Editable Fairness: Fine-Grained Bias Mitigation in Language Models
- URL: http://arxiv.org/abs/2408.11843v1
- Date: Wed, 7 Aug 2024 17:14:58 GMT
- Title: Editable Fairness: Fine-Grained Bias Mitigation in Language Models
- Authors: Ruizhe Chen, Yichen Li, Jianfei Yang, Joey Tianyi Zhou, Zuozhu Liu,
- Abstract summary: We propose a novel debiasing approach, Fairness Stamp (FAST), which enables fine-grained calibration of individual social biases.
FAST surpasses state-of-the-art baselines with superior debiasing performance.
This highlights the potential of fine-grained debiasing strategies to achieve fairness in large language models.
- Score: 52.66450426729818
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Generating fair and accurate predictions plays a pivotal role in deploying large language models (LLMs) in the real world. However, existing debiasing methods inevitably generate unfair or incorrect predictions as they are designed and evaluated to achieve parity across different social groups but leave aside individual commonsense facts, resulting in modified knowledge that elicits unreasonable or undesired predictions. In this paper, we first establish a new bias mitigation benchmark, BiaScope, which systematically assesses performance by leveraging newly constructed datasets and metrics on knowledge retention and generalization. Then, we propose a novel debiasing approach, Fairness Stamp (FAST), which enables fine-grained calibration of individual social biases. FAST identifies the decisive layer responsible for storing social biases and then calibrates its outputs by integrating a small modular network, considering both bias mitigation and knowledge-preserving demands. Comprehensive experiments demonstrate that FAST surpasses state-of-the-art baselines with superior debiasing performance while not compromising the overall model capability for knowledge retention and downstream predictions. This highlights the potential of fine-grained debiasing strategies to achieve fairness in LLMs. Code will be publicly available.
Related papers
- Investigating Implicit Bias in Large Language Models: A Large-Scale Study of Over 50 LLMs [0.0]
Large Language Models (LLMs) are being adopted across a wide range of tasks.
Recent research indicates that LLMs can harbor implicit biases even when they pass explicit bias evaluations.
This study highlights that newer or larger language models do not automatically exhibit reduced bias.
arXiv Detail & Related papers (2024-10-13T03:43:18Z) - Test-Time Fairness and Robustness in Large Language Models [17.758735680493917]
Frontier Large Language Models (LLMs) can be socially discriminatory or sensitive to spurious features of their inputs.
Existing solutions, which instruct the LLM to be fair or robust, rely on the model's implicit understanding of bias.
We show that our prompting strategy, unlike implicit instructions, consistently reduces the bias of frontier LLMs.
arXiv Detail & Related papers (2024-06-11T20:05:15Z) - Towards Understanding Task-agnostic Debiasing Through the Lenses of Intrinsic Bias and Forgetfulness [10.081447621656523]
The impact on language modeling ability can be alleviated given a high-quality and long-contextualized debiasing corpus.
The effectiveness of task-agnostic debiasing hinges on the quantitative bias level of both the task-specific data used for downstream applications and the debiased model.
We propose a novel framework which can Propagate Socially-fair Debiasing to Downstream Fine-tuning, ProSocialTuning.
arXiv Detail & Related papers (2024-06-06T15:11:11Z) - Large Language Model Bias Mitigation from the Perspective of Knowledge Editing [12.855975783223236]
We propose a novel debiasing method, Fairness Stamp (FAST), which enables editable fairness through fine-grained calibration on individual biased knowledge.
FAST surpasses state-of-the-art baselines with remarkable debiasing performance while not hampering overall model capability for knowledge preservation.
arXiv Detail & Related papers (2024-05-15T13:44:13Z) - Fair Multivariate Adaptive Regression Splines for Ensuring Equity and
Transparency [1.124958340749622]
We propose a fair predictive model based on MARS that incorporates fairness measures in the learning process.
MARS is a non-parametric regression model that performs feature selection, handles non-linear relationships, generates interpretable decision rules, and derives optimal splitting criteria on the variables.
We apply our fairMARS model to real-world data and demonstrate its effectiveness in terms of accuracy and equity.
arXiv Detail & Related papers (2024-02-23T19:02:24Z) - Marginal Debiased Network for Fair Visual Recognition [59.05212866862219]
We propose a novel marginal debiased network (MDN) to learn debiased representations.
Our MDN can achieve a remarkable performance on under-represented samples.
arXiv Detail & Related papers (2024-01-04T08:57:09Z) - 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) - Learning for Counterfactual Fairness from Observational Data [62.43249746968616]
Fairness-aware machine learning aims to eliminate biases of learning models against certain subgroups described by certain protected (sensitive) attributes such as race, gender, and age.
A prerequisite for existing methods to achieve counterfactual fairness is the prior human knowledge of the causal model for the data.
In this work, we address the problem of counterfactually fair prediction from observational data without given causal models by proposing a novel framework CLAIRE.
arXiv Detail & Related papers (2023-07-17T04:08:29Z) - Delving into Identify-Emphasize Paradigm for Combating Unknown Bias [52.76758938921129]
We propose an effective bias-conflicting scoring method (ECS) to boost the identification accuracy.
We also propose gradient alignment (GA) to balance the contributions of the mined bias-aligned and bias-conflicting samples.
Experiments are conducted on multiple datasets in various settings, demonstrating that the proposed solution can mitigate the impact of unknown biases.
arXiv Detail & Related papers (2023-02-22T14:50:24Z) - General Greedy De-bias Learning [163.65789778416172]
We propose a General Greedy De-bias learning framework (GGD), which greedily trains the biased models and the base model like gradient descent in functional space.
GGD can learn a more robust base model under the settings of both task-specific biased models with prior knowledge and self-ensemble biased model without prior knowledge.
arXiv Detail & Related papers (2021-12-20T14:47:32Z)
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.