DiSCo: Making Absence Visible in Intelligent Summarization Interfaces

TL;DR

DiSCo enhances summarization by making absences visible through domain expectation comparisons, reducing bias and aiding user decision-making in various accommodation contexts.

Contribution

Introduces DiSCo, a novel expectation-based method that reveals missing information in summaries by contrasting content with domain norms.

Findings

DiSCo summaries are more detailed and useful for decisions.

Modeling expectations reduces presence bias.

Summaries are slightly harder to read but more transparent.

Abstract

Intelligent interfaces increasingly use large language models to summarize user-generated content, yet these summaries emphasize what is mentioned while overlooking what is missing. This presence bias can mislead users who rely on summaries to make decisions. We present Domain Informed Summarization through Contrast (DiSCo), an expectation-based computational approach that makes absences visible by comparing each entity's content with domain topical expectations captured in reference distributions of aspects typically discussed in comparable accommodations. This comparison identifies aspects that are either unusually emphasized or missing relative to domain norms and integrates them into the generated text. In a user study across three accommodation domains, namely ski, beach, and city center, DiSCo summaries were rated as more detailed and useful for decision making than baseline large language model summaries, although slightly harder to read. The findings show that modeling expectations reduces presence bias and improves both transparency and decision support in intelligent summarization interfaces.