United States

Detecting and mitigating harmful biases in modern language models are widely recognized as crucial, open problems. In this paper, we take a step back and investigate how language models come to be biased in the first place. We use a relatively small language model, using the LSTM architecture trained on an English Wikipedia corpus. With full access to the data and to the model parameters as they change during every step while training, we can map in detail how the representation of gender develops, what patterns in the dataset drive this, and how the model&#39;s internal state relates to the bias in a downstream task (semantic textual similarity). We find that the representation of gender is dynamic and identify different phases during training. Furthermore, we show that gender information is represented increasingly locally in the input embeddings of the model and that, as a consequence, debiasing these can be effective in reducing the downstream bias. Monitoring the training dynamics, allows us to detect an asymmetry in how the female and male gender are represented in the input embeddings. This is important, as it may cause naive mitigation strategies to introduce new undesirable biases. We discuss the relevance of the findings for mitigation strategies more generally and the prospects of generalizing our methods to larger language models, the Transformer architecture, other languages and other undesirable biases.

NAACL 2022

The Birth of Bias: A case study on the evolution of gender bias in an English language model

undesirable biases

word embeddings

language models

### 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!

NAACL 2025

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

Detecting and mitigating harmful biases in modern language models are widely recognized as crucial, open problems. In this paper, we take a step back and investigate how language models come to be biased in the first place. We use a relatively small language model, using the LSTM architecture trained on an English Wikipedia corpus. With full access to the data and to the model parameters as they change during every step while training, we can map in detail how the representation of gender develops, what patterns in the dataset drive this, and how the model's internal state relates to the bias in a downstream task (semantic textual similarity). We find that the representation of gender is dynamic and identify different phases during training. Furthermore, we show that gender information is represented increasingly locally in the input embeddings of the model and that, as a consequence, debiasing these can be effective in reducing the downstream bias. Monitoring the training dynamics, allows us to detect an asymmetry in how the female and male gender are represented in the input embeddings. This is important, as it may cause naive mitigation strategies to introduce new undesirable biases. We discuss the relevance of the findings for mitigation strategies more generally and the prospects of generalizing our methods to larger language models, the Transformer architecture, other languages and other undesirable biases.

workshop paper

## Welcome to NAACL 2022!
The Annual Meeting of the North American Chapter of the Association for Computational Linguistics (NAACL) is taking place July 10-15, 2022 as a hybrid event, in Seattle, WA and online. We are happy to welcome all of you to conference! 
 
The main conference program features oral presentations, in-person and virtual posters and demo sessions, a plenary session for our best paper presentations and awards, keynote presentations, a plenary panel on the place of linguistics and symbolic structures in NLP, and an Industrial Track panel on Careers in NLP.
 
Posters (including Findings of NAACL 2022) and demos are grouped by areas for both the in-person and the virtual sessions. For the virtual component, the talks will be on Zoom and the posters and the demos will be in GatherTown. The Student Research Workshop and will have an oral session and a poster session.
 
The program also features 6 Tutorials and 26 Workshops.
 
 We wish you a wonderful conference!
 
[The NAACL 2022 Organizing Committee](https://2022.naacl.org/committees/organization/)

2022 Annual Conference of the North American Chapter of the Association for Computational Linguistics

Researchers have devised numerous ways to quantify social biases vested in pretrained language models. As some language models are capable of generating coherent completions given a set of textual prompts, several prompting datasets have been proposed to measure biases between social groups---posing language generation as a way of identifying biases. In this opinion paper, we analyze how specific choices of prompt sets, metrics, automatic tools and sampling strategies affect bias results. We find out that the practice of measuring biases through text completion is prone to yielding contradicting results under different experiment settings. We additionally provide recommendations for reporting biases in open-ended language generation for a more complete outlook of biases exhibited by a given language model.

