Bridging Context Gaps: Enhancing Comprehension in Long-Form Social Conversations Through Contextualized Excerpts

TL;DR

This paper investigates how Large Language Models can enhance comprehension of social conversations by enriching shared excerpts with relevant context, thereby improving understanding, readability, and empathy in multi-party discussions.

Contribution

It introduces methods for contextualizing conversation excerpts using LLMs, addresses challenges in preserving social nuances, and releases a new dataset for future research.

Findings

LLMs significantly improve comprehension and empathy in social excerpts.

Context-enriched excerpts lead to more focused conversation summaries.

The Human-annotated Salient Excerpts (HSE) dataset supports future work.

Abstract

We focus on enhancing comprehension in small-group recorded conversations, which serve as a medium to bring people together and provide a space for sharing personal stories and experiences on crucial social matters. One way to parse and convey information from these conversations is by sharing highlighted excerpts in subsequent conversations. This can help promote a collective understanding of relevant issues, by highlighting perspectives and experiences to other groups of people who might otherwise be unfamiliar with and thus unable to relate to these experiences. The primary challenge that arises then is that excerpts taken from one conversation and shared in another setting might be missing crucial context or key elements that were previously introduced in the original conversation. This problem is exacerbated when conversations become lengthier and richer in themes and shared experiences. To address this, we explore how Large Language Models (LLMs) can enrich these excerpts by providing socially relevant context. We present approaches for effective contextualization to improve comprehension, readability, and empathy. We show significant improvements in understanding, as assessed through subjective and objective evaluations. While LLMs can offer valuable context, they struggle with capturing key social aspects. We release the Human-annotated Salient Excerpts (HSE) dataset to support future work. Additionally, we show how context-enriched excerpts can provide more focused and comprehensive conversation summaries.