Austria

With the development of large language models (LLMs), social biases in these LLMs have become a pressing issue.
Although there are various benchmarks for social biases across languages, the extent to which Japanese LLMs exhibit social biases has not been fully investigated.
In this study, we construct the Japanese Bias Benchmark dataset for Question Answering (JBBQ) based on the English bias benchmark BBQ, with analysis of social biases in Japanese LLMs.
The results show that while current open Japanese LLMs with more parameters show improved accuracies on JBBQ, their bias scores increase.
In addition, prompts with a warning about social biases and chain-of-thought prompting reduce the effect of biases in model outputs, but there is room for improvement in extracting the correct evidence from contexts in Japanese. 
Our dataset is available at https://github.com/ynklab/JBBQ_data.

ACL 2025

JBBQ: Japanese Bias Benchmark for Analyzing Social Biases in 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.

workshop paper

### Welcome to The 63rd Annual Meeting of the Association for Computational Linguistics (ACL 2025)

Message from the General Chair: 
*It is my great pleasure and honor to welcome you to the 63rd Annual Meeting of the Association for Computational Linguistics (ACL 2025), held in beautiful Vienna, Austria, from July 27 to August 1, 2025. ACL2025continues our field’s tradition of excellence in scholarship, innovation, and inclusivity, and I am deeply grateful to the many volunteers who have worked tirelessly to bring this event to life.* 
[Read more](https://drive.google.com/file/d/1GI_hvOpjswAuYdUTromfeDiPpCcqidwg/view?usp=sharing)

To access this event page, you need to log in with the **email address you registered with**. Access credentials will be sent to your email from Underline - subject line "Welcome to ACL 2025". Please be sure to check your spam email folder if you do not see an email confirmation right away.

Please log in

To access this event page, you need to log in with the **email address you registered with**. 

Welcome to The 63rd Annual Meeting of the Association for Computational Linguistics (ACL 2025)

An growing number of studies have examined the social bias of rapidly developed large language models (LLMs). Although most of these studies have focused on bias occurring in a single social attribute, research in social science has shown that social bias often occurs in the form of intersectionality---the constitutive and contextualized perspective on bias aroused by social attributes. In this study, we construct the Japanese benchmark inter-JBBQ, designed to evaluate the intersectional bias in LLMs on the question-answering setting. Using inter-JBBQ to analyze GPT-4o and Swallow, we find that biased output varies according to its contexts even with the equal combination of social attributes.

Intersectional Bias in Japanese Large Language Models from a Contextualized Perspective

In the current landscape of automatic language generation, there is a need to understand, evaluate, and mitigate demographic biases, as existing models are becoming increasingly multilingual. To address this, we present the initial eight languages from the Massive Multilingual Holistic Bias (MMHB) dataset and benchmark consisting of approximately 6 million sentences. The sentences are designed to induce biases towards different groups of people which can yield significant results when using them as a benchmark to test different text generation models. To further scale up in terms of both language coverage and size and to leverage limited human translation, we use systematic approach to independently translate sentence parts. This technique carefully designs a structure to dynamically generate multiple sentence variations and significantly reduces the human translation workload. The translation process has been meticulously conducted to avoid an English-centric perspective and include all necessary morphological variations for languages that require them, improving from the original English HOLISTICBIAS. Finally, we utilize MMHB to report results on gender bias and added toxicity in MT tasks.

Towards Massive Multilingual Holistic Bias

Bias in Natural Language Processing (NLP) applications has become a critical issue, with many methods developed to measure and mitigate bias in word embeddings and language models. However, most approaches focus on single categories such as gender or ethnicity, neglecting the intersectionality of biases, particularly in non-English languages. This paper addresses these gaps by studying both single-category and intersectional biases in Italian word embeddings and language models. We extend existing bias metrics to Italian, introducing GG-FISE, a novel method for detecting intersectional bias while accounting for grammatical gender. We also adapt the CrowS-Pairs dataset and bias metric to Italian. Through a series of experiments using WEAT, SEAT, and LPBS tests, we identify significant biases along gender and ethnic lines, with particular attention to biases against Romanian and South Asian populations. Our results highlight the need for culturally adapted methods to detect and address biases in multilingual and intersectional contexts.

Detecting Bias and Intersectional Bias in Italian Word Embeddings and Language Models

Large Language Models (LLMs) have been shown to be biased in prior work, as they generate text that is in line with stereotypical views of the world or that is not representative of the viewpoints and values of some demographic groups. In this work, we propose using data from parallel men's and women's events at the Olympic Games to investigate different forms of gender bias in language models. We define three different types of bias, and find that models are consistently biased against women when the gender is ambiguous in a prompt. In this case, the model frequently retrieves only results of the men's event with or without acknowledging it as such, revealing pervasive gender bias in LLMs in the context of athletics.

Sports and Women’s Sports: Gender Bias in a Generation with Olympic Data

The tendency for Natural Language Processing (NLP) technologies to reproduce stereotypical associations, such as associating Black people with criminality or women with care professions, is a site of major concern and, therefore, much study. Stereotyping is a powerful tool of oppression, but the social and linguistic mechanisms behind it are largely ignored in the NLP field. Thus, we fail to effectively challenge stereotypes and the power asymmetries they reinforce. This opinion paper problematizes several common aspects of current work addressing stereotyping in NLP, and offers practicable suggestions for potential forward directions.

