United States

We study language ideologies in text produced by LLMs through a case study on English gendered language reform (related to role nouns like congressperson/-woman/-man, and singular they). First, we find political bias: when asked to use language that is &quot;correct&quot; or &quot;natural&quot;, LLMs use language most similarly to when asked to align with conservative (vs. progressive) values. This shows how LLMs&#39; metalinguistic preferences can implicitly communicate the language ideologies of a particular political group, even in seemingly non-political contexts. Second, we find LLMs exhibit internal inconsistency: LLMs use gender-neutral variants more often when more explicit metalinguistic context is provided. This shows how the language ideologies expressed in text produced by LLMs can vary, which may be unexpected to users. We discuss the broader implications of these findings for value alignment.

NAACL 2025

Do language models practice what they preach? Examining language ideologies about gendered language reform encoded in LLMs

gendered languag reform

language ideologies

large language models

## Welcome!
"I am excited to welcome you to this year’s edition of the Conference on Empirical Methods in Natural Language Processing! Importantly, it marks the 30th edition of EMNLP. With over 8,000 submissions, more than 3,000 accepted papers, and thousands of attendees, we have come a long way from that first
workshop, which had 14 accepted papers. As the field looks ahead, Suzhou is the fitting location for celebrating this milestone: rooted in a long literary tradition, yet modern and forward-looking, and home to a large share of the NLP community." 

*Message from the General Chair, Dirk Hovy*

EMNLP 2025

Celebrate 30 Years of EMNLP! 
EMNLP 2025 will be held in Suzhou, China from November 5th to November 9th, 2025.

We study language ideologies in text produced by LLMs through a case study on English gendered language reform (related to role nouns like congressperson/-woman/-man, and singular they). First, we find political bias: when asked to use language that is "correct" or "natural", LLMs use language most similarly to when asked to align with conservative (vs. progressive) values. This shows how LLMs' metalinguistic preferences can implicitly communicate the language ideologies of a particular political group, even in seemingly non-political contexts. Second, we find LLMs exhibit internal inconsistency: LLMs use gender-neutral variants more often when more explicit metalinguistic context is provided. This shows how the language ideologies expressed in text produced by LLMs can vary, which may be unexpected to users. We discuss the broader implications of these findings for value alignment.

workshop paper

### Welcome to 2025 Annual Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics

Welcome to the 2025 meeting of the Nations of the Americas Chapter of the Association for Computational Linguistics! I am proud to help organize the first NAACL conference to carry the new name of our organization, one that emphasizes inclusion for all of the Americas. I am also pleased to welcome you to Albuquerque, New Mexico, a state whose unique blend of cultural influences will make for an excellent backdrop for NAACL 2025, especially with this year’s special theme on NLP in a Multicultural World. 
**[Continue reading...](https://drive.google.com/file/d/1jX-qGhqVSZZCIrAnJaz798pflu5Irrdn/view?usp=sharing)**

*- Colin Cherry, Google, NAACL 2025 General Chair* 

[![](https://assets.underline.io/markdown_image/1/image/b087f8a4dc5816d6e1a6514e59c59ac3.png)](https://drive.google.com/file/d/1T96GzPqObXrMln2BMByCSXTSizjTg69P/view?usp=sharing)

You need to log in with the email address you registered with. Access credentials have been sent to your email. 

Please be sure to check your spam and other email folders if you do not see an email confirmation right away.

Please log in to explore this event.

To access NAACL 2025 event page you are required to register. Please follow [**this link**](https://2025.naacl.org/registration/registration/) to register. Access will depend on your registration type.

Please register!

Welcome to 2025 Annual Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics

This study presents BiasAdapt, a novel data augmentation strategy designed to enhance the robustness of automatic media bias detection models. Leveraging the BABE dataset, BiasAdapt uses a generative language model to identify bias-indicative keywords and replace them with alternatives from opposing categories, thus creating adversarial examples that preserve the original bias labels. The contributions of this work are twofold: it proposes a scalable method for augmenting bias datasets with adversarial examples while preserving labels, and it publicly releases an augmented adversarial media bias dataset.
Training on BiasAdapt reduces the reliance on spurious cues in four of the six evaluated media bias categories.

