Localize-Then-Decide Guarantees for LLM Judgments

• URL: http://arxiv.org/abs/2608.25824v1
• Date: Wed, 26 Aug 2026 14:04:37 GMT
• Title: Localize-Then-Decide Guarantees for LLM Judgments
• Abstract summary: Large language models (LLMs) are increasingly used as evaluators to assess output quality and preference alignment.<n>We propose a Localize-Then-Decide framework to provide high-probability agreement guarantees.<n>Our framework consistently achieves higher guarantee success rates and substantially higher coverage than single-stage baselines.
• Score: 20.020682117057238
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large language models (LLMs) are increasingly used as evaluators to assess output quality and preference alignment, yet providing reliable guarantees of agreement with human judgments remains challenging. Recent work introduces confidence-thresholding methods that provide such guarantees for pairwise comparisons, relying on the assumption that higher estimated confidence implies lower disagreement risk with humans. However, this assumption can break down when the number of candidate responses increases, since distributing probability mass across many alternatives can distort confidence estimates. To address this issue, we propose a Localize-Then-Decide framework. First, conformal prediction localizes a small shortlist that contains the human-preferred response with high probability. Then, a calibrated confidence-based rule selectively chooses a single response from this shortlist or abstains. This design restores the monotonic relationship between confidence and disagreement risk and enables high-probability agreement guarantees. Experiments with multiple candidate sizes across several datasets and judge LLMs demonstrate that our framework consistently achieves higher guarantee success rates and substantially higher coverage than single-stage baselines.

Related papers

• Uncertainty-Aware Abstention in Large Language Models with Provable Alignment Guarantees [0.5371337604556311]
  Large language models (LLMs) are increasingly deployed in question answering (QA) systems.<n>They may generate hallucinated or misaligned responses without reliable confidence estimates.<n>We propose CIC, a confidence-interval-based calibration framework that converts arbitrary uncertainty scores into risk-controlled selective answering rules.
  arXiv  Detail & Related papers  (2026-07-05T17:50:32Z)
• Margin-Adaptive Confidence Ranking for Reliable LLM Judgement [19.892445164810987]
  Jung et al. (2025) introduce a hypothesis testing framework for guaranteeing agreement between large language models and human judgments.<n>We learn a dedicated confidence estimator instead of relying on confidence signals.<n>When integrated into fixed-sequence testing, the learned confidence estimator yields improved ranking accuracy and empirically strengthens the monotonic relationship between confidence and disagreement risk.
  arXiv  Detail & Related papers  (2026-05-14T21:01:05Z)
• ORCE: Order-Aware Alignment of Verbalized Confidence in Large Language Models [17.761630515662947]
  We propose a decoupled and order-aware framework for verbalized confidence calibration.<n>Our method first generates an answer and then estimates confidence conditioned on the fixed question--answer pair.<n>Experiments show that our method improves calibration and failure prediction performance while largely preserving answer accuracy.
  arXiv  Detail & Related papers  (2026-05-12T17:39:43Z)
• Less Approximates More: Harmonizing Performance and Confidence Faithfulness via Hybrid Post-Training for High-Stakes Tasks [52.81286869496811]
  Large language models are increasingly deployed in high-stakes tasks, where confident yet incorrect inferences may cause real-world harm.<n>We propose to jointly optimize unsupervised Reinforcement Learning from Internal Feedback with reasoning-trace-guided Reasoning Distillation.<n>We introduce HyTuning, a hybrid post-training framework that adaptively reweights RD and RLIF via a PRG-style metric.
  arXiv  Detail & Related papers  (2026-04-09T16:50:11Z)
• Confidence Before Answering: A Paradigm Shift for Efficient LLM Uncertainty Estimation [47.91529693614168]
  Existing methods are predominantly answer-first, producing confidence only after generating an answer.<n>We study a confidence-first paradigm, where the model outputs its confidence before answering, interpreting this score as the model's probability of answering the question correctly.<n>We propose CoCA, a reinforcement learning framework that jointly optimize confidence calibration and answer accuracy via segmented credit assignment.
  arXiv  Detail & Related papers  (2026-03-06T04:03:13Z)
• Calibrating Verbalized Confidence with Self-Generated Distractors [24.56911906044891]
  We introduce Distractor-Normalized Coherence (DINCO)<n>DINCO estimates and accounts for an LLM's suggestibility bias by having the model its confidence independently across several self-generated distractors.<n>We frame the popular approach of self-consistency as leveraging coherence across sampled generations, and normalized verbalized confidence as leveraging coherence across validations on incompatible claims.
  arXiv  Detail & Related papers  (2025-09-29T21:41:22Z)
• Can Large Language Models Express Uncertainty Like Human? [71.27418419522884]
  We release the first diverse, large-scale dataset of hedging expressions with human-annotated confidence scores.<n>We conduct the first systematic study of linguistic confidence across modern large language models.
  arXiv  Detail & Related papers  (2025-09-29T02:34:30Z)
• Mind the Generation Process: Fine-Grained Confidence Estimation During LLM Generation [63.49409574310576]
  Large language models (LLMs) exhibit overconfidence, assigning high confidence scores to incorrect predictions.<n>We introduce FineCE, a novel confidence estimation method that delivers accurate, fine-grained confidence scores during text generation.<n>Our code and all baselines used in the paper are available on GitHub.
  arXiv  Detail & Related papers  (2025-08-16T13:29:35Z)
• COIN: Uncertainty-Guarding Selective Question Answering for Foundation Models with Provable Risk Guarantees [51.5976496056012]
  COIN is an uncertainty-guarding selection framework that calibrates statistically valid thresholds to filter a single generated answer per question.<n>COIN estimates the empirical error rate on a calibration set and applies confidence interval methods to establish a high-probability upper bound on the true error rate.<n>We demonstrate COIN's robustness in risk control, strong test-time power in retaining admissible answers, and predictive efficiency under limited calibration data.
  arXiv  Detail & Related papers  (2025-06-25T07:04:49Z)
• Trust or Escalate: LLM Judges with Provable Guarantees for Human Agreement [49.15348173246146]
  We present a principled approach to provide LLM-based evaluation with a rigorous guarantee of human agreement. We first propose that a reliable evaluation method should not uncritically rely on model preferences for pairwise evaluation. We then show that under this selective evaluation framework, human agreement can be provably guaranteed.
  arXiv  Detail & Related papers  (2024-07-25T20:04:59Z)
• When to Trust LLMs: Aligning Confidence with Response Quality [49.371218210305656]
  We propose CONfidence-Quality-ORDer-preserving alignment approach (CONQORD) It integrates quality reward and order-preserving alignment reward functions. Experiments demonstrate that CONQORD significantly improves the alignment performance between confidence and response accuracy.
  arXiv  Detail & Related papers  (2024-04-26T09:42:46Z)
• Think Twice Before Trusting: Self-Detection for Large Language Models through Comprehensive Answer Reflection [90.71323430635593]
  We propose a novel self-detection paradigm that considers the comprehensive answer space beyond LLM-generated answers. Building upon this paradigm, we introduce a two-step framework, which firstly instructs LLM to reflect and provide justifications for each candidate answer. This framework can be seamlessly integrated with existing approaches for superior self-detection.
  arXiv  Detail & Related papers  (2024-03-15T02:38:26Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.