A Trip Towards Fairness: Bias and De-Biasing in Large Language Models

Anonymous

Abstract: Cheap-to-Build Very Large-Language Models (CtB-LLMs) with affordable training are emerging as the next big revolution in natural language processing and understanding. These CtB-LLMs are democratizing access to trainable Very Large-Language Models (VLLMs) and, thus, may represent the building blocks of many NLP systems solving downstream tasks. Hence, a little or a large bias in CtB-LLMs may cause huge harm. In this paper, we performed a large investigation of the bias of three families of CtB-LLMs, and we showed that debiasing techniques are effective and usable. Indeed, according to current tests, the LLaMA and the OPT families have an important bias in gender, race, religion, and profession. In contrast to the analysis for other LMMs, we discovered that bias depends not on the number of parameters but on the perplexity. Finally, the debiasing of OPT using LORA reduces bias up to 4.12 points in the normalized stereotype score.

Paper Type: long

Research Area: Ethics, Bias, and Fairness

Contribution Types: Model analysis & interpretability, NLP engineering experiment, Publicly available software and/or pre-trained models

Languages Studied: English

Consent To Share Submission Details: On behalf of all authors, we agree to the terms above to share our submission details.