Salvato in:
Dettagli Bibliografici
Autori principali: Tian, Zailong, Han, Zhuoheng, Chen, Yanzhe, Xu, Haozhe, Yang, Xi, Xuan, Richeng, Wang, Houfeng, Liao, Lizi
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:https://arxiv.org/abs/2508.06225
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866913995153211392
author Tian, Zailong
Han, Zhuoheng
Chen, Yanzhe
Xu, Haozhe
Yang, Xi
Xuan, Richeng
Wang, Houfeng
Liao, Lizi
author_facet Tian, Zailong
Han, Zhuoheng
Chen, Yanzhe
Xu, Haozhe
Yang, Xi
Xuan, Richeng
Wang, Houfeng
Liao, Lizi
contents Large Language Models (LLMs) are widely used as automated judges, where practical value depends on both accuracy and trustworthy, risk-aware judgments. Existing approaches predominantly focus on accuracy, overlooking the necessity of well-calibrated confidence, which is vital for adaptive and reliable evaluation pipelines. In this work, we advocate a shift from accuracy-centric evaluation to confidence-driven, risk-aware LLM-as-a-Judge systems, emphasizing the necessity of well-calibrated confidence for trustworthy and adaptive evaluation. We systematically identify the Overconfidence Phenomenon in current LLM-as-a-Judges, where predicted confidence significantly overstates actual correctness, undermining reliability in practical deployment. To quantify this phenomenon, we introduce TH-Score, a novel metric measuring confidence-accuracy alignment. Furthermore, we propose LLM-as-a-Fuser, an ensemble framework that transforms LLMs into reliable, risk-aware evaluators. Extensive experiments demonstrate that our approach substantially improves calibration and enables adaptive, confidence-driven evaluation pipelines, achieving superior reliability and accuracy compared to existing baselines.
format Preprint
id arxiv_https___arxiv_org_abs_2508_06225
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Overconfidence in LLM-as-a-Judge: Diagnosis and Confidence-Driven Solution
Tian, Zailong
Han, Zhuoheng
Chen, Yanzhe
Xu, Haozhe
Yang, Xi
Xuan, Richeng
Wang, Houfeng
Liao, Lizi
Artificial Intelligence
Large Language Models (LLMs) are widely used as automated judges, where practical value depends on both accuracy and trustworthy, risk-aware judgments. Existing approaches predominantly focus on accuracy, overlooking the necessity of well-calibrated confidence, which is vital for adaptive and reliable evaluation pipelines. In this work, we advocate a shift from accuracy-centric evaluation to confidence-driven, risk-aware LLM-as-a-Judge systems, emphasizing the necessity of well-calibrated confidence for trustworthy and adaptive evaluation. We systematically identify the Overconfidence Phenomenon in current LLM-as-a-Judges, where predicted confidence significantly overstates actual correctness, undermining reliability in practical deployment. To quantify this phenomenon, we introduce TH-Score, a novel metric measuring confidence-accuracy alignment. Furthermore, we propose LLM-as-a-Fuser, an ensemble framework that transforms LLMs into reliable, risk-aware evaluators. Extensive experiments demonstrate that our approach substantially improves calibration and enables adaptive, confidence-driven evaluation pipelines, achieving superior reliability and accuracy compared to existing baselines.
title Overconfidence in LLM-as-a-Judge: Diagnosis and Confidence-Driven Solution
topic Artificial Intelligence
url https://arxiv.org/abs/2508.06225