Challenges in Measuring Bias via Open-Ended Language Generation

Numerous works have analyzed biases in vision and pre-trained language models individually - however, less attention has been paid to how these biases interact in multimodal settings. This work extends text-based bias analysis methods to investigate multimodal language models, and analyzes intra- and intermodality
associations and biases learned by these models. Specifically, we demonstrate
that VL-BERT (Su et al., 2020) exhibits gender biases, often preferring to reinforce a
stereotype over faithfully describing the visual scene. We demonstrate these findings on a controlled case-study and extend them for a larger set of stereotypically gendered entities.

Worst of Both Worlds: Biases Compound in Pre-trained Vision-and-Language Models

Although approximately 50\% of medical school graduates today are women, female physicians tend to be underrepresented in senior positions, make less money than their male counterparts and receive fewer promotions. There is a growing body of literature demonstrating gender bias in various forms of evaluation in medicine, but this work was mainly conducted by looking for specific words using fixed dictionaries such as LIWC and focused on recommendation letters. We use a dataset of written and quantitative assessments of medical student performance on individual shifts of work, collected across multiple institutions, to investigate the extent to which gender bias exists in a day-to-day context for medical students. We investigate differences in the narrative comments given to male and female students by both male or female faculty assessors, using a fine-tuned BERT model. This allows us to examine whether groups are written about in systematically different ways, without relying on hand-crafted wordlists or topic models. We compare these results to results from the traditional LIWC method and find that, although we find no evidence of group-level gender bias in this dataset, terms related to family and children are used more in feedback given to women.

Assessing Group-level Gender Bias in Professional Evaluations: The Case of Medical Student End-of-Shift Feedback

Due to the complexity of bias and the opaque nature of current neural approaches, there is a rising interest in auditing language technologies. In this work, we contribute to such a line of inquiry by exploring the emergence of gender bias in Speech Translation (ST). As a new perspective, rather than focusing on the final
systems only, we examine their evolution over the course of training. In this way, we are able to account for different variables related to the learning dynamics of gender translation, and investigate when and how gender divides emerge in ST. Accordingly, for three language pairs (en–> es, fr, it) we compare how ST systems behave for masculine and feminine translation at several levels of granularity. We find that masculine and feminine curves are dissimilar, with the feminine one being characterized by a more erratic behaviour and late improvements over the course of training. Also, depending on the considered phenomena, their learning trends can be either antiphase or parallel. Overall, we show how such a progressive analysis can
inform on the reliability and time-wise acquisition of gender, which is concealed by static evaluations and standard metrics

On the Dynamics of Gender Learning in Speech Translation

The size of pretrained models is increasing,
and so is their performance on a variety of NLP
tasks. However, as their memorization capacity
grows, they might pick up more social biases.
In this work, we examine the connection be-
tween model size and its gender bias (specifi-
cally, occupational gender bias). We measure
bias in three masked language model families
(RoBERTa, DeBERTa, and T5) in two setups:
directly using prompt based method, and using
a downstream task (Winogender). We find on
the one hand that larger models receive higher
bias scores on the former task, but when eval-
uated on the latter, they make fewer gender
errors. To examine these potentially conflicting
results, we carefully investigate the behavior of
the different models on Winogender. We find
that while larger models outperform smaller
ones, the probability that their mistakes are
caused by gender bias is higher. Moreover,
we find that the proportion of stereotypical er-
rors compared to anti-stereotypical ones grows
with the model size. Our findings highlight the
potential risks that can arise from increasing
model size.

Fewer Errors, but More Stereotypes? The Effect of Model Size on Gender Bias

As the use of natural language processing increases in our day-to-day life, the need to address gender bias inherent in these systems also amplifies. This is because the inherent bias interferes with the semantic structure of the output of these systems while performing tasks in natural language processing. While research is being done in English to quantify and mitigate bias, debiasing methods in Indic Languages are either relatively nascent or absent for some Indic languages altogether. Most Indic languages are gendered, i.e., each noun is assigned a gender according to each language's rules of grammar. As a consequence, evaluation differs from what is done in English. This paper evaluates the gender stereotypes in Hindi and Marathi languages. The methodologies will differ from the ones in the English language because there are masculine and feminine counterparts in the case of some words. We create a dataset of neutral and gendered occupation words, and emotion words and measure bias with the help of Embedding Coherence Test (ECT) and Relative Norm Distance (RND). We also attempt to mitigate this bias from the embeddings. Experiments show that our proposed debiasing techniques reduce gender bias in these languages.

