我们能信任大语言模型吗？通过知识迁移缓解大语言模型中的过度自信偏差
Can We Trust LLMs? Mitigate Overconfidence Bias in LLMs through Knowledge Transfer
AI总结：
本研究提出基于思维链的知识迁移方法，利用大模型推理微调小模型，以缓解过度自信偏差，实验显示相比普通和QA微调，关键指标平均提升55.3%和43.1%，增强了模型可信度与准确性。
摘要：
本研究探讨了缓解大语言模型（LLM）中的过度自信偏差，以提高其可靠性。我们引入了一种利用思维链（chain of thoughts）的知识迁移（KT）方法，其中“大”模型通过详细的、顺序的推理路径向“小”模型传授知识。该方法利用较大模型的高级推理能力来微调较小模型，使其能够生成更准确的预测并具有校准的置信度。使用多项选择题和情感分析任务在多个数据集上进行的实验评估表明，KT方法优于普通微调方法和问答对（QA）微调方法。在三个关键指标上取得了最显著的改进，其中KT方法相比普通方法和QA方法分别平均提升了55.3%和43.1%。这些发现强调了KT方法在增强模型可信度和准确性方面的潜力，能够在各种情境下提供与置信度水平良好匹配的精确输出。
英文摘要：
The study explores mitigating overconfidence bias in LLMs to improve their reliability. We introduce a knowledge transfer (KT) method utilizing chain of thoughts, where "big" LLMs impart knowledge to "small" LLMs via detailed, sequential reasoning paths. This method uses advanced reasoning of larger models to fine-tune smaller models, enabling them to produce more accurate predictions with calibrated confidence. Experimental evaluation using multiple-choice questions and sentiment analysis across diverse datasets demonstrated the KT method's superiority over the vanilla and question-answer pair (QA) fine-tuning methods. The most significant improvement in three key metrics, where the KT method outperformed the vanilla and QA methods by an average of 55.3% and 43.1%, respectively. These findings underscore the KT method's potential in enhancing model trustworthiness and accuracy, offering precise outputs with well-matched confidence levels across various contexts.
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。
