arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2202.12299cs.CLcs.AIcs.LG
收藏

通过人类认知偏差捕获大语言模型的故障

Capturing Failures of Large Language Models via Human Cognitive Biases

UC Berkeley(加州大学伯克利分校)

Erik Jones, Jacob Steinhardt

摘要:

大语言模型生成复杂的、开放式的输出:它们不是输出类标签,而是编写摘要、生成对话或生成工作代码。为了评估这些开放式发电系统的可靠性,我们的目标是确定定性类别的错误行为,而不是确定个别错误。为了假设和测试这种定性错误,我们从人类认知偏差中汲取灵感-偏离理性判断的系统模式。具体来说,我们使用认知偏差作为动机,(i)为模型可能存在的问题生成假设,(ii)开发引发这些问题的实验。使用代码生成作为案例研究,我们发现OpenAI的Codex基于输入提示的框架可以预测错误,调整输出到锚点,并偏向于模仿频繁训练样本的输出。然后,我们使用我们的框架来引发高影响力的错误,例如错误地删除文件。我们的研究结果表明,认知科学的实验方法可以帮助描述机器学习系统的行为。

英文摘要:

Large language models generate complex, open-ended outputs: instead of outputting a class label they write summaries, generate dialogue, or produce working code. In order to asses the reliability of these open-ended generation systems, we aim to identify qualitative categories of erroneous behavior, beyond identifying individual errors. To hypothesize and test for such qualitative errors, we draw inspiration from human cognitive biases -- systematic patterns of deviation from rational judgement. Specifically, we use cognitive biases as motivation to (i) generate hypotheses for problems that models may have, and (ii) develop experiments that elicit these problems. Using code generation as a case study, we find that OpenAI's Codex errs predictably based on how the input prompt is framed, adjusts outputs towards anchors, and is biased towards outputs that mimic frequent training examples. We then use our framework to elicit high-impact errors such as incorrectly deleting files. Our results indicate that experimental methodology from cognitive science can help characterize how machine learning systems behave.

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。

↑