cs.SEOct 31, 2026

Architecting Fairness-Aware LLM Interactions

Authors: Alessandra Parziale, Valeria Pontillo, Fabio Palomba, Patrizio Pelliccione

Organizations: Gran Sasso Science Institute L’Aquila, Italy · University of Salerno Fisciano, Italy

Abstract

Large Language Models (LLMs) are increasingly used as decision-support tools but may generate stereotypical, discriminatory, or unfair responses. As LLMs become embedded in decision-critical software systems, fairness can no longer be treated as a downstream evaluation step, but must become an architectural concern of the interaction itself. Yet current fairness approaches operate as standalone evaluation techniques, lacking a reusable mechanism to verify and mitigate violations at runtime. We propose a fairness-assurance architecture grounded in three reusable design patterns, instantiated as a multi-agent framework that evaluates and iteratively refines LLM responses before delivery. A preliminary evaluation across eight configurations involving different LLM families shows that the architecture identifies fairness violations and iteratively produces compliant responses in all configurations, with behavior differing depending on the model-family composition. These results provide initial evidence for the joint instantiation of the proposed patterns and a first step toward architecting non-functional properties into LLM-based systems.

Figures & tables

Explore similar work

Feb 6, 2026

FairJudge: An Adaptive, Debiased, and Consistent LLM-as-a-Judge

Existing LLM-as-a-Judge systems suffer from three fundamental limitations: limited adaptivity to task- and domain-specific evaluation criteria, systematic biases driven by non-semantic cues such as position, length, format, and model provenance, and evaluation inconsistency that leads to contradictory judgments across different evaluation modes (e.g., pointwise versus pairwise). To address these issues, we propose FairJudge, an adaptive, debiased, and consistent LLM-as-a-Judge. Unlike prior approaches that treat the judge as a static evaluator, FairJudge models judging behavior itself as a learnable and regularized policy. From a data-centric perspective, we construct a high-information-density judging dataset that explicitly injects supervision signals aligned with evaluation behavior. Building on this dataset, we adopt a curriculum-style SFT-DPO-GRPO training paradigm that progressively aligns rubric adherence, bias mitigation, and cross-mode consistency, while avoiding catastrophic forgetting. Experimental results on multiple internal and public benchmarks show that FairJudge consistently improves agreement and F1, reduces non-semantic biases, and outperforms substantially larger instruction-tuned LLMs. All resources will be publicly released after acceptance to facilitate future research.
Feb 16, 2026

Counterfactual Fairness Evaluation of LLM-Based Contact Center Agent Quality Assurance System

Large Language Models (LLMs) are increasingly deployed in contact-center Quality Assurance (QA) to automate agent performance evaluation and coaching feedback. While LLMs offer unprecedented scalability and speed, their reliance on web-scale training data raises concerns regarding demographic and behavioral biases that may distort workforce assessment. We present a counterfactual fairness evaluation of LLM-based QA systems across 13 dimensions spanning three categories: Identity, Context, and Behavioral Style. Fairness is quantified using the Counterfactual Flip Rate (CFR), the frequency of binary judgment reversals, and the Mean Absolute Score Difference (MASD), the average shift in coaching or confidence scores across counterfactual pairs. Evaluating 18 LLMs on 3,000 real-world contact center transcripts, we find systematic disparities, with CFR ranging from 5.4% to 13.0% and consistent MASD shifts across confidence, positive, and improvement scores. Larger, more strongly aligned models show lower unfairness, though fairness does not track accuracy. Contextual priming of historical performance induces the most severe degradations (CFR up to 16.4%), while implicit linguistic identity cues remain a persistent bias source. Finally, we analyze the efficacy of fairness-aware prompting, finding that explicit instructions yield only modest improvements in evaluative consistency. Our findings underscore the need for standardized fairness auditing pipelines prior to deploying LLMs in high-stakes workforce evaluation.
Jan 6, 2026

Audit Me If You Can: Query-Efficient Active Fairness Auditing of Black-Box LLMs

Large Language Models (LLMs) exhibit systematic biases across demographic groups. Auditing is proposed as an accountability tool for black-box LLM applications, but suffers from resource-intensive query access. We conceptualise auditing as uncertainty estimation over a target fairness metric and introduce BAFA, the Bounded Active Fairness Auditor for query-efficient auditing of black-box LLMs. BAFA maintains a version space of surrogate models consistent with queried scores and computes uncertainty intervals for fairness metrics (e.g., ΔΔ AUC) via constrained empirical risk minimisation. Active query selection narrows these intervals to reduce estimation error. We evaluate BAFA on two standard fairness dataset case studies: CivilComments and Bias-in-Bios, comparing against stratified sampling, power sampling, and ablations. BAFA achieves target error thresholds with up to 40×\times fewer queries than stratified sampling (e.g., 144 vs 5,956 queries at ε=0.02\varepsilon=0.02 for CivilComments) for tight thresholds, demonstrates substantially better performance over time, and shows lower variance across runs. These results suggest that active sampling can reduce resources needed for independent fairness auditing with LLMs, supporting continuous model evaluations.