LLM-based Adversarial Dataset Augmentation for Automatic Media Bias Detection

Violence descriptions in literature offer valuable insights for a wide range of research in the humanities. For historians, depictions of violence are of special interest for analyzing the societal dynamics surrounding large wars and individual conflicts of influential people. Harvesting data for violence research manually is laborious and time-consuming. This study is the first one to evaluate the effectiveness of large language models (LLMs) in identifying violence in ancient texts and categorizing it across multiple dimensions. Our experiments identify LLMs as a valuable tool to scale up the accurate analysis of historical texts and show the effect of fine-tuning and data augmentation, yielding an F1-score of up to 0.93 for violence detection and 0.86 for fine-grained violence categorization.

Automating Violence Detection and Categorization from Ancient Texts

The application of text mining methods is becoming increasingly prevalent, particularly within Humanities and Computational Social Sciences, as well as in a broader range of disciplines. This paper presents an analysis of gender bias in English song lyrics using topic modeling and bias measurement techniques. Leveraging BERTopic, we cluster a dataset of 537,553 English songs into distinct topics and analyze their temporal evolution. Our results reveal a significant thematic shift in song lyrics over time, transitioning from romantic themes to a heightened focus on the sexualization of women. Additionally, we observe a substantial prevalence of profanity and misogynistic content across various topics, with a particularly high concentration in the largest thematic cluster. To further analyse gender bias across topics and genres in a quantitative way, we employ the Single Category Word Embedding Association Test (SC-WEAT) to calculate bias scores for word embeddings trained on the most prominent topics as well as individual genres. The results indicate a consistent male bias in words associated with intelligence and strength, while appearance and weakness words show a female bias. Further analysis highlights variations in these biases across topics, illustrating the interplay between thematic content and gender stereotypes in song lyrics.

Tuning Into Bias: A Computational Study of Gender Bias in Song Lyrics

Relation extraction (RE) in fiction presents unique NLP challenges due to implicit, narrative-driven relationships. Unlike factual texts, fiction weaves complex connections, yet existing RE datasets focus on non-fiction. To address this, we introduce Artificial Relationships in Fiction (ARF), a synthetically annotated dataset for literary RE. Built from diverse Project Gutenberg fiction, ARF considers author demographics, publication periods, and themes. We curated an ontology for fiction-specific entities and relations, and using GPT-4o, generated artificial relationships to capture narrative complexity. Our analysis demonstrates its value for finetuning RE models and advancing computational literary studies. By bridging a critical RE gap, ARF enables deeper exploration of fictional relationships, enriching NLP research at the intersection of storytelling and AI-driven literary analysis.

Artificial Relationships in Fiction: A Dataset for Advancing NLP in Literary Domains

Recent studies have shown that few-shot learning enables large language models (LLMs) to generate training data for supervised models at a low cost. However, for complex tasks, the quality of LLM-generated data often falls short compared to human-labeled data. This presents a critical challenge: how should one balance the trade-off between the higher quality but more expensive human-annotated data and the lower quality yet significantly cheaper LLM-generated data? In this paper, we tackle this question for a demanding task: conversational semantic frame analysis (SFA). To address this, we propose a novel method for synthesizing training data tailored to this complex task. Through experiments conducted across a wide range of budget levels, we find that smaller budgets favor a higher reliance on LLM-generated data to achieve optimal cost-efficiency.

Optimizing Cost-Efficiency with LLM-Generated Training Data for Conversational Semantic Frame Analysis

Developing specialised language models for low-resource domains typically involves a trade-off between two specialisation strategies: adapting a general-purpose model through continued pretraining or retraining a model from scratch. While adapting preserves the model's linguistic knowledge, retraining benefits from the flexibility of an in-domain tokeniser -- a potentially significant advantage when handling rare languages. This study investigates the impact of tokenisation, specialisation strategy, and pretraining data availability using classical scholarship -- a multilingual, code-switching and highly domain-specific field -- as a case study. Through extensive experiments, we assess whether domain-specific tokenisation improves model performance, whether character-based models provide a viable alternative to subword-based models, and which specialisation strategy is optimal given the constraints of limited pretraining data. Contrary to prior findings, our results show that in-domain tokenisation does not necessarily enhance performance. Most notably, adaptation consistently outperforms retraining, even with limited data, confirming its efficiency as the preferred strategy for resource-constrained domains. These insights provide valuable guidelines for developing specialised models in fields with limited textual resources.

