Investigating Thinking Behaviours of Reasoning-Based Language Models for Social Bias Mitigation

ArXi:2510.17062v2 Announce Type: replace-cross While reasoning-based large language models excel at complex tasks through an internal, structured thinking process, a concerning phenomenon has emerged that such a thinking process can aggregate social stereotypes, leading to biased outcomes. However, the underlying behaviours of these language models in social bias scenarios remain underexplored.