# Overconfidence in LLM-as-a-Judge: Diagnosis and Confidence-Driven Solution

arXiv: https://arxiv.org/abs/2508.06225 · HTML: https://mlsanity.com/paper/2508.06225/

## Key facts

- Cited by 18 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 26 references that are in the map.
- First posted on arXiv 8 Aug 2025.

## Builds on (most cited first, 16 of 16)

- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [On Calibration of Modern Neural Networks](https://mlsanity.com/paper/1706.04599/) (2017)
- [A Survey on LLM-as-a-Judge](https://mlsanity.com/paper/2411.15594/) (2024)
- [Calibrate Before Use: Improving Few-Shot Performance of Language Models](https://mlsanity.com/paper/2102.09690/) (2021)
- [Large Language Models are not Fair Evaluators](https://mlsanity.com/paper/2305.17926/) (2023)
- [LLMs-as-Judges: A Comprehensive Survey on LLM-based Evaluation Methods](https://mlsanity.com/paper/2412.05579/) (2024)
- [JudgeLM: Fine-tuned Large Language Models are Scalable Judges](https://mlsanity.com/paper/2310.17631/) (2023)
- [JudgeBench: A Benchmark for Evaluating LLM-based Judges](https://mlsanity.com/paper/2410.12784/) (2024)
- [PandaLM: An Automatic Evaluation Benchmark for LLM Instruction Tuning Optimization](https://mlsanity.com/paper/2306.05087/) (2023)
- [Evaluating Large Language Models at Evaluating Instruction Following](https://mlsanity.com/paper/2310.07641/) (2023)
- [Agent-as-a-Judge: Evaluate Agents with Agents](https://mlsanity.com/paper/2410.10934/) (2024)
- [Reducing conversational agents' overconfidence through linguistic calibration](https://mlsanity.com/paper/2012.14983/) (2020)
- [Meta-Rewarding Language Models: Self-Improving Alignment with LLM-as-a-Meta-Judge](https://mlsanity.com/paper/2407.19594/) (2024)
- [Navigating the Grey Area: How Expressions of Uncertainty and Overconfidence Affect Language Models](https://mlsanity.com/paper/2302.13439/) (2023)
- [Confidence Calibration and Rationalization for LLMs via Multi-Agent Deliberation](https://mlsanity.com/paper/2404.09127/) (2024)
- [Generation Meets Verification: Accelerating Large Language Model Inference with Smart Parallel Auto-Correct Decoding](https://mlsanity.com/paper/2402.11809/) (2024)

## Built on by (most cited first, 18 of 18)

- [Calibrating LLM Judges: Linear Probes for Fast and Reliable Uncertainty Estimation](https://mlsanity.com/paper/2512.22245/) (2025)
- [Agentic Uncertainty Reveals Agentic Overconfidence](https://mlsanity.com/paper/2602.06948/) (2026)
- [KnowGuard: Knowledge-Driven Abstention for Multi-Round Clinical Reasoning](https://mlsanity.com/paper/2509.24816/) (2025)
- [Efficient Inference for Noisy LLM-as-a-Judge Evaluation](https://mlsanity.com/paper/2601.05420/) (2026)
- [Guideline-Grounded Evidence Accumulation for High-Stakes Agent Verification](https://mlsanity.com/paper/2603.02798/) (2026)
- [Semantic Intent Fragmentation: A Single-Shot Compositional Attack on Multi-Agent AI Pipelines](https://mlsanity.com/paper/2604.08608/) (2026)
- [Calibrate, Don't Curate: Label-Efficient Estimation from Noisy LLM Judges](https://mlsanity.com/paper/2605.09702/) (2026)
- [Same Attention, Different Truths: Put Logit-Lens over Visual Attention to Detect and Mitigate LVLM Object Hallucination](https://mlsanity.com/paper/2608.07302/) (2026)
- [Another Turn, Better Output? A Turn-Wise Analysis of Iterative LLM Prompting](https://mlsanity.com/paper/2509.06770/) (2025)
- [Rewarding the Journey, Not Just the Destination: A Composite Path and Answer Self-Scoring Reward Mechanism for Test-Time Reinforcement Learning](https://mlsanity.com/paper/2510.17923/) (2025)
- [The Chameleon Nature of LLMs: Quantifying Multi-Turn Stance Instability in Search-Enabled Language Models](https://mlsanity.com/paper/2510.16712/) (2025)
- [Self-signals Driven Multi-LLM Debate for Efficient and Accurate Reasoning](https://mlsanity.com/paper/2510.06843/) (2025)
- [Completing Missing Annotation: Multi-Agent Debate for Accurate and Scalable Relevant Assessment for IR Benchmarks](https://mlsanity.com/paper/2602.06526/) (2026)
- [Bayesian Elicitation with LLMs: Model Size Helps, Extra "Reasoning" Doesn't Always](https://mlsanity.com/paper/2604.01896/) (2026)
- [VERDI: Single-Call Confidence Estimation for Verification-Based LLM Judges via Decomposed Inference](https://mlsanity.com/paper/2605.11334/) (2026)
- [Different Teachers, Different Capabilities: Sub-1B On-Device Distillation for Structured Text Enrichment](https://mlsanity.com/paper/2607.08268/) (2026)
- [When Accuracy Gaps Fail to Certify: Auditing Cross-Domain Recalibration of LLM Judges](https://mlsanity.com/paper/2609.27954/) (2026)
- [A CaLLM Judge is a Better Judge: Mitigating Bias in LLM-as-a-judge](https://mlsanity.com/paper/2610.18108/) (2026)

## Abstract (arXiv)

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.