Document detail
ID
oai:arXiv.org:2409.00352
Topic
Computer Science - Computation and... Computer Science - Machine Learnin...Author
Oh, Hongseok Hwang, WonseokCategory
Computer Science
Year
2024
listing date
2/12/2025
Keywords
calibration analysisAbstract
Large Language Models (LLMs) have shown remarkable progress, but their real-world application necessitates reliable calibration.
This study conducts a comprehensive analysis of calibration degradation of LLMs across four dimensions: models, calibration metrics, tasks, and confidence extraction methods.
Initial analysis showed that the relationship between alignment and calibration is not always a trade-off, but under stricter analysis conditions, we found the alignment process consistently harms calibration.
This highlights the need for (1) a careful approach when measuring model confidences and calibration errors and (2) future research into algorithms that can help LLMs to achieve both instruction-following and calibration without sacrificing either.
;Comment: Presented at the BlackboxNLP Workshop at EMNLP 2024 (Poster)
Oh, Hongseok,Hwang, Wonseok, 2024, Does Alignment Tuning Really Break LLMs' Internal Confidence?
Projection-Specific Heterogeneity of the Axon Initial Segment of Pyramidal Neurons in the Prelimbic Cortex
heterogeneity projection-specific
