Papers by Anjalie Field
Controlled Generation for Private Synthetic Text (2025.emnlp-main)
Copied to clipboard
| Challenge: | Text anonymization is essential for developing and deploying AI in high stakes domains . tools for redacting directly identifying content are unlikely to guarantee 100% recall . |
| Approach: | They propose a method for privacy-preserving synthetic text generation that leverages HIPS theory and de-identification principles. |
| Outcome: | The proposed method achieves a strong balance between privacy protection and utility on legal and clinical datasets. |
Framing and Agenda-setting in Russian News: a Computational Analysis of Intricate Political Strategies (D18-1)
Copied to clipboard
| Challenge: | Amidst growing concern over media manipulation, NLP studies focus on overt strategies like censorship and “fake news”. |
| Approach: | They propose to use two concepts from political science literature to identify subtler media manipulation strategies . they propose to apply embedding-based methods to cross-lingually project English frames to Russian . |
| Outcome: | The proposed techniques can be applied to 13 years of the Russian newspaper Izvestia and show that they highlight U.S. moral failings and threats to the U.s. |
Unsupervised Discovery of Implicit Gender Bias (2020.emnlp-main)
Copied to clipboard
| Challenge: | Social biases are difficult to identify because human judgements in this domain can be unreliable. |
| Approach: | They propose an unsupervised approach to detecting implicit gender bias in text . their main challenge is forcing the model to focus on signs of implicit bias . |
| Outcome: | The proposed model reduces the influence of confounds by focusing on signs of implicit bias rather than other artifacts in the data. |
A Survey of Race, Racism, and Anti-Racism in NLP (2021.acl-long)
Copied to clipboard
| Challenge: | despite inextricable ties between race and language, little work has considered race in NLP research and development. |
| Approach: | They survey 79 papers from the ACL anthology that mention race . they find race has been siloed as a niche topic and ignored in many NLP tasks . authors call for inclusion and racial justice in NLP research practices . |
| Outcome: | The findings highlight the need for inclusion and racial justice in NLP research practices. |
Riveter: Measuring Power and Social Dynamics Between Entities (2023.acl-demo)
Copied to clipboard
| Challenge: | Riveter provides a complete pipeline for analyzing verb connotations associated with entities in text corpora. |
| Approach: | et al., 2005, provide a verb-centric analysis pipeline for verb connotations in text corpora . they prepopulate the pipeline with connotation frames of sentiment, power, and agency . lexical frameworks have been foundational tools in social science, digital humanities, and natural language processing . |
| Outcome: | Riveter provides a complete pipeline for analyzing verb connotations associated with entities in text corpora. |
Evaluating Differentially Private Synthetic Data Generation in High-Stakes Domains (2024.findings-emnlp)
Copied to clipboard
| Challenge: | a lack of anonymization of sensitive text data hinders development of NLP tools . poorly anonymized sensitive data cannot be easily shared with annotators or external researchers . |
| Approach: | They propose to use synthetic data to generate differentially private language models in place of real data to facilitate NLP development without compromising privacy. |
| Outcome: | The proposed model can be used to train public models without compromising privacy. |
Multi-Token Completion for Text Anonymization (2026.eacl-long)
Copied to clipboard
| Challenge: | Text anonymization is a critical task for enabling research and development in high-stakes domains containing private data. |
| Approach: | They propose a method for predicting replacements for sensitive spans with principled use-inspired evaluation criteria. |
| Outcome: | The proposed method produces more realistic text and preserves utility than alternative infilling methods and differentially private mechanisms across multiple domains without retraining. |
Locating Information Gaps and Narrative Inconsistencies Across Languages: A Case Study of LGBT People Portrayals on Wikipedia (2024.emnlp-main)
Copied to clipboard
| Challenge: | a recent study focuses on comparative text analyses to explain social phenomena and identify systematic biases. |
| Approach: | They evaluate InfoGap method to locate information gaps and inconsistencies in articles at the fact level, across languages. |
| Outcome: | The method identifies discrepancies in factual coverage across languages and biographical facts carrying negative connotations are more likely to be highlighted in Russian Wikipedia. |
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. |
Gendered Mental Health Stigma in Masked Language Models (2022.emnlp-main)
Copied to clipboard
Inna Lin, Lucille Njoo, Anjalie Field, Ashish Sharma, Katharina Reinecke, Tim Althoff, Yulia Tsvetkov
| Challenge: | Mental health stigma prevents many individuals from receiving appropriate care, and social psychology studies have shown that mental health tends to be overlooked in men. |
| Approach: | They propose to use clinical psychology literature to curate prompts, then evaluate models’ propensity to generate gendered words. |
| Outcome: | The proposed framework captures stigma about gender in mental health and is more likely to predict female subjects than male in sentences about mental health conditions (32% vs. 19%), and this disparity is exacerbated for sentences that indicate treatment-seeking behavior. |
HICode: Hierarchical Inductive Coding with LLMs (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods for fine-grained corpus analysis are limited to small subsets and require manual labeling and statistical tools like topic modeling. |
| Approach: | They propose a pipeline that inductively generates labels from analysis data and then hierarchically clusters them to surface emergent themes. |
| Outcome: | The proposed pipeline validates the approach across three datasets and shows it is robust through automated and human evaluations. |
Annotating Mentions Alone Enables Efficient Domain Adaptation for Coreference Resolution (2023.acl-long)
Copied to clipboard
| Challenge: | Recent results show that annotating mentions is twice as fast as annotation of full coreference chains. |
| Approach: | They propose a method for efficiently adapting coreference models using only mentions in the target domain without increasing annotator time. |
| Outcome: | The proposed method improves average F1 without increasing annotator time. |
Entity-Centric Contextual Affective Analysis (P19-1)
Copied to clipboard
| Challenge: | Existing methods for analyzing people portrayals take an unsupervised approach, or rely on domain-specific knowledge. |
| Approach: | They show how contextualized word embeddings can be used to capture affect dimensions in portrayals of people. |
| Outcome: | The proposed method can capture affect dimensions in portrayals of men and women . it is biased towards training data, which limits its usefulness to in-domain analyses . |
SynthTextEval: Synthetic Text Data Generation and Evaluation for High-Stakes Domains (2025.emnlp-demos)
Copied to clipboard
Krithika Ramesh, Daniel Smolyak, Zihao Zhao, Nupoor Gandhi, Ritu Agarwal, Margrét V. Bjarnadóttir, Anjalie Field
| Challenge: | SynthTextEval is a toolkit for conducting comprehensive evaluations of synthetic text. |
| Approach: | They propose a toolkit for conducting comprehensive evaluations of synthetic text using large language models. |
| Outcome: | The proposed toolkit can be run over any dataset, but it is aimed at two high-stakes domains: healthcare and law. |