Self-Debiasing Large Language Models: Zero-Shot Recognition and
Reduction of Stereotypes
- URL: http://arxiv.org/abs/2402.01981v1
- Date: Sat, 3 Feb 2024 01:40:11 GMT
- Title: Self-Debiasing Large Language Models: Zero-Shot Recognition and
Reduction of Stereotypes
- Authors: Isabel O. Gallegos, Ryan A. Rossi, Joe Barrow, Md Mehrab Tanjim, Tong
Yu, Hanieh Deilamsalehy, Ruiyi Zhang, Sungchul Kim, Franck Dernoncourt
- Abstract summary: We leverage the zero-shot capabilities of large language models to reduce stereotyping.
We show that self-debiasing can significantly reduce the degree of stereotyping across nine different social groups.
We hope this work opens inquiry into other zero-shot techniques for bias mitigation.
- Score: 73.12947922129261
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Large language models (LLMs) have shown remarkable advances in language
generation and understanding but are also prone to exhibiting harmful social
biases. While recognition of these behaviors has generated an abundance of bias
mitigation techniques, most require modifications to the training data, model
parameters, or decoding strategy, which may be infeasible without access to a
trainable model. In this work, we leverage the zero-shot capabilities of LLMs
to reduce stereotyping in a technique we introduce as zero-shot self-debiasing.
With two approaches, self-debiasing via explanation and self-debiasing via
reprompting, we show that self-debiasing can significantly reduce the degree of
stereotyping across nine different social groups while relying only on the LLM
itself and a simple prompt, with explanations correctly identifying invalid
assumptions and reprompting delivering the greatest reductions in bias. We hope
this work opens inquiry into other zero-shot techniques for bias mitigation.
Related papers
- Towards Transfer Unlearning: Empirical Evidence of Cross-Domain Bias Mitigation [18.150899267807965]
We study an unlearning-based approach to debiasing in large language models (LLMs)
We propose a mask language modeling unlearning technique, which unlearns the harmful part of the text.
Experimental results demonstrate the effectiveness of our approach in diminishing bias while maintaining the language modeling abilities.
arXiv Detail & Related papers (2024-07-24T02:37:42Z) - The Devil is in the Neurons: Interpreting and Mitigating Social Biases in Pre-trained Language Models [78.69526166193236]
Pre-trained Language models (PLMs) have been acknowledged to contain harmful information, such as social biases.
We propose sc Social Bias Neurons to accurately pinpoint units (i.e., neurons) in a language model that can be attributed to undesirable behavior, such as social bias.
As measured by prior metrics from StereoSet, our model achieves a higher degree of fairness while maintaining language modeling ability with low cost.
arXiv Detail & Related papers (2024-06-14T15:41:06Z) - Cognitive Bias in High-Stakes Decision-Making with LLMs [19.87475562475802]
We develop a framework designed to uncover, evaluate, and mitigate cognitive bias in large language models (LLMs)
Inspired by prior research in psychology and cognitive science, we develop a dataset containing 16,800 prompts to evaluate different cognitive biases.
We test various bias mitigation strategies, amidst proposing a novel method utilising LLMs to debias their own prompts.
arXiv Detail & Related papers (2024-02-25T02:35:56Z) - Prompt-Based Bias Calibration for Better Zero/Few-Shot Learning of
Language Models [7.967925911756304]
We propose a null-input prompting method to calibrate intrinsic bias encoded in pre-trained language models.
Our method significantly improves zero/few-shot learning performance of LMs for both in-context learning and prompt-based fine-tuning.
arXiv Detail & Related papers (2024-02-15T22:54:24Z) - Mitigating Biases for Instruction-following Language Models via Bias Neurons Elimination [54.865941973768905]
We propose a novel and practical bias mitigation method, CRISPR, to eliminate bias neurons of language models in instruction-following settings.
CRISPR automatically determines biased outputs and categorizes neurons that affect the biased outputs as bias neurons using an explainability method.
Experimental results demonstrate the effectiveness of our method in mitigating biases under zero-shot instruction-following settings without losing the model's task performance and existing knowledge.
arXiv Detail & Related papers (2023-11-16T07:16:55Z) - Gaining Wisdom from Setbacks: Aligning Large Language Models via Mistake
Analysis [127.85293480405082]
The rapid development of large language models (LLMs) has not only provided numerous opportunities but also presented significant challenges.
Existing alignment methods usually direct LLMs toward the favorable outcomes by utilizing human-annotated, flawless instruction-response pairs.
This study proposes a novel alignment technique based on mistake analysis, which deliberately exposes LLMs to erroneous content to learn the reasons for mistakes and how to avoid them.
arXiv Detail & Related papers (2023-10-16T14:59:10Z) - Debiasing Vision-Language Models via Biased Prompts [79.04467131711775]
We propose a general approach for debiasing vision-language foundation models by projecting out biased directions in the text embedding.
We show that debiasing only the text embedding with a calibrated projection matrix suffices to yield robust classifiers and fair generative models.
arXiv Detail & Related papers (2023-01-31T20:09:33Z) - Right for the Right Latent Factors: Debiasing Generative Models via
Disentanglement [20.41752850243945]
Key assumption of most statistical machine learning methods is that they have access to independent samples from the distribution of data they encounter at test time.
In particular, machine learning models have been shown to exhibit Clever-Hans-like behaviour, meaning that spurious correlations in the training set are inadvertently learnt.
We propose to debias generative models by disentangling their internal representations, which is achieved via human feedback.
arXiv Detail & Related papers (2022-02-01T13:16:18Z) - Few-shot Instruction Prompts for Pretrained Language Models to Detect
Social Biases [55.45617404586874]
We propose a few-shot instruction-based method for prompting pre-trained language models (LMs)
We show that large LMs can detect different types of fine-grained biases with similar and sometimes superior accuracy to fine-tuned models.
arXiv Detail & Related papers (2021-12-15T04:19:52Z)
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.