MBIAS: Mitigating Bias in Large Language Models While Retaining Context
The deployment of Large Language Models (LLMs) in diverse applications necessitates an assurance of safety without compromising the contextual integrity of the generated content. Traditional approaches, including safety-specific fine-tuning or adversarial testing, often yield safe outputs at the expense of contextual meaning. This can result in a diminished capacity to handle nuanced aspects of bias and toxicity, such as underrepresentation or negative portrayals across various demographics. To address these challenges, we introduce MBIAS, an LLM framework carefully instruction fine-tuned on a custom dataset designed specifically for safety interventions. MBIAS is designed to significantly reduce biases and toxic elements in LLM outputs while preserving the main information. This work also details our further use of LLMs: as annotator under human supervision and as evaluator of generated content. Empirical analysis reveals that MBIAS achieves a reduction in bias and toxicity by over 30\% in standard evaluations, and by more than 90\% in diverse demographic tests, highlighting the robustness of our approach. We make the dataset and the fine-tuned model available to the research community for further investigation and ensure reproducibility. The code for this project can be accessed here https://github.com/shainarazavi/MBIAS/tree/main. Warning: This paper contains examples that may be offensive or upsetting.
Code (1)
Similar Papers 제목 키워드 기반
Edu-MMBias: A Three-Tier Multimodal Benchmark for Auditing Social Bias in Vision-Language Models under Educational Contexts
As Vision-Language Models (VLMs) become integral to educational decision-making, ensuring their fairness is paramount. However, current text-centric evaluations neglect the visual modality, leaving an unregulated channel…
Overconfident and Blind to Details: Fixing Prompt Insensitivity with Abductive Preference Learning
Vision and language models frequently ignore semantically critical input edits, defaulting to pretraining priors. For example, models will confidently assert a five-legged dog has four legs; consequently, on the VLMBias …
Breaking the Self-Confirming Loop: Diagnosing and Mitigating Systemic Reward Bias in Self-Rewarding RL
Reinforcement learning with verifiable rewards (RLVR) efficiently scales the reasoning ability of large language models (LLMs) but is bottlenecked by scarce labeled data. Reinforcement learning with intrinsic rewards (RL…
Reinforcement LearningMultiModal Bias: Introducing a Framework for Stereotypical Bias Assessment beyond Gender and Race in Vision Language Models
Recent breakthroughs in self supervised training have led to a new class of pretrained vision language models. While there have been investigations of bias in multimodal models, they have mostly focused on gender and rac…
An Empirical Study on the Fairness of Pre-trained Word Embeddings
Pre-trained word embedding models are easily distributed and applied, as they alleviate users from the effort to train models themselves. With widely distributed models, it is important to ensure that they do not exhibit…
FairnessWord Embeddings