Mitigating Gender Stereotypes in Hindi and Marathi

This presentation introduces a taxonomy of phenomena which cause bias in machine translation, covering gender bias (people being male and/or female), number bias (singular you versus plural you) and formality bias (informal you versus formal you). The taxonomy is a formalism for describing situations in machine translation when the source text leaves some of these properties unspecified (eg. does not say whether doctor is male or female) but the target language requires the property to be specified (eg. because it does not have a gender-neutral word for doctor). The formalism described here is used internally by Fairslator, a web-based tool for detecting and correcting bias in the output of any machine translator.

A taxonomy of bias-causing ambiguities in machine translation

Pretrained language models are publicly available and constantly finetuned for various real-life applications. As they become capable of grasping complex contextual information, harmful biases are likely increasingly intertwined with those models. This paper analyses gender bias in BERT models with two main contributions: First, a novel bias measure is introduced, defining biases as the difference in sentiment valuation of female and male sample versions. Second, we comprehensively analyse BERT’s biases on the example of a realistic IMDB movie classifier. By systematically varying elements of the training pipeline, we can conclude regarding their impact on the final model bias. Seven different public BERT models in nine training conditions, i.e. 63 models in total, are compared. Almost all conditions yield significant gender biases. Results indicate that reflected biases stem from public BERT models rather than task-specific data, emphasising the weight of responsible usage.

Gender Bias in BERT - Measuring and Analysing Biases through Sentiment Rating in a Realistic Downstream Classification Task

In this paper we explore how a demographic distribution of occupations, along gender dimensions, is reflected in pre-trained language models. We give a descriptive assessment of the distribution of occupations, and investigate to what extent these are reflected in four Norwegian and two multilingual models. To this end, we introduce a set of simple bias probes, and perform five different tasks combining gendered pronouns, first names, and a set of occupations from the Norwegian statistics bureau. We show that language specific models obtain more accurate results, and are much closer to the real-world distribution of clearly gendered occupations. However, we see that none of the models have correct representations of the occupations that are demographically balanced between genders. We also discuss the importance of the training data on which the models were trained on, and argue that template-based bias probes can sometimes be fragile, and a simple alteration in a template can change a model's behavior.

Occupational Biases in Norwegian and Multilingual Language Models

Films are a rich source of data for natural language processing. OpenSubtitles is a popular movie script dataset, used for training models for tasks such as machine translation and dialogue generation. However, movies often contain biases that reflect society at the time, and these biases may be introduced during pre-training and influence downstream models. We perform sentiment analysis on template infilling and the Sentence Embedding Association Test to measure how BERT-based language models change after continued pre-training on OpenSubtitles. We consider gender bias as a primary motivating case for this analysis, while also measuring other social biases such as disability. We show that sentiment analysis on template infilling is not an effective measure of bias due to the rarity of disability and gender identifying tokens in the movie dialogue. We extend our analysis to a longitudinal study of bias in film dialogue over the last 110 years and find that continued pre-training on OpenSubtitles encodes additional bias into BERT. We show that BERT learns associations that reflect the biases and representation of each film era, suggesting that additional care must be taken when using historical data.

Downloads

Next from NAACL 2022

Challenges in Measuring Bias via Open-Ended Language Generation

Similar lecture

Gender Encoding Patterns in Pretrained Language Model Representations

.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 2022

Challenges in Measuring Bias via Open-Ended Language Generation

Similar lecture

Gender Encoding Patterns in Pretrained Language Model Representations

Downloads