# Judge, Retrieve, or Abstain: Uncertainty-Guarded LLM Judging with Provable Risk Guarantees

arXiv: https://arxiv.org/abs/2608.17994 · HTML: https://mlsanity.com/paper/2608.17994/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 28 of its 35 references that are in the map.
- First posted on arXiv 18 Aug 2026.

## Builds on (most cited first, 28 of 28)

- [Self-Consistency Improves Chain of Thought Reasoning in Language Models](https://mlsanity.com/paper/2203.11171/) (2022)
- [HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering](https://mlsanity.com/paper/1809.09600/) (2018)
- [TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension](https://mlsanity.com/paper/1705.03551/) (2017)
- [G-Eval: NLG Evaluation using GPT-4 with Better Human Alignment](https://mlsanity.com/paper/2303.16634/) (2023)
- [A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions](https://mlsanity.com/paper/2311.05232/) (2023)
- [A Survey on LLM-as-a-Judge](https://mlsanity.com/paper/2411.15594/) (2024)
- [A Gentle Introduction to Conformal Prediction and Distribution-Free Uncertainty Quantification](https://mlsanity.com/paper/2107.07511/) (2021)
- [Can Large Language Models Be an Alternative to Human Evaluations?](https://mlsanity.com/paper/2305.01937/) (2023)
- [Active Retrieval Augmented Generation](https://mlsanity.com/paper/2305.06983/) (2023)
- [JudgeBench: A Benchmark for Evaluating LLM-based Judges](https://mlsanity.com/paper/2410.12784/) (2024)
- [Conformal Risk Control](https://mlsanity.com/paper/2208.02814/) (2022)
- [R-Judge: Benchmarking Safety Risk Awareness for LLM Agents](https://mlsanity.com/paper/2401.10019/) (2024)
- [Long-form factuality in large language models](https://mlsanity.com/paper/2403.18802/) (2024)
- [AutoMix: Automatically Mixing Language Models](https://mlsanity.com/paper/2310.12963/) (2023)
- [Know Your Limits: A Survey of Abstention in Large Language Models](https://mlsanity.com/paper/2407.18418/) (2024)
- [A Survey on Uncertainty Quantification of Large Language Models: Taxonomy, Open Research Challenges, and Future Directions](https://mlsanity.com/paper/2412.05563/) (2024)
- [Trust or Escalate: LLM Judges with Provable Guarantees for Human Agreement](https://mlsanity.com/paper/2407.18370/) (2024)
- [Large Language Models Must Be Taught to Know What They Don't Know](https://mlsanity.com/paper/2406.08391/) (2024)
- [ConU: Conformal Uncertainty in Large Language Models with Correctness Coverage Guarantees](https://mlsanity.com/paper/2407.00499/) (2024)
- [Can You Trust LLM Judgments? Reliability of LLM-as-a-Judge](https://mlsanity.com/paper/2412.12509/) (2024)
- [Improving Automatic VQA Evaluation Using Large Language Models](https://mlsanity.com/paper/2310.02567/) (2023)
- [Reference-Guided Verdict: LLMs-as-Judges in Automatic Evaluation of Free-Form QA](https://mlsanity.com/paper/2408.09235/) (2024)
- [SConU: Selective Conformal Uncertainty in Large Language Models](https://mlsanity.com/paper/2504.14154/) (2025)
- [COIN: Uncertainty-Guarding Selective Question Answering for Foundation Models with Provable Risk Guarantees](https://mlsanity.com/paper/2506.20178/) (2025)
- [SCOPE: Selective Conformal Optimized Pairwise LLM Judging](https://mlsanity.com/paper/2602.13110/) (2026)
- [SAFER: Risk-Constrained Sample-then-Filter in Large Language Models](https://mlsanity.com/paper/2510.10193/) (2025)
- [CLEV: LLM-Based Evaluation Through Lightweight Efficient Voting for Free-Form Question-Answering](https://mlsanity.com/paper/2503.08542/) (2025)
- [SAGE: A Search-AuGmented Evaluation of Large Language Models on Free-Form QA](https://mlsanity.com/paper/2504.07385/) (2025)

## Built on by (most cited first, 2 of 2)

- [From Migration to Calibration: Aligning Agents with Deployment Requirements](https://mlsanity.com/paper/2609.35149/) (2026)
- [Can We Trust This Evaluation? Instance-Level Reliability of LLM-as-a-Judge](https://mlsanity.com/paper/2610.14029/) (2026)

## Abstract (arXiv)

Using LLMs as judges has become standard practice for evaluating model outputs at scale. This is particularly common for subjective, open-ended tasks such as assessing helpfulness or alignment, where no single reference answer exists. However, objective tasks introduce a distinct reliability challenge for reference-free LLM judging. In the absence of a reference answer, the judge evaluates factual correctness either through its parametric knowledge or through tool augmentation. Although the former enables efficient evaluation, the judge may hallucinate or lack sufficient evidence for its verdict. Conversely, tool augmentation can provide additional evidence but introduces extra computational cost and requires an appropriate mechanism to determine when and how that evidence should be used reliably. More importantly, neither approach alone provides formal control over the risk of accepted verdicts or guarantees their reliability at a specified level. We propose a risk-controlled framework that calibrates uncertainty thresholds on a held-out set so that the false discovery rate among accepted verdicts remains below a user-specified level~α with high probability, using finite-sample Clopper--Pearson intervals. When the parametric mode is not sufficiently confident, the instance is routed to a retrieval-augmented mode, where the judge gathers web evidence and re-evaluates the instance under a second calibrated threshold. The finite-sample guarantee carries over to this two-threshold routing without additional assumptions. Across open-domain QA benchmarks and judges of varying scales, the framework maintains the target error rate while achieving substantially higher coverage than single-mode baselines.