再问一次，然后失败：大型语言模型在判断中的摇摆不定
Ask Again, Then Fail: Large Language Models' Vacillations in Judgment
AI总结：
本文针对大模型在后续提问中动摇正确判断的问题，提出后续提问机制与评估指标，并开发训练框架Unwavering-FQ以增强判断稳定性。
摘要：
我们观察到，当前对话式语言模型在面对后续提问时，即使最初的判断是正确的，也常常会在判断上产生动摇。这种摇摆对生成可靠响应和建立用户信任构成了重大挑战。为了全面评估这一问题，我们引入了一种后续提问机制（Follow-up Questioning Mechanism），并提出了两个量化这种不一致性的指标，证实了该问题在当前语言模型中广泛存在。为了缓解这一问题，我们探索了针对闭源模型的各种提示策略；此外，我们开发了一个基于训练的框架 Unwavering-FQ，通过合成的高质量偏好数据来教导语言模型保持其最初正确的判断。我们的实验结果证实了该框架的有效性及其提升模型通用能力的能力。
英文摘要：
We observe that current conversational language models often waver in their judgments when faced with follow-up questions, even if the original judgment was correct. This wavering presents a significant challenge for generating reliable responses and building user trust. To comprehensively assess this issue, we introduce a \textsc{Follow-up Questioning Mechanism} along with two metrics to quantify this inconsistency, confirming its widespread presence in current language models. To mitigate this issue, we explore various prompting strategies for closed-source models; moreover, we develop a training-based framework \textsc{Unwavering-FQ} that teaches language models to maintain their originally correct judgments through synthesized high-quality preference data. Our experimental results confirm the effectiveness of our framework and its ability to enhance the general capabilities of models.
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。
