← Back to all news
arXiv Computation and Language

Localize-Then-Decide Guarantees for LLM Judgments

Large language models (LLMs) are increasingly used to evaluate output quality, but guaranteeing agreement with human judgments is difficult. The paper introduces a Localize-Then-Decide framework that first uses conformal prediction to narrow down a shortlist likely to contain the human-preferred response, then applies a calibrated confidence rule to select a single response or abstain. Experiments show this two-stage approach consistently yields higher guarantee success rates and greater coverage than single-stage baselines across various candidate sizes and datasets.

Related stories

arXiv AI
Aug 19

SCOPE: Selective Conformal Optimized Pairwise LLM Judging

SCOPE is a framework that calibrates an acceptance threshold for large language models used as pairwise judges, ensuring that the error rate among non-abstained judgments does not exceed a user-specified level α. It introduces Bidirectional Preference Entropy (BPE) to provide a bias-neutral uncertainty signal by querying the judge in both response positions and converting the averaged preference probability into an entropy-based score. Across multiple pairwise judging benchmarks, BPE outperforms standard confidence proxies in calibration and discrimination, while SCOPE consistently meets the target risk bound (empirical FDR ≈0.097–0.099 at α=0.10) and retains substantial coverage, accepting up to 2.4× more judgments under the same risk constraint.

By Sher Badshah, Ali Emami, Hassan Sajjad
llmsbenchmarkssafety
More like this →
arXiv AI
Sep 28

DIAL: Position-Debiased LLM Judges with Adaptive Human Preference Calibration

The paper introduces DIAL, a framework that uses large language models (LLMs) as judges while mitigating position bias and aligning their judgments with human preferences. DIAL separates judge‑specific position effects, learns shared structure in debiased LLM preferences, and adaptively calibrates this structure toward human targets using limited human comparisons. Experiments on simulations and three human‑preference benchmarks show that DIAL remains robust to unbalanced response order, achieves strong human‑aligned rankings with few labels, and adapts when LLM information is imperfect, supported by a real‑data study of over 410K judgments from 21 LLM judges.

By Zesheng Cai, Yingqi Fan, Sichang Chen, Jin-Hong Du
llmsbenchmarkssafety
More like this →
arXiv Computation and Language
Sep 7

A Calibrated Reflection Approach for Enhancing Confidence Estimation in LLMs

The paper introduces a Calibrated Reflection approach to improve confidence estimation in Large Language Models (LLMs). It combines structured reasoning with a distance‑aware calibration technique, featuring a Maximum Confidence Selection method, a reflection‑based prompting mechanism, and an ordinal‑aware calibration strategy. Experiments on datasets such as HelpSteer2, Llama T‑REx, and a proprietary conversational set show the method works for both conversational and fact‑based classification tasks.

By Umesh Bodhwani, Yuan Ling, Shujing Dong, Yarong Feng, Hongfei Li, Ayush Goyal
llms
More like this →
arXiv Computation and Language
Aug 28

The Score Granularity Gap in Black-Box LLM Classification: A Comparative Study of Confidence Constructions

The paper investigates the "score granularity gap" in black-box large language model (LLM) classifiers, asking how finely a confidence score can be thresholded for deployment. By comparing seven confidence construction methods across 25 model-dataset pairs, the authors find that single-shot verbalized confidence, when properly converted to a probability, ranks well but offers only a few distinct threshold values, limiting operational flexibility. The study also shows that multi-query aggregation can improve weak models but may harm strong ones, and provides concrete guidance for deployment trade-offs.

By Ao Sun, Tian Sun, Jiaxing Geng
llmsbenchmarks
More like this →