English
Related papers

Related papers: Intersectional Bias in Causal Language Models

200 papers

Large language models (LLMs) are increasingly used to assess moral or ethical statements, yet their judgments may reflect social and linguistic biases. This work presents a controlled, sentence-level study of how grammatical person, number,…

Computation and Language · Computer Science 2026-03-17 Gustavo Lúcius Fernandes , Jeiverson C. V. M. Santos , Pedro O. S. Vaz-de-Melo

Machine learning models are trained to find patterns in data. NLP models can inadvertently learn socially undesirable patterns when training on gender biased text. In this work, we propose a general framework that decomposes gender bias in…

Computation and Language · Computer Science 2020-05-05 Emily Dinan , Angela Fan , Ledell Wu , Jason Weston , Douwe Kiela , Adina Williams

While reasoning-based large language models excel at complex tasks through an internal, structured thinking process, a concerning phenomenon has emerged that such a thinking process can aggregate social stereotypes, leading to biased…

Computation and Language · Computer Science 2026-05-13 Guoqing Luo , Iffat Maab , Lili Mou , Junichi Yamagishi

Time series are critical for decision-making in fields like finance and healthcare. Their importance has driven a recent influx of works passing time series into language models, leading to non-trivial forecasting on some datasets. But it…

Computation and Language · Computer Science 2024-04-19 Mike A. Merrill , Mingtian Tan , Vinayak Gupta , Tom Hartvigsen , Tim Althoff

Large Language Models (LLMs) are increasingly utilized in educational tasks such as providing writing suggestions to students. Despite their potential, LLMs are known to harbor inherent biases which may negatively impact learners. Previous…

Computation and Language · Computer Science 2023-11-07 Thiemo Wambsganss , Xiaotian Su , Vinitra Swamy , Seyed Parsa Neshaei , Roman Rietsche , Tanja Käser

Many natural language inference (NLI) datasets contain biases that allow models to perform well by only using a biased subset of the input, without considering the remainder features. For instance, models are able to make a classification…

Computation and Language · Computer Science 2021-09-01 Dimion Asael , Zachary Ziegler , Yonatan Belinkov

The pervasive influence of social biases in language data has sparked the need for benchmark datasets that capture and evaluate these biases in Large Language Models (LLMs). Existing efforts predominantly focus on English language and the…

Computation and Language · Computer Science 2024-04-04 Nihar Ranjan Sahoo , Pranamya Prashant Kulkarni , Narjis Asad , Arif Ahmad , Tanu Goyal , Aparna Garimella , Pushpak Bhattacharyya

Many studies have revealed that word embeddings, language models, and models for specific downstream tasks in NLP are prone to social biases, especially gender bias. Recently these techniques have been gradually applied to automatic…

Computation and Language · Computer Science 2022-10-18 Mingqi Gao , Xiaojun Wan

Exposure bias describes the phenomenon that a language model trained under the teacher forcing schema may perform poorly at the inference stage when its predictions are conditioned on its previous predictions unseen from the training…

Computation and Language · Computer Science 2020-04-02 Yifan Xu , Kening Zhang , Haoyu Dong , Yuezhou Sun , Wenlong Zhao , Zhuowen Tu

This work describes a large-scale analysis of sentiment associations in popular word embedding models along the lines of gender and ethnicity but also along the less frequently studied dimensions of socioeconomic status, age, sexual…

Computers and Society · Computer Science 2020-07-01 David Rozado

Large language models generate complex, open-ended outputs: instead of outputting a class label they write summaries, generate dialogue, or produce working code. In order to asses the reliability of these open-ended generation systems, we…

Computation and Language · Computer Science 2022-11-28 Erik Jones , Jacob Steinhardt

To guide the generation of large pretrained language models (LM), previous work has focused on directly fine-tuning the language model or utilizing an attribute discriminator. In this work, we propose a novel lightweight framework for…

Computation and Language · Computer Science 2022-03-01 Jing Qian , Li Dong , Yelong Shen , Furu Wei , Weizhu Chen

We present a robust methodology for evaluating biases in natural language generation(NLG) systems. Previous works use fixed hand-crafted prefix templates with mentions of various demographic groups to prompt models to generate continuations…

Computation and Language · Computer Science 2022-12-06 Arshiya Aggarwal , Jiao Sun , Nanyun Peng

Language models encode and subsequently perpetuate harmful gendered stereotypes. Research has succeeded in mitigating some of these harms, e.g. by dissociating non-gendered terms such as occupations from gendered terms such as 'woman' and…

Computation and Language · Computer Science 2025-05-21 Franziska Sofia Hafner , Ana Valdivia , Luc Rocher

Large pretrained language models can easily produce toxic or biased content, which is prohibitive for practical use. In order to detect such toxic generations, existing methods rely on templates, real-world data extraction, crowdsourcing…

Computation and Language · Computer Science 2022-12-06 Zhexin Zhang , Jiale Cheng , Hao Sun , Jiawen Deng , Fei Mi , Yasheng Wang , Lifeng Shang , Minlie Huang

Language models have been shown to propagate social bias through their output, particularly in the representation of gender and ethnicity. This paper investigates gender and ethnicity biases in AI-generated occupational stories.…

Computation and Language · Computer Science 2025-09-08 Martha O. Dimgba , Sharon Oba , Ameeta Agrawal , Philippe J. Giabbanelli

This paper addresses the critical gap in evaluating bias in multilingual Large Language Models (LLMs), with a specific focus on Spanish language within culturally-aware Latin American contexts. Despite widespread global deployment, current…

Computers and Society · Computer Science 2025-09-04 Melissa Robles , Catalina Bernal , Denniss Raigoso , Mateo Dulce Rubio

Safety guardrails in large language models(LLMs) are developed to prevent malicious users from generating toxic content at a large scale. However, these measures can inadvertently introduce or reflect new biases, as LLMs may refuse to…

Computation and Language · Computer Science 2025-11-03 Adel Khorramrouz , Sharon Levy

Research shows that natural language processing models are generally considered to be vulnerable to adversarial attacks; but recent work has drawn attention to the issue of validating these adversarial inputs against certain criteria (e.g.,…

Computation and Language · Computer Science 2021-09-10 Maximilian Mozes , Max Bartolo , Pontus Stenetorp , Bennett Kleinberg , Lewis D. Griffin

With the emergence of numerous Large Language Models (LLM), the usage of such models in various Natural Language Processing (NLP) applications is increasing extensively. Counterspeech generation is one such key task where efforts are made…

Computation and Language · Computer Science 2024-03-25 Punyajoy Saha , Aalok Agrawal , Abhik Jana , Chris Biemann , Animesh Mukherjee