作者位次 #3/8SIGIR 2026Oral· Information Retrieval (Full)
Mitigating Bias in Large Language Model Based Question Answering through Causal Front Door Prompting
Yaqi Yang · Ziqi Xu · Jie Li · Chenglong Ma · Jeffrey Chan · Mark Sanderson · Xin Zheng · Yongli Ren
摘要
Large language models (LLMs) are widely used for question answering (QA) but can generate biased or stereotype-driven answers due to demographic associations learned during pre-training. Existing mitigation strategies often rely on model access or fine-tuning, which limits their applicability to...