is a phenomenon of language models inferring a user's background from the implicit cues in the input prompts and tailoring the response based on this inference. While previous work has touched upon various instances of this problem, there lacks a unified framework to study this behavior. This work systematically studies IP through a rigorous mathematical formulation, a multi-perspective moral reasoning framework, and a set of case studies. Our theoretical foundation for IP relies on a structural causal model and introduces a novel method, indirect intervention, to estimate the causal effect of a mediator variable that cannot be directly intervened upon. Beyond the technical approach, we also introduce a set of moral reasoning principles based on three schools of moral philosophy to study when IP may or may not be ethically appropriate. Equipped with both mathematical and ethical insights, we present three diverse case studies illustrating the varied nature of the IP problem and offer recommendations for future research. Our code is at https://github.com/jiarui-liu/IP, and our data is at https://huggingface.co/datasets/Jerry999/ImplicitPersonalizationData.