Testing Occupational Gender Bias in Language Models: Towards Robust Measurement and Zero-Shot Debiasing
- URL: http://arxiv.org/abs/2212.10678v2
- Date: Mon, 15 Jul 2024 15:10:45 GMT
- Title: Testing Occupational Gender Bias in Language Models: Towards Robust Measurement and Zero-Shot Debiasing
- Authors: Yuen Chen, Vethavikashini Chithrra Raghuram, Justus Mattern, Mrinmaya Sachan, Rada Mihalcea, Bernhard Schölkopf, Zhijing Jin,
- Abstract summary: Large language models (LLMs) have been shown to exhibit a variety of harmful, human-like biases against various demographics.
We introduce a list of desiderata for robustly measuring biases in generative language models.
We then use this benchmark to test several state-of-the-art open-source LLMs, including Llama, Mistral, and their instruction-tuned versions.
- Score: 98.07536837448293
- License: http://creativecommons.org/licenses/by-sa/4.0/
- Abstract: Generated texts from large language models (LLMs) have been shown to exhibit a variety of harmful, human-like biases against various demographics. These findings motivate research efforts aiming to understand and measure such effects. Prior works have proposed benchmarks for identifying and techniques for mitigating these stereotypical associations. However, as recent research pointed out, existing benchmarks lack a robust experimental setup, hindering the inference of meaningful conclusions from their evaluation metrics. In this paper, we introduce a list of desiderata for robustly measuring biases in generative language models. Building upon these design principles, we propose a benchmark called OCCUGENDER, with a bias-measuring procedure to investigate occupational gender bias. We then use this benchmark to test several state-of-the-art open-source LLMs, including Llama, Mistral, and their instruction-tuned versions. The results show that these models exhibit substantial occupational gender bias. We further propose prompting techniques to mitigate these biases without requiring fine-tuning. Finally, we validate the effectiveness of our methods through experiments on the same set of models.
Related papers
- GenderBias-\emph{VL}: Benchmarking Gender Bias in Vision Language Models via Counterfactual Probing [72.0343083866144]
This paper introduces the GenderBias-emphVL benchmark to evaluate occupation-related gender bias in Large Vision-Language Models.
Using our benchmark, we extensively evaluate 15 commonly used open-source LVLMs and state-of-the-art commercial APIs.
Our findings reveal widespread gender biases in existing LVLMs.
arXiv Detail & Related papers (2024-06-30T05:55:15Z) - Projective Methods for Mitigating Gender Bias in Pre-trained Language Models [10.418595661963062]
Projective methods are fast to implement, use a small number of saved parameters, and make no updates to the existing model parameters.
We find that projective methods can be effective at both intrinsic bias and downstream bias mitigation, but that the two outcomes are not necessarily correlated.
arXiv Detail & Related papers (2024-03-27T17:49:31Z) - Locating and Mitigating Gender Bias in Large Language Models [40.78150878350479]
Large language models (LLM) are pre-trained on extensive corpora to learn facts and human cognition which contain human preferences.
This process can inadvertently lead to these models acquiring biases and prevalent stereotypes in society.
We propose the LSDM (Least Square Debias Method), a knowledge-editing based method for mitigating gender bias in occupational pronouns.
arXiv Detail & Related papers (2024-03-21T13:57:43Z) - Measuring Social Biases in Masked Language Models by Proxy of Prediction
Quality [0.0]
Social political scientists often aim to discover and measure distinct biases from text data representations (embeddings)
In this paper, we evaluate the social biases encoded by transformers trained with a masked language modeling objective.
We find that proposed measures produce more accurate estimations of relative preference for biased sentences between transformers than others based on our methods.
arXiv Detail & Related papers (2024-02-21T17:33:13Z) - GPTBIAS: A Comprehensive Framework for Evaluating Bias in Large Language
Models [83.30078426829627]
Large language models (LLMs) have gained popularity and are being widely adopted by a large user community.
The existing evaluation methods have many constraints, and their results exhibit a limited degree of interpretability.
We propose a bias evaluation framework named GPTBIAS that leverages the high performance of LLMs to assess bias in models.
arXiv Detail & Related papers (2023-12-11T12:02:14Z) - Gender Biases in Automatic Evaluation Metrics for Image Captioning [87.15170977240643]
We conduct a systematic study of gender biases in model-based evaluation metrics for image captioning tasks.
We demonstrate the negative consequences of using these biased metrics, including the inability to differentiate between biased and unbiased generations.
We present a simple and effective way to mitigate the metric bias without hurting the correlations with human judgments.
arXiv Detail & Related papers (2023-05-24T04:27:40Z) - This Prompt is Measuring <MASK>: Evaluating Bias Evaluation in Language
Models [12.214260053244871]
We analyse the body of work that uses prompts and templates to assess bias in language models.
We draw on a measurement modelling framework to create a taxonomy of attributes that capture what a bias test aims to measure.
Our analysis illuminates the scope of possible bias types the field is able to measure, and reveals types that are as yet under-researched.
arXiv Detail & Related papers (2023-05-22T06:28:48Z) - Counter-GAP: Counterfactual Bias Evaluation through Gendered Ambiguous
Pronouns [53.62845317039185]
Bias-measuring datasets play a critical role in detecting biased behavior of language models.
We propose a novel method to collect diverse, natural, and minimally distant text pairs via counterfactual generation.
We show that four pre-trained language models are significantly more inconsistent across different gender groups than within each group.
arXiv Detail & Related papers (2023-02-11T12:11:03Z) - An Empirical Survey of the Effectiveness of Debiasing Techniques for
Pre-Trained Language Models [4.937002982255573]
Recent work has shown that pre-trained language models capture social biases from the text corpora they are trained on.
Five recently proposed debiasing techniques: Counterfactual Data Augmentation, Dropout, Iterative Nullspace Projection, Self-Debias, and SentenceDebias.
We quantify the effectiveness of each technique using three different bias benchmarks while also measuring the impact of these techniques on a model's language modeling ability.
arXiv Detail & Related papers (2021-10-16T09:40:30Z) - The Gap on GAP: Tackling the Problem of Differing Data Distributions in
Bias-Measuring Datasets [58.53269361115974]
Diagnostic datasets that can detect biased models are an important prerequisite for bias reduction within natural language processing.
undesired patterns in the collected data can make such tests incorrect.
We introduce a theoretically grounded method for weighting test samples to cope with such patterns in the test data.
arXiv Detail & Related papers (2020-11-03T16:50:13Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.