Feng Jiang, Benyou Wang, Shunian Chen, Ziche Liu, Guiming Hardy Chen
We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. If it links a repository, it is listed below.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Adopting human and large language models (LLM) as judges (a.k.a human-and LLM-as-ajudge) for evaluating the performance of LLMs has recently gained attention. Nonetheless, this approach concurrently introduces potential biases from human and LLMs, questioning the reliability of the evaluation results. In this paper, we propose a novel framework that is free from referencing groundtruth annotations for investigating Misinformation Oversight Bias, Gender Bias, Authority Bias and Beauty Bias on LLM and human judges. We curate a dataset referring to the revised Bloom's Taxonomy and conduct thousands of evaluations. Results show that human and LLM judges are vulnerable to perturbations to various degrees, and that even the cutting-edge judges possess considerable biases. We further exploit these biases to conduct attacks on LLM judges. We hope that our work can notify the community of the bias and vulnerability of human-and LLMas-a-judge, as well as the urgency of developing robust evaluation systems 1 . Warning: we provide illustrative attack protocols to reveal the vulnerabilities of LLM judges, aiming to develop more robust ones.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2402.10669")
get_code_for_paper("2402.10669")
have("2402.10669")
Connect an agent — have() is free.