Pareto Optimal Learning for Estimating Large Language Model Errors
This addresses the challenge of quantifying errors in LLMs for applications requiring precise answers, representing an incremental advancement in error estimation techniques.
The paper tackles the problem of estimating error rates in Large Language Models (LLMs) by developing a Pareto optimization-based method that generates risk scores, which are shown to correlate well with true error rates and improve LLM performance when combined with prompting strategies.
Large Language Models (LLMs) have shown impressive abilities in many applications. When a concrete and precise answer is desired, it is important to have a quantitative estimation of the potential error rate. However, this can be challenging due to the text-in-text-out nature of generative models. We present a method based on Pareto optimization that generates a risk score to estimate the probability of error in an LLM response by integrating multiple sources of information. We prove theoretically that the error estimator optimized in our framework aligns with the LLM and the information sources in an Pareto optimal manner. Experimental results show that the risk scores estimated by our method are well correlated with the true LLM error rate, thus facilitating error correction. By dynamically combining with prompting strategies such as self-verification and information retrieval, we demonstrate the proposed method can be utilized to increase the performance of an LLM, surpassing state-of-the-art task specific models.