Papers by Julia Mendelsohn
When People are Floods: Analyzing Dehumanizing Metaphors in Immigration Discourse with Large Language Models (2025.acl-long)
Copied to clipboard
| Challenge: | a computational approach to measure metaphorical language is based on immigration discourse on social media. |
| Approach: | They propose a computational approach that leverages word-level and document-level signals to measure metaphor with respect to immigration discourse on social media. |
| Outcome: | The proposed method measures metaphorical language in immigration discourse on social media. |
AI-LieDar : Examine the Trade-off Between Utility and Truthfulness in LLM Agents (2025.naacl-long)
Copied to clipboard
| Challenge: | LieDar is a framework to study how LLM-based agents navigate these scenarios in a multi-turn interactive setting. |
| Approach: | They propose a framework to study how LLM-based agents navigate these scenarios in an interactive multi-turn setting. |
| Outcome: | The proposed framework shows that all models are truthful less than 50% of the time, although truthfulness and goal achievement rates vary across models. |
Challenges and Opportunities in Information Manipulation Detection: An Examination of Wartime Russian Media (2022.findings-emnlp)
Copied to clipboard
| Challenge: | Information manipulation campaigns rely on textbased news and social media content, and NLP can be a valuable tool in combating them. |
| Approach: | They propose to use a dataset to examine the use of NLP in public opinion manipulation campaigns in the 2022 Russia-Ukraine war. |
| Outcome: | The proposed dataset contains 38M+ posts from Russian media outlets on Twitter and VKontakte, as well as public activity and responses, immediately preceding and during the 2022 Russia-Ukraine war. |
From Dogwhistles to Bullhorns: Unveiling Coded Rhetoric with Language Models (2023.acl-long)
Copied to clipboard
| Challenge: | This work sheds light on the theoretical and applied importance of dogwhistles in both NLP and computational social science. |
| Approach: | They propose a typology of dogwhistles, curate a glossary of over 300 dogwhitles and analyze their usage in historical U.S. politicians’ speeches. |
| Outcome: | The proposed model identifies dogwhistles and their meanings and shows that harmful content containing dogwhitles avoids toxicity detection. |
Detecting Community Sensitive Norm Violations in Online Conversations (2021.findings-emnlp)
Copied to clipboard
Chan Young Park, Julia Mendelsohn, Karthik Radhakrishnan, Kinjal Jain, Tushar Kanakagiri, David Jurgens, Yulia Tsvetkov
| Challenge: | Existing efforts to identify unacceptable behavior have focused on toxicity as the sole form of community norm violation. |
| Approach: | They propose a dataset that focuses on a more complete spectrum of community norms and their violations in local conversational and global contexts. |
| Outcome: | The proposed model improves the detection of community norm violations in local conversational and global contexts. |
Modeling Framing in Immigration Discourse on Social Media (2021.naacl-main)
Copied to clipboard
| Challenge: | Using a dataset of immigration-related tweets, we examine how ordinary people on social media frame political issues. |
| Approach: | They propose to use a dataset of immigration-related tweets labeled for multiple framing typologies from political communication theory to analyze framers. |
| Outcome: | The proposed model enables comparisons between different types of frames on social media and a dataset of immigration-related tweets. |