Large Language Models (LLMs) perpetuate social biases, reflecting prejudices
in their training data and reinforcing societal stereotypes and inequalities.
Our work explores the potential of the Contact Hypothesis, a concept from
social psychology for debiasing LLMs. We simulate various forms of social
contact through LLM prompting to measure their influence on the model's biases,
mirroring how intergroup interactions can reduce prejudices in social contexts.
We create a dataset of 108,000 prompts following a principled approach
replicating social contact to measure biases in three LLMs (LLaMA 2, Tulu, and
NousHermes) across 13 social bias dimensions. We propose a unique debiasing
technique, Social Contact Debiasing (SCD), that instruction-tunes these models
with unbiased responses to prompts. Our research demonstrates that LLM
responses exhibit social biases when subject to contact probing, but more
importantly, these biases can be significantly reduced by up to 40% in 1 epoch
of instruction tuning LLaMA 2 following our SCD strategy. Our code and data are
available at this https URL

大型语言模型（LLMs）持续存在社会偏见，反映其训练数据中的偏见，并加强社会刻板印象和不平等现象。我们的研究探讨了社会心理学概念中的接触假设在消除 LLMs 偏见方面的潜在潜力。通过对 LLMs 进行各种形式的社会接触模拟，以测量其对模型偏见的影响，反映了群体间互动如何在社会环境中减少偏见。我们使用一种有原则的方法创建了一个包含 108,000 个提示的数据集，用于复制社会接触以测量三个 LLMs（LLaMA 2，Tulu 和 NousHermes）在 13 个社会偏见维度上的偏见。我们提出了一种独特的去偏思路，即社会接触去偏（SCD），通过对提问的无偏回复进行指导调整这些模型。我们的研究表明，当 LLMs 经过接触探测时，其回答存在社会偏见，但更重要的是，经过我们的 SCD 策略后，LLaMA 2 的指令调整可以将这些偏见显著减少 40%。我们的代码和数据可在此 URL 上获得。