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 metric for each response it generates, making it difficult to evaluate trustworthiness. Although a number of works 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 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.

PDF

In Proceedings of the 38th Conference on Neural Information Processing Systems, 2024. (also arXiv:2405.13845).

@inproceedings{qiu:neurips24, title={Semantic Density: Uncertainty Quantification in Semantic Space for Large Language Models}, author={Xin Qiu and Risto Miikkulainen}, booktitle={Proceedings of the 38th Conference on Neural Information Processing Systems}, month={ }, note={(also arXiv:2405.13845)}, url="http://nn.cs.utexas.edu/?qiu:neurips24", year={2024} }