arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2405.13845cs.CLcs.AI
收藏

语义密度:通过语义空间中的置信度测量实现大语言模型的不确定性量化

Semantic Density: Uncertainty Quantification for Large Language Models through Confidence Measurement in Semantic Space

Cognizant AI Labs(高知特人工智能实验室);The University of Texas at Austin(德克萨斯大学奥斯汀分校)

Xin Qiu, Risto Miikkulainen

AI总结:

针对现有大语言模型不确定性量化方法的诸多局限,提出语义密度框架,从语义空间概率分布提取回复置信度,不受任务限制且开箱即用,实验验证其性能与鲁棒性优于现有方法。

摘要:

随着大语言模型(Large Language Models, LLMs)在各领域的广泛应用,由于其存在不可预测的幻觉及生成错误信息的倾向,人们对LLMs在安全关键场景中的可信度提出了担忧。现有LLMs不具备为其生成的每条回复提供不确定性/置信度指标的固有功能,导致可信度难以评估。尽管已有多项研究旨在开发LLM的不确定性量化方法,但这些方法存在根本性局限:例如仅适用于分类任务、需要额外的训练和数据、仅考虑词汇信息而非语义信息,且是针对提示而非针对回复的。本文提出了一个新框架以解决这些问题。语义密度(Semantic density)从语义空间的概率分布角度提取每条回复的不确定性/置信度信息,它不受任务类型限制,对新模型和新任务可“开箱即用”。在包括最新的Llama 3和Mixtral-8x22B模型在内的7个先进LLM上,针对4个自由形式问答基准开展的实验表明,与现有方法相比,语义密度具备更优的性能和鲁棒性。

英文摘要:

With the widespread application of Large Language Models (LLMs) to various domains, concerns regarding the trustworthiness of LLMs in safety-critical scenarios have been raised, due to their unpredictable tendency to hallucinate and generate misinformation. Existing LLMs do not have an inherent functionality to provide the users with an uncertainty/confidence metric for each response it generates, making it difficult to evaluate trustworthiness. Although several studies aim to develop uncertainty quantification methods for LLMs, they have fundamental limitations, such as being restricted to classification tasks, requiring additional training and data, considering only lexical instead of semantic information, and being prompt-wise but not response-wise. A new framework is proposed in this paper to address these issues. Semantic density extracts uncertainty/confidence information for each response from a probability distribution perspective in semantic space. It has no restriction on task types and is "off-the-shelf" for new models and tasks. Experiments on seven state-of-the-art LLMs, including the latest Llama 3 and Mixtral-8x22B models, on four free-form question-answering benchmarks demonstrate the superior performance and robustness of semantic density compared to prior approaches.

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。

↑