Enregistré dans:
Détails bibliographiques
Auteurs principaux: Sabir, Ahmed, Kängsepp, Markus, Sharma, Rajesh
Format: Preprint
Publié: 2026
Sujets:
Accès en ligne:https://arxiv.org/abs/2601.07806
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866911369941483520
author Sabir, Ahmed
Kängsepp, Markus
Sharma, Rajesh
author_facet Sabir, Ahmed
Kängsepp, Markus
Sharma, Rajesh
contents The increased use of Large Language Models (LLMs) in sensitive domains leads to growing interest in how their confidence scores correspond to fairness and bias. This study examines the alignment between LLM-predicted confidence and human-annotated bias judgments. Focusing on gender bias, the research investigates probability confidence calibration in contexts involving gendered pronoun resolution. The goal is to evaluate if calibration metrics based on predicted confidence scores effectively capture fairness-related disparities in LLMs. The results show that, among the six state-of-the-art models, Gemma-2 demonstrates the worst calibration according to the gender bias benchmark. The primary contribution of this work is a fairness-aware evaluation of LLMs' confidence calibration, offering guidance for ethical deployment. In addition, we introduce a new calibration metric, Gender-ECE, designed to measure gender disparities in resolution tasks.
format Preprint
id arxiv_https___arxiv_org_abs_2601_07806
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle The Confidence Trap: Gender Bias and Predictive Certainty in LLMs
Sabir, Ahmed
Kängsepp, Markus
Sharma, Rajesh
Computation and Language
Machine Learning
The increased use of Large Language Models (LLMs) in sensitive domains leads to growing interest in how their confidence scores correspond to fairness and bias. This study examines the alignment between LLM-predicted confidence and human-annotated bias judgments. Focusing on gender bias, the research investigates probability confidence calibration in contexts involving gendered pronoun resolution. The goal is to evaluate if calibration metrics based on predicted confidence scores effectively capture fairness-related disparities in LLMs. The results show that, among the six state-of-the-art models, Gemma-2 demonstrates the worst calibration according to the gender bias benchmark. The primary contribution of this work is a fairness-aware evaluation of LLMs' confidence calibration, offering guidance for ethical deployment. In addition, we introduce a new calibration metric, Gender-ECE, designed to measure gender disparities in resolution tasks.
title The Confidence Trap: Gender Bias and Predictive Certainty in LLMs
topic Computation and Language
Machine Learning
url https://arxiv.org/abs/2601.07806