Constructing Holistic Measures for Social Biases in Masked Language
Models
- URL: http://arxiv.org/abs/2305.07795v2
- Date: Fri, 1 Sep 2023 13:44:14 GMT
- Title: Constructing Holistic Measures for Social Biases in Masked Language
Models
- Authors: Yang Liu and Yuexian Hou
- Abstract summary: Masked Language Models (MLMs) have been successful in many natural language processing tasks.
Real-world stereotype biases are likely to be reflected ins due to their learning from large text corpora.
Two evaluation metrics, Kullback Leiblergence Score (KLDivS) and Jensen Shannon Divergence Score (JSDivS) are proposed to evaluate social biases ins.
- Score: 17.45153670825904
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Masked Language Models (MLMs) have been successful in many natural language
processing tasks. However, real-world stereotype biases are likely to be
reflected in MLMs due to their learning from large text corpora. Most of the
evaluation metrics proposed in the past adopt different masking strategies,
designed with the log-likelihood of MLMs. They lack holistic considerations
such as variance for stereotype bias and anti-stereotype bias samples. In this
paper, the log-likelihoods of stereotype bias and anti-stereotype bias samples
output by MLMs are considered Gaussian distributions. Two evaluation metrics,
Kullback Leibler Divergence Score (KLDivS) and Jensen Shannon Divergence Score
(JSDivS) are proposed to evaluate social biases in MLMs The experimental
results on the public datasets StereoSet and CrowS-Pairs demonstrate that
KLDivS and JSDivS are more stable and interpretable compared to the metrics
proposed in the past.
Related papers
- CEB: Compositional Evaluation Benchmark for Fairness in Large Language Models [58.57987316300529]
Large Language Models (LLMs) are increasingly deployed to handle various natural language processing (NLP) tasks.
To evaluate the biases exhibited by LLMs, researchers have recently proposed a variety of datasets.
We propose CEB, a Compositional Evaluation Benchmark that covers different types of bias across different social groups and tasks.
arXiv Detail & Related papers (2024-07-02T16:31:37Z) - Cycles of Thought: Measuring LLM Confidence through Stable Explanations [53.15438489398938]
Large language models (LLMs) can reach and even surpass human-level accuracy on a variety of benchmarks, but their overconfidence in incorrect responses is still a well-documented failure mode.
We propose a framework for measuring an LLM's uncertainty with respect to the distribution of generated explanations for an answer.
arXiv Detail & Related papers (2024-06-05T16:35:30Z) - 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) - Exploring Value Biases: How LLMs Deviate Towards the Ideal [57.99044181599786]
Large-Language-Models (LLMs) are deployed in a wide range of applications, and their response has an increasing social impact.
We show that value bias is strong in LLMs across different categories, similar to the results found in human studies.
arXiv Detail & Related papers (2024-02-16T18:28:43Z) - Measuring Implicit Bias in Explicitly Unbiased Large Language Models [14.279977138893846]
Large language models (LLMs) can pass explicit social bias tests but still harbor implicit biases.
We introduce two new measures of bias: LLM Implicit Bias, a prompt-based method for revealing implicit bias; and LLM Decision Bias, a strategy to detect subtle discrimination in decision-making tasks.
Using these measures, we found pervasive stereotype biases mirroring those in society in 8 value-aligned models across 4 social categories.
arXiv Detail & Related papers (2024-02-06T15:59:23Z) - Robust Evaluation Measures for Evaluating Social Biases in Masked
Language Models [6.697298321551588]
We construct evaluation measures for the distributions of stereotypical and anti-stereotypical scores.
Our proposed measures are significantly more robust and interpretable than those proposed previously.
arXiv Detail & Related papers (2024-01-21T21:21:51Z) - 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) - BERTScore is Unfair: On Social Bias in Language Model-Based Metrics for
Text Generation [89.41378346080603]
This work presents the first systematic study on the social bias in PLM-based metrics.
We demonstrate that popular PLM-based metrics exhibit significantly higher social bias than traditional metrics on 6 sensitive attributes.
In addition, we develop debiasing adapters that are injected into PLM layers, mitigating bias in PLM-based metrics while retaining high performance for evaluating text generation.
arXiv Detail & Related papers (2022-10-14T08:24:11Z) - Debiasing isn't enough! -- On the Effectiveness of Debiasing MLMs and
their Social Biases in Downstream Tasks [33.044775876807826]
We study intrinsic relationship between task-agnostic and task-specific extrinsic social bias evaluation measures for Masked Language Models (MLMs)
We find that there exists only a weak correlation between these two types of evaluation measures.
arXiv Detail & Related papers (2022-10-06T14:08:57Z) - Towards Understanding and Mitigating Social Biases in Language Models [107.82654101403264]
Large-scale pretrained language models (LMs) can be potentially dangerous in manifesting undesirable representational biases.
We propose steps towards mitigating social biases during text generation.
Our empirical results and human evaluation demonstrate effectiveness in mitigating bias while retaining crucial contextual information.
arXiv Detail & Related papers (2021-06-24T17:52:43Z) - Unmasking the Mask -- Evaluating Social Biases in Masked Language Models [28.378270372391498]
Masked Language Models (MLMs) have superior performances in numerous downstream NLP tasks when used as text encoders.
We propose All Unmasked Likelihood (AUL), a bias evaluation measure that predicts all tokens in a test case.
We also propose AUL with attention weights (AULA) to evaluate tokens based on their importance in a sentence.
arXiv Detail & Related papers (2021-04-15T14:40:42Z)
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.