揭示LLM评审在创意评估中重风格轻实质的偏见，挑战AI评价可靠性。
arXiv:2608.01666v1 Announce Type: cross Abstract: However, whether these judges truly evaluate the scientific substance of ideas or are influenced by …
多语言评测水太深？翻译误差和评估细节就能悄悄改写模型排名，这份研究带你拆穿假象。
arXiv:2511.05162v2 Announce Type: replace Abstract: Most current large language models (LLMs) support a wide variety of languages in addition to Engli…
临床AI评测翻车？提示词框架竟能制造“多模态能力”假象，看清这项研究避免误判。
arXiv:2603.28387v2 Announce Type: replace Abstract: Trustworthy clinical AI requires that performance gains reflect genuine evidence integration rathe…
揭示多智能体LLM中评估偏差像病毒一样通过网络传播，影响AI协作的可靠性。
arXiv:2606.20493v1 Announce Type: cross Abstract: When large language models serve as evaluators in multi-agent systems, their systematic evaluation b…
多模态AI自我评估存在系统性偏差，一种新发现的“偏好崩溃”现象加剧了模型反馈循环中的错误。
arXiv:2606.16682v1 Announce Type: new Abstract: When AI agents use language models to evaluate their own outputs in a feedback loop, systematic biases…