"TL;DR:" Out-of-Context Adversarial Text Summarization and Hashtag Recommendation

TL;DR

This paper introduces Out-of-Context Summarizer, a tool that rewrites news articles to fit specific political biases and suggests hashtags to promote polarization, highlighting risks of misuse in automated text generation.

Contribution

The paper presents a novel summarization tool capable of producing politically biased summaries and associated hashtags, advancing understanding of potential misuse of automated text generation.

Findings

Achieved high precision and recall in summarizing COVID-19 and political articles.

Successfully generated biased summaries that can pass adversarial disclosure tests.

Demonstrated potential for misuse in political and social media contexts.

Abstract

This paper presents Out-of-Context Summarizer, a tool that takes arbitrary public news articles out of context by summarizing them to coherently fit either a liberal- or conservative-leaning agenda. The Out-of-Context Summarizer also suggests hashtag keywords to bolster the polarization of the summary, in case one is inclined to take it to Twitter, Parler or other platforms for trolling. Out-of-Context Summarizer achieved 79% precision and 99% recall when summarizing COVID-19 articles, 93% precision and 93% recall when summarizing politically-centered articles, and 87% precision and 88% recall when taking liberally-biased articles out of context. Summarizing valid sources instead of synthesizing fake text, the Out-of-Context Summarizer could fairly pass the "adversarial disclosure" test, but we didn't take this easy route in our paper. Instead, we used the Out-of-Context Summarizer to push the debate of potential misuse of automated text generation beyond the boilerplate text of responsible disclosure of adversarial language models.