arXiv 2406.132612024-07-08cs.CLcs.AI

BeHonest：大语言模型诚实性基准测试

BeHonest: Benchmarking Honesty in Large Language Models

Shanghai Jiao Tong University（上海交通大学）；Carnegie Mellon University（卡内基梅隆大学）；Fudan University（复旦大学）；Shanghai AI Laboratory（上海人工智能实验室）；Generative AI Research Lab (GAIR)（生成式人工智能研究实验室（GAIR））

Steffi Chern, Zhulin Hu, Yuqing Yang, Ethan Chern, Yuan Guo, Jiahe Jin, Binjie Wang, Pengfei Liu

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

针对大语言模型诚实性评估研究不足的问题，本文提出全面评估LLM诚实性的基准BeHonest，从三个维度、10个场景测试9款主流LLM，发现其诚实性仍有较大提升空间，呼吁业界重视诚实性对齐。

摘要：

现有大语言模型（LLM）相关研究主要聚焦于评估其有用性或无害性，但另一项关键对齐标准——诚实性受到的关注相对较少。LLM的不诚实行为，比如传播错误信息、欺骗用户，会带来严重风险，且这类风险会随着模型趋近超智能水平而加剧。提升LLM的诚实性能解决关键局限，还有助于发掘其不易表现出的潜在能力，这凸显了当前迫切需要可靠的方法与基准，来有效保障和评估LLM的诚实性。\n本文提出了BeHonest，这是首个专门用于全面评估LLM诚实性的基准。BeHonest从三个核心维度评估诚实性：知识边界认知、欺骗行为规避以及回答一致性。在此基础上，我们设计了10个测试场景，对市面上9款主流LLM开展评估与分析，涵盖不同模型家族的闭源与开源模型，且模型规模各有不同。研究结果表明，LLM的诚实性仍有很大提升空间。我们呼吁AI界优先推进这类模型的诚实性对齐工作，从而充分释放LLM的潜力造福社会，同时避免它们因欺骗或回答不一致造成危害。我们的基准与代码可访问：https://github.com/GAIR-NLP/BeHonest。

英文摘要：

Previous works on Large Language Models (LLMs) have mainly focused on evaluating their helpfulness or harmlessness. However, honesty, another crucial alignment criterion, has received relatively less attention. Dishonest behaviors in LLMs, such as spreading misinformation and defrauding users, present severe risks that intensify as these models approach superintelligent levels. Enhancing honesty in LLMs addresses critical limitations and helps uncover latent capabilities that are not readily expressed. This underscores the urgent need for reliable methods and benchmarks to effectively ensure and evaluate the honesty of LLMs. In this paper, we introduce BeHonest, a pioneering benchmark specifically designed to assess honesty in LLMs comprehensively. BeHonest evaluates three essential aspects of honesty: awareness of knowledge boundaries, avoidance of deceit, and consistency in responses. Building on this foundation, we designed 10 scenarios to evaluate and analyze 9 popular LLMs on the market, including both closed-source and open-source models from different model families with varied model sizes. Our findings indicate that there is still significant room for improvement in the honesty of LLMs. We encourage the AI community to prioritize honesty alignment in these models, which can harness their full potential to benefit society while preventing them from causing harm through deception or inconsistency. Our benchmark and code can be found at: \url{https://github.com/GAIR-NLP/BeHonest}.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。