Challenge: Misgendering is the act of incorrectly addressing someone’s gender and is pervasive in everyday use platforms and technologies.
Approach: They propose a task and evaluation dataset to assess the effectiveness of automated misgendering interventions for text-based misgending in the US.
Outcome: The proposed dataset includes 3790 instances of social media content and LLM-generations about non-cisgender public figures, annotated for the presence of misgendering, with additional annotations for correcting misgending in LLM generated text.

Similar Papers

A Multilingual, Culture-First Approach to Addressing Misgendering in LLM Applications (2025.emnlp-main)

Copied to clipboard

Challenge: Misgendering is the act of referring to someone by using words that do not match their chosen identity.
Approach: They propose to use a participatory-design approach to assess and mitigate misgendering across 42 languages and dialects using a human-in-the-loop approach.
Outcome: The proposed guardrails reduce misgendering rates across all languages and dialects without loss of quality and without loss in quality.
MISGENDERED: Limits of Large Language Models in Understanding Pronouns (2023.acl-long)

Copied to clipboard

Challenge: excluding non-binary gender identities can perpetuate harm against non-bisexual individuals through exclusion and marginalization.
Approach: They propose a framework for evaluating large language models’ ability to correctly use preferred pronouns.
Outcome: The proposed framework evaluates language models' ability to correctly use preferred pronouns in English.
Stereotypes and Smut: The (Mis)representation of Non-cisgender Identities by Text-to-Image Models (2023.findings-acl)

Copied to clipboard

Challenge: Initial studies have pointed to the potential for harm due to predictive bias, reflecting and potentially reinforcing cultural stereotypes.
Approach: They conduct a survey among non-cisgender individuals and interviews to establish which harms affected individuals anticipate, and how they would like to be represented.
Outcome: The results show that certain non-cisgender identities are consistently (mis)represented as less human, more stereotyped and more sexualised.
RtGender: A Corpus for Studying Differential Responses to Gender (L18-1)

Copied to clipboard

Challenge: Prior work on linguistic gender difference and communications about gender has focused on language about or portraying persons of a particular gender.
Approach: They present a multi-genre corpus of 25M comments from five socially and topically diverse sources tagged for the gender of the addressee and 30k annotations for sentiment and relevance of these responses.
Outcome: The proposed dataset shows that responses to women are more emotive and about the speaker as an individual (rather than about the content being responded to).
Explaining Toxic Text via Knowledge Enhanced Text Generation (2022.naacl-main)

Copied to clipboard

Challenge: Existing work on toxic speech classification relies on generic and repetitive explanations . elucidating toxic speech can help with downstream tasks such as debiasing .
Approach: They propose a knowledge-informed encoder-decoder framework to generate toxic text explanations . they use multiple knowledge sources to generate detailed explanations of toxic text .
Outcome: The proposed model outperforms state-of-the-art models significantly in generating toxic explanations . the proposed model can generate detailed explanations of toxic speech compared to baselines compared with baseline models .
Gender Identity in Pretrained Language Models: An Inclusive Approach to Data Creation and Probing (2024.findings-emnlp)

Copied to clipboard

Challenge: Pretrained language models encode binary gender information of text authors, raising the risk of skewed representations and downstream harms.
Approach: They use a corpus of YouTube transcripts from transgender, cisgender and non-binary speakers to examine whether pretrained language models encode binary gender information.
Outcome: The proposed model encodes gender information for all gender identities but to different extents.
Black is to Criminal as Caucasian is to Police: Detecting and Removing Multiclass Bias in Word Embeddings (N19-1)

Copied to clipboard

Challenge: Existing methods to debias word embeddings in binary settings such as gender and religion are limited to binary labels, whereas word2vec embedders can be used to propagate biases.
Approach: They propose a method to debias word embeddings in multiclass settings such as gender and religion, extending the work of Bolukbasi et al. (2016).
Outcome: The proposed method maintains the efficacy in standard NLP tasks while maintaining the utility of embeddings.
MisinfoEval: Generative AI in the Era of “Alternative Facts” (2024.emnlp-main)

Copied to clipboard

Challenge: Existing efforts to address misinformation on social media platforms are hampered by user biases and scalability challenges.
Approach: They propose a framework for generating and comprehensively evaluating large language model based misinformation interventions using a simulated social media environment and personalized explanations tailored to users' beliefs.
Outcome: The proposed framework improves accuracy at reliability labeling by up to 41.72% and personalized explanations appeal to users' pre-existing values.
Annotating Online Misogyny (2021.acl-long)

Copied to clipboard

Challenge: Online misogyny is a category of online abusive language with serious and harmful social consequences.
Approach: They propose an iterative annotation process and a taxonomy of labels for annotating misogyny in natural written language and cite a high-quality dataset of annotated posts from social media posts.
Outcome: The proposed method aims to identify misogynistic language in natural written language and annotate it in social media posts using a high-quality dataset.
A Just and Comprehensive Strategy for Using NLP to Address Online Abuse (P19-1)

Copied to clipboard

Challenge: Current methods to detect online abuse focus on a narrow definition of abuse to detriment of victims seeking validation and solutions.
Approach: They argue that the NLP community needs to make three substantive changes to tackle both more subtle and more serious forms of abuse.
Outcome: The proposed approach would address the problem of abuse in a more inclusive and productive way.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations