Related papers: Bias Testing and Mitigation in Black Box LLMs using Metamorphic Relations

Bias Testing and Mitigation in Black Box LLMs using Metamorphic Relations

URL: http://arxiv.org/abs/2512.00556v1
Date: Sat, 29 Nov 2025 16:56:38 GMT
Title: Bias Testing and Mitigation in Black Box LLMs using Metamorphic Relations
Authors: Sina Salimian, Gias Uddin, Sumon Biswas, Henry Leung,
Abstract summary: We propose a unified framework for both systematic bias evaluation and targeted mitigation.<n>Our approach introduces six novel Metamorphic Relations (MRs)<n>MRs transform direct bias-inducing inputs into semantically equivalent yet adversarially challenging variants.
Score: 12.095552079739933
License: http://creativecommons.org/licenses/by/4.0/
Abstract: The widespread deployment of Large Language Models (LLMs) has intensified concerns about subtle social biases embedded in their outputs. Existing guardrails often fail when faced with indirect or contextually complex bias-inducing prompts. To address these limitations, we propose a unified framework for both systematic bias evaluation and targeted mitigation. Our approach introduces six novel Metamorphic Relations (MRs) that, based on metamorphic testing principles, transform direct bias-inducing inputs into semantically equivalent yet adversarially challenging variants. These transformations enable an automated method for exposing hidden model biases: when an LLM responds inconsistently or unfairly across MR-generated variants, the underlying bias becomes detectable. We further show that the same MRs can be used to generate diverse bias-inducing samples for fine-tuning, directly linking the testing process to mitigation. Using six state-of-the-art LLMs - spanning open-source and proprietary models - and a representative subset of 385 questions from the 8,978-item BiasAsker benchmark covering seven protected groups, our MRs reveal up to 14% more hidden biases compared to existing tools. Moreover, fine-tuning with both original and MR-mutated samples significantly enhances bias resiliency, increasing safe response rates from 54.7% to over 88.9% across models. These results highlight metamorphic relations as a practical mechanism for improving fairness in conversational AI.

Related papers

Silenced Biases: The Dark Side LLMs Learned to Refuse [5.2630646053506345]
We introduce the concept of silenced biases, which are unfair preferences encoded within models' latent space.<n>We propose the Silenced Bias Benchmark (SBB), which aims to uncover these biases by employing activation steering.
arXiv Detail & Related papers (2025-11-05T11:24:50Z)
Adaptive Generation of Bias-Eliciting Questions for LLMs [18.608477560948003]
Large language models (LLMs) are now widely deployed in user-facing applications, reaching hundreds of millions worldwide.<n>We introduce a counterfactual bias evaluation framework that automatically generates realistic, open-ended questions over sensitive attributes such as sex, race, or religion.<n>We also capture distinct response dimensions that are increasingly relevant in user interactions, such as asymmetric refusals and explicit acknowledgment of bias.
arXiv Detail & Related papers (2025-10-14T13:08:10Z)
BiasFreeBench: a Benchmark for Mitigating Bias in Large Language Model Responses [32.58830706120845]
Existing studies on bias mitigation methods for large language models (LLMs) use diverse baselines and metrics to evaluate debiasing performance.<n>We introduce BiasFreeBench, an empirical benchmark that comprehensively compares eight mainstream bias mitigation techniques.<n>We will publicly release our benchmark, aiming to establish a unified testbed for bias mitigation research.
arXiv Detail & Related papers (2025-09-30T19:56:54Z)
From Harm to Help: Turning Reasoning In-Context Demos into Assets for Reasoning LMs [58.02809208460186]
We revisit this paradox using high-quality traces from DeepSeek-R1 as demonstrations.<n>We find that adding more exemplars consistently degrades accuracy, even when demonstrations are optimal.<n>We introduce Insight-to-solve (I2S), a sequential test-time procedure that turns demonstrations into explicit, reusable insights.
arXiv Detail & Related papers (2025-09-27T08:59:31Z)
Meta-Fair: AI-Assisted Fairness Testing of Large Language Models [2.9632404823837777]
Fairness is a core principle in the development of Artificial Intelligence (AI) systems.<n>Current approaches to fairness testing in large language models (LLMs) often rely on manual evaluation, fixed templates, deterministics, and curated datasets.<n>This work aims to lay the groundwork for a novel, automated method for testing fairness in LLMs.
arXiv Detail & Related papers (2025-07-03T11:20:59Z)
Judging with Many Minds: Do More Perspectives Mean Less Prejudice? On Bias Amplifications and Resistance in Multi-Agent Based LLM-as-Judge [70.89799989428367]
We conduct a systematic analysis of four diverse bias types: position bias, verbosity bias, chain-of-thought bias, and bandwagon bias.<n>We evaluate these biases across two widely adopted multi-agent LLM-as-Judge frameworks: Multi-Agent-Debate and LLM-as-Meta-Judge.
arXiv Detail & Related papers (2025-05-26T03:56:41Z)
Metamorphic Testing for Fairness Evaluation in Large Language Models: Identifying Intersectional Bias in LLaMA and GPT [2.380039717474099]
Large Language Models (LLMs) have made significant strides in Natural Language Processing but remain vulnerable to fairness-related issues.<n>This paper introduces a metamorphic testing approach to systematically identify fairness bugs in LLMs.
arXiv Detail & Related papers (2025-04-04T21:04:14Z)
Exploring Response Uncertainty in MLLMs: An Empirical Evaluation under Misleading Scenarios [49.53589774730807]
Multimodal large language models (MLLMs) have recently achieved state-of-the-art performance on tasks ranging from visual question answering to video understanding.<n>We reveal a response uncertainty phenomenon: twelve state-of-the-art open-source MLLMs overturn a previously correct answer in 65% of cases after receiving a single deceptive cue.
arXiv Detail & Related papers (2024-11-05T01:11:28Z)
Cycles of Thought: Measuring LLM Confidence through Stable Explanations [53.15438489398938]
Large language models (LLMs) can reach and even surpass human-level accuracy on a variety of benchmarks, but their overconfidence in incorrect responses is still a well-documented failure mode. We propose a framework for measuring an LLM's uncertainty with respect to the distribution of generated explanations for an answer.
arXiv Detail & Related papers (2024-06-05T16:35:30Z)
Take Care of Your Prompt Bