Calibrating Large Language Models with Sample Consistency
Accurately gauging the confidence level of Large Language Models' (LLMs) predictions is pivotal for their reliable application. However, LLMs are often uncalibrated inherently and elude conventional calibration techniques due to their proprietary nature and massive scale. In this work, we explore the potential of deriving confidence from the distribution of multiple randomly sampled model generations, via three measures of consistency. We perform an extensive evaluation across various open and closed-source models on nine reasoning datasets. Results show that consistency-based calibration methods outperform existing post-hoc approaches. Meanwhile, we find that factors such as intermediate explanations, model scaling, and larger sample sizes enhance calibration, while instruction-tuning makes calibration more difficult. Moreover, confidence scores obtained from consistency have the potential to enhance model performance. Finally, we offer practical guidance on choosing suitable consistency metrics for calibration, tailored to the characteristics of various LMs.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Calibrating Likelihoods towards Consistency in Summarization Models
Despite the recent advances in abstractive text summarization, current summarization models still suffer from generating factually inconsistent summaries, reducing their utility for real-world application. We argue that …
Abstractive Text SummarizationNatural Language InferenceText SummarizationCalibrating Uncertainty Quantification of Multi-Modal LLMs using Grounding
We introduce a novel approach for calibrating uncertainty quantification (UQ) tailored for multi-modal large language models (LLMs). Existing state-of-the-art UQ methods rely on consistency among multiple responses gener…
Medical Question AnsweringQuestion AnsweringUncertainty QuantificationVisual Question AnsweringWho Gets the Kidney? Human-AI Alignment, Indecision, and Moral Values
The rapid integration of Large Language Models (LLMs) in high-stakes decision-making -- such as allocating scarce resources like donor organs -- raises critical questions about their alignment with human moral values. We…
Decision MakingAre Knowledge and Reference in Multilingual Language Models Cross-Lingually Consistent?
Cross-lingual consistency should be considered to assess cross-lingual transferability, maintain the factuality of the model knowledge across languages, and preserve the parity of language model performance. We are thus …
Word AlignmentCalibrating Verbalized Confidence with Self-Generated Distractors
Calibrated confidence estimates are necessary for large language model (LLM) outputs to be trusted by human users. While LLMs can express their confidence in human-interpretable ways, verbalized LLM-generated confidence …