Don't stop pretraining! Efficiently building specialised language models in resource-constrained settings.

The growing volume of digitized historical texts requires effective semantic search using text embeddings. However, pre-trained multilingual models face challenges with historical content due to OCR noise and outdated spellings. This study examines multilingual embeddings for cross-lingual semantic search in historical Luxembourgish (LB), a low-resource language. We collect historical Luxembourgish news articles from various periods and use GPT-4o for sentence segmentation and translation, generating 20,000 parallel training sentences per language pair. Additionally, we create a semantic search (Historical LB Bitext Mining) evaluation set and find that existing models perform poorly on cross-lingual search for historical Luxembourgish. Using our historical and additional modern parallel training data, we adapt several multilingual embedding models through contrastive learning or knowledge distillation and increase accuracy significantly for all models. We release our adapted models and historical Luxembourgish-German/French/English bitexts to support further research.

Adapting Multilingual Embedding Models to Historical Luxembourgish

Automatic poetry generation is an immensely complex task, even for the most advanced Large Language Models (LLMs) that requires a profound understanding of intelligence, world and linguistic knowledge, and a touch of creativity.
This paper investigates the use of LLMs in generating Russian syllabo-tonic poetry of various genres and styles. The study explores a character-level tokenization architectures and demonstrates how a language model can be pretrained and finetuned to generate poetry requiring knowledge of a language's phonetics. Additionally, the paper assesses the quality of the generated poetry and the effectiveness of the approach in producing different genres and styles. The study's main contribution is the introduction of two end-to-end architectures for syllabo-tonic Russian poetry: pretrained models, a comparative analysis of the approaches, and poetry evaluation metrics.

Generation of Russian Poetry of Different Genres and Styles Using Neural Networks with Character-Level Tokenization

Algorithmic hate speech detection faces significant challenges due to the diverse definitions and datasets used in research and practice. Social media platforms, legal frameworks, and institutions each apply distinct yet overlapping definitions, complicating classification efforts. This study addresses these challenges by demonstrating that existing datasets and taxonomies can be integrated into a unified model, enhancing prediction performance and reducing reliance on multiple specialized classifiers. The work introduces a universal taxonomy and a hate speech classifier capable of detecting a wide range of definitions within a single framework. Our approach is validated by combining two widely used but differently annotated datasets, showing improved classification performance on an independent test set. This work highlights the potential of dataset and taxonomy integration in advancing hate speech detection, increasing efficiency, and ensuring broader applicability across contexts.

Improving Hate Speech Classification with Cross-Taxonomy Dataset Integration

This paper investigates the application of prompt-answering Large Language Models (LLMs) for the task of Named Entity Recognition (NER) in historical texts. Historical NER presents unique challenges due to language change through time, spelling variation, limited availability of digitized data (and, in particular, labeled data), and errors introduced by Optical Character Recognition (OCR) and Handwritten Text Recognition (HTR) processes. Leveraging the zero-shot capabilities of prompt-answering LLMs, we address these challenges by prompting the model to extract entities such as persons, locations, organizations, and dates from historical documents. We then conduct an extensive error analysis of the model output in order to identify and address potential weaknesses in the entity recognition process. The results show that, while such models display ability for extracting named entities, their overall performance is lackluster. Our analysis reveals that model performance is significantly affected by hallucinations in the model output, as well as by challenges imposed by the evaluation of NER output.

Content not yet available

Downloads

Next from NAACL 2025

LLM-based Adversarial Dataset Augmentation for Automatic Media Bias Detection

Similar lecture

Analyzing values about gendered language reform in LLMs' revisions

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES

Content not yet available

.css-70qvj9{display:-webkit-box;display:-webkit-flex;display:-ms-flexbox;display:flex;-webkit-align-items:center;-webkit-box-align:center;-ms-flex-align:center;align-items:center;}Downloads

Next from NAACL 2025

LLM-based Adversarial Dataset Augmentation for Automatic Media Bias Detection

Similar lecture

Analyzing values about gendered language reform in LLMs' revisions

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES

Downloads