The presence of specific linguistic signals particular to a certain sub-group can become highly salient to language models during training. In automated decision-making settings, this may lead to biased outcomes when models rely on cues that correlate with protected characteristics. We investigate whether prompting ChatGPT to rewrite text using simplification, neutralisation, localisation, and formalisation can reduce demographic signals while preserving meaning. Experimental results show a statistically significant drop in location classification accuracy across multiple models after transformation, suggesting reduced reliance on group-specific language. At the same time, sentiment analysis and rating prediction tasks confirm that the core meaning of the reviews remains greatly intact. These results suggest that prompt-based rewriting offers a practical and generalisable approach for mitigating bias in text classification.
Michigan State University（密歇根州立大学）；TAL Education Group（好未来教育集团）
It is evident that deep text classification models trained on human data could be biased. In particular, they produce biased outcomes for texts that explicitly include identity terms of certain demographic groups. We refer to this type of bias as explicit bias, which has been extensively studied. However, deep text classification models can also produce biased outcomes for texts written by authors of certain demographic groups. We refer to such bias as implicit bias of which we still have a rather limited understanding. In this paper, we first demonstrate that implicit bias exists in different…
Word embeddings carry stereotypical connotations from the text they are trained on, which can lead to invalid inferences in downstream models that rely on them. We use this observation to design a mechanism for measuring stereotypes using the task of natural language inference. We demonstrate a reduction in invalid inferences via bias mitigation strategies on static word embeddings (GloVe). Further, we show that for gender bias, these techniques extend to contextualized embeddings when applied selectively only to the static components of contextualized embeddings (ELMo, BERT).
Word embeddings are the standard model for semantic and syntactic representations of words. Unfortunately, these models have been shown to exhibit undesirable word associations resulting from gender, racial, and religious biases. Existing post-processing methods for debiasing word embeddings are unable to mitigate gender bias hidden in the spatial arrangement of word vectors. In this paper, we propose RAN-Debias, a novel gender debiasing methodology which not only eliminates the bias present in a word vector but also alters the spatial distribution of its neighbouring vectors, achieving a bias…
UC Santa Barbara（加州大学圣巴巴拉分校）；UC Los Angeles（加州大学洛杉矶分校）
As Natural Language Processing (NLP) and Machine Learning (ML) tools rise in popularity, it becomes increasingly vital to recognize the role they play in shaping societal biases and stereotypes. Although NLP models have shown success in modeling various applications, they propagate and may even amplify gender bias found in text corpora. While the study of bias in artificial intelligence is not new, methods to mitigate gender bias in NLP are relatively nascent. In this paper, we review contemporary studies on recognizing and mitigating gender bias in NLP. We discuss gender bias based on four fo…
Same Question, Different Answer? Measuring and Mitigating Prompt Privilege for Equitable AI Access
Fuqua School of Business Duke University（杜克大学福库商学院）；Department of Engineering Carnegie Mellon University（卡内基梅隆大学工程学院）；Department of Industrial Engineering and Management Sciences Northwestern University（西北大学工业工程与管理科学系）；Department of Information and Decision Sciences University of Minnesota（明尼苏达大学信息与决策科学学院）
Facebook AI Research（Facebook人工智能研究院）；Laboratoire Lorrain d’Informatique et Applications (LORIA)（洛林计算机科学及其应用实验室）
Models often easily learn biases present in the training data, and their predictions directly reflect this bias. We analyze gender bias in dialogue data, and examine how this bias is actually amplified in subsequent generative chit-chat dialogue models. We measure gender bias in six existing dialogue datasets, and focus on the most biased one, the multi-player text-based fantasy adventure dataset LIGHT, as a testbed for our bias mitigation techniques. The LIGHT dataset is highly imbalanced with respect to gender, containing predominantly male characters, likely because it is entirely collected…
University of Groningen（格罗宁根大学）；University of Malta（马耳他大学）