Power(ful) Associations: Rethinking ``Stereotype'' for NLP

In recent years, various methods have been proposed to evaluate gender bias in large language models (LLMs). A key challenge lies in the transferability of bias measurement methods initially developed for the English language when applied to other languages. This work aims to contribute to this research strand by presenting five German datasets for gender bias evaluation in LLMs. The datasets are grounded in well-established concepts of gender bias and are accessible through multiple methodologies. Our findings, reported for eight multilingual LLM models, reveal unique challenges associated with gender bias in German, including the ambiguous interpretation of male occupational terms and the influence of seemingly neutral nouns on gender perception. This work contributes to the understanding of gender bias in LLMs across languages and underscores the necessity for tailored evaluation frameworks.

Exploring Gender Bias in Large Language Models: An In-depth Dive into the German Language

Reporting bias is the tendency for speakers to omit unnecessary or obvious information while mentioning things they consider relevant or surprising. In descriptions of people, reporting bias can manifest as a tendency to over report on attributes that deviate from the norm. While social bias in language models has garnered a lot of attention in recent years, a majority of the existing work equates "bias" with "stereotypes". We suggest reporting bias as an alternative lens through which to study how social attitudes manifest in language models. We present the MARB dataset, a diagnostic dataset for studying the interaction between social bias and reporting bias in language models. We use MARB to evaluate the off-the-shelf behavior of both masked and autoregressive language models and find signs of reporting bias with regards to marginalized identities, mirroring that which can be found in human text. This effect is particularly pronounced when taking gender into account, demonstrating the importance of considering intersectionality when studying social phenomena like biases.

Introducing MARB — A Dataset for Studying the Social Dimensions of Reporting Bias in Language Models

Gender-inclusive language is often used with the aim of ensuring that all individuals, regardless of gender, can be associated with certain concepts. While psycholinguistic studies have examined its effects in relation to human cognition, it remains unclear how Large Language Models (LLMs) process gender-inclusive language. Given that commercial LLMs are gaining an increasingly strong foothold in everyday applications, it is crucial to examine whether LLMs in fact interpret gender-inclusive language neutrally, because the language they generate has the potential to influence the language of their users. This study examines whether LLM-generated coreferent terms align with a given gender expression or reflect model biases. Adapting psycholinguistic methods from French to English and German, we find that in English, LLMs generally maintain the antecedent’s gender but exhibit underlying masculine bias. In German, this bias is much stronger, overriding all tested gender-neutralization strategies.

Adapting Psycholinguistic Research for LLMs: Gender-inclusive Language in a Coreference Context

Bias in Nepali NLP is rarely addressed, as the language is classified as low-resource, which leads to the perpetuation of biases in downstream systems. Our research focuses on gender bias in Nepali-English machine translation, an area that has seen little exploration. With the emergence of Large Language Models(LLM), there is a unique opportunity to mitigate these biases. In this study, we quantify and evaluate gender bias by constructing an occupation corpus and adapting three gender-bias challenge sets for Nepali. Our findings reveal that gender bias is prevalent in existing translation systems, with translations often reinforcing stereotypes and misrepresenting gender-specific roles. However, LLMs perform significantly better in both gender-neutral and gender-specific contexts, demonstrating less bias compared to traditional machine translation systems. Despite some quirks, LLMs offer a promising alternative for culture-rich, low-resource languages like Nepali. We also explore how LLMs can improve gender accuracy and mitigate biases in occupational terms, providing a more equitable translation experience. Our work contributes to the growing effort to reduce biases in machine translation and highlights the potential of LLMs to address bias in low-resource languages, paving the way for more inclusive and accurate translation systems.

Gender Bias in Nepali-English Machine Translation: A Comparison of LLMs and Existing MT Systems

Large language models (LLMs) often inherit and amplify social biases embedded in their training data. A prominent social bias is gender bias. In this regard, prior work has mainly focused on gender stereotyping bias – the association of specific roles or traits with a particular gender – in English and on evaluating gender bias in model embeddings or generated outputs. In contrast, gender representation bias – the unequal frequency of references to individuals of different genders – in the training corpora has received less attention. Yet such imbalances in the training data constitute an upstream source of bias that can propagate and intensify throughout the entire model lifecycle. To fill this gap, we propose a novel LLM-based method to detect and quantify gender representation bias in LLM training data in gendered languages, where grammatical gender challenges the applicability of methods developed for English. By leveraging the LLMs' contextual understanding, our approach automatically identifies and classifies person-referencing words in gendered language corpora. Applied to four Spanish-English benchmarks and five Valencian corpora, our method reveals substantial male-dominant imbalances. We show that such biases in training data affect model outputs, but can surprisingly be mitigated leveraging small-scale training on datasets that are biased towards the opposite gender. Our findings highlight the need for corpus-level gender bias analysis in multilingual NLP. We make our code and data publicly available.

Downloads

Next from ACL 2025

Intersectional Bias in Japanese Large Language Models from a Contextualized Perspective

Similar lecture

Social Bias Evaluation for Large Language Models Requires Prompt Variations

.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 ACL 2025

Intersectional Bias in Japanese Large Language Models from a Contextualized Perspective

Similar lecture

Social Bias Evaluation for Large Language Models Requires Prompt Variations

Downloads