DyMT-ESB: Dynamic Multi-Turn Evaluation of Social Bias in User-LLM Interactions
Experimental results show that LLMs exhibit social bias even in coherent, response-conditioned multi-turn interactions, revealing late-emerging bias, non-monotonic bias patterns, and bias re-emergence, which motivate evaluations that extend beyond fixed-turn, pre-scripted protocols.
Rem Hida, Masahiro Kaneko, Daisuke Oba et al.
· 0 citations