Contextualized word embeddings have been replacing standard embeddings as the representational knowledge source of choice in NLP systems. Since a variety of biases have previously been found in standard word embeddings, it is crucial to assess biases encoded in their replacements as well. Focusing on BERT (Devlin et al., 2018), we measure gender bias by studying associations between gender-denoting target words and names of professions in English and German, comparing the findings with real-world workforce statistics. We mitigate bias by fine-tuning BERT on the GAP corpus (Webster et al., 2018…
National Taiwan University（台湾大学）；MIT CSAIL（麻省理工学院计算机科学与人工智能实验室）；Amazon AI（亚马逊人工智能）
Automatic detection of toxic language plays an essential role in protecting social media users, especially minority groups, from verbal abuse. However, biases toward some attributes, including gender, race, and dialect, exist in most training datasets for toxicity detection. The biases make the learned models unfair and can even exacerbate the marginalization of people. Considering that current debiasing methods for general natural language understanding tasks cannot effectively mitigate the biases in the toxicity detectors, we propose to use invariant rationalization (InvRat), a game-theoreti…
Entity typing aims at predicting one or more words that describe the type(s) of a specific mention in a sentence. Due to shortcuts from surface patterns to annotated entity labels and biased training, existing entity typing models are subject to the problem of spurious correlations. To comprehensively investigate the faithfulness and reliability of entity typing methods, we first systematically define distinct kinds of model biases that are reflected mainly from spurious correlations. Particularly, we identify six types of existing model biases, including mention-context bias, lexical overlapp…
This paper studies the exposure bias problem in task-oriented dialog systems, where the model's generated content over multiple turns drives the dialog context away from the ground-truth distribution at training time, introducing error propagation and damaging the robustness of the TOD system. To bridge the gap between training and inference for multi-turn task-oriented dialogs, we propose session-level sampling which explicitly exposes the model to sampled generated content of dialog context during training. Additionally, we employ a dropout-based consistency regularization with the masking s…
Non-contextual word embedding models have been shown to inherit human-like stereotypical biases of gender, race and religion from the training corpora. To counter this issue, a large body of research has emerged which aims to mitigate these biases while keeping the syntactic and semantic utility of embeddings intact. This paper describes Fair Embedding Engine (FEE), a library for analysing and mitigating gender bias in word embeddings. FEE combines various state of the art techniques for quantifying, visualising and mitigating gender bias in word embeddings under a standard abstraction. FEE wi…
Delhi Technological University（德里技术大学）；Indraprastha Institute of Information Technology Delhi（德里英迪拉普拉斯信息技术研究所）
Euclidean word embedding models such as GloVe and Word2Vec have been shown to reflect human-like gender biases. In this paper, we extend the study of gender bias to the recently popularized hyperbolic word embeddings. We propose gyrocosine bias, a novel measure for quantifying gender bias in hyperbolic word representations and observe a significant presence of gender bias. To address this problem, we propose Poincaré Gender Debias (PGD), a novel debiasing procedure for hyperbolic word representations. Experiments on a suit of evaluation tests show that PGD effectively reduces bias while adding…
Dartmouth College（达特茅斯学院）；University of Texas at Austin（德克萨斯大学奥斯汀分校）；ProtagoLabs
Current large-scale language models can be politically biased as a result of the data they are trained on, potentially causing serious problems when they are deployed in real-world settings. In this paper, we describe metrics for measuring political bias in GPT-2 generation and propose a reinforcement learning (RL) framework for mitigating political biases in generated text. By using rewards from word embeddings or a classifier, our RL framework guides debiased generation without having access to the training data or requiring the model to be retrained. In empirical experiments on three attrib…
BERT and other large-scale language models (LMs) contain gender and racial bias. They also exhibit other dimensions of social bias, most of which have not been studied in depth, and some of which vary depending on the language. In this paper, we study ethnic bias and how it varies across languages by analyzing and mitigating ethnic bias in monolingual BERT for English, German, Spanish, Korean, Turkish, and Chinese. To observe and quantify ethnic bias, we develop a novel metric called Categorical Bias score. Then we propose two methods for mitigation; first using a multilingual model, and secon…
Artificial Intelligence has the capacity to amplify and perpetuate societal biases and presents profound ethical implications for society. Gender bias has been identified in the context of employment advertising and recruitment tools, due to their reliance on underlying language processing and recommendation algorithms. Attempts to address such issues have involved testing learned associations, integrating concepts of fairness to machine learning and performing more rigorous analysis of training data. Mitigating bias when algorithms are trained on textual data is particularly challenging given…
Internet search affects people's cognition of the world, so mitigating biases in search results and learning fair models is imperative for social good. We study a unique gender bias in image search in this work: the search images are often gender-imbalanced for gender-neutral natural language queries. We diagnose two typical image search models, the specialized model trained on in-domain datasets and the generalized representation model pre-trained on massive image and text data across the internet. Both models suffer from severe gender bias. Therefore, we introduce two novel debiasing approac…
Machine translation and other NLP systems often contain significant biases regarding sensitive attributes, such as gender or race, that worsen system performance and perpetuate harmful stereotypes. Recent preliminary research suggests that adversarial learning can be used as part of a model-agnostic bias mitigation method that requires no data modifications. However, adapting this strategy for machine translation and other modern NLP domains requires (1) restructuring training objectives in the context of fine-tuning pretrained large language models and (2) developing measures for gender or ot…
As machine learning methods are deployed in real-world settings such as healthcare, legal systems, and social science, it is crucial to recognize how they shape social biases and stereotypes in these sensitive decision-making processes. Among such real-world deployments are large-scale pretrained language models (LMs) that can be potentially dangerous in manifesting undesirable representational biases - harmful biases resulting from stereotyping that propagate negative generalizations involving gender, race, religion, and other social constructs. As a step towards improving the fairness of LMs…
Center for Artificial Intelligence Research (CAiRE)（人工智能研究中心（CAiRE））；Hong Kong University of Science and Technology（香港科技大学）
Media bias can lead to increased political polarization, and thus, the need for automatic mitigation methods is growing. Existing mitigation work displays articles from multiple news outlets to provide diverse news coverage, but without neutralizing the bias inherent in each of the displayed articles. Therefore, we propose a new task, a single neutralized article generation out of multiple biased articles, to facilitate more efficient access to balanced and unbiased information. In this paper, we compile a new dataset NeuWS, define an automatic evaluation metric, and provide baselines and mult…
Compared to other language tasks, applying pre-trained language models (PLMs) for search ranking often requires more nuances and training signals. In this paper, we identify and study the two mismatches between pre-training and ranking fine-tuning: the training schema gap regarding the differences in training objectives and model architectures, and the task knowledge gap considering the discrepancy between the knowledge needed in ranking and that learned during pre-training. To mitigate these gaps, we propose Pre-trained, Prompt-learned and Pre-finetuned Neural Ranker (P^3 Ranker). P^3 Ranker …
TU Wien（维也纳工业大学）；University College London（伦敦大学学院）
Supervised machine learning models and their evaluation strongly depends on the quality of the underlying dataset. When we search for a relevant piece of information it may appear anywhere in a given passage. However, we observe a bias in the position of the correct answer in the text in two popular Question Answering datasets used for passage re-ranking. The excessive favoring of earlier positions inside passages is an unwanted artefact. This leads to three common Transformer-based re-ranking models to ignore relevant parts in unseen passages. More concerningly, as the evaluation set is taken…
DR.GAP: Mitigating Bias in Large Language Models using Gender-Aware Prompting with Decoupled Reasoning
School of Information Science and Technology, ShanghaiTech University（上海科技大学信息科学与技术学院）；School of Computer and Cyber Sciences, Augusta University（奥古斯塔大学计算机与网络科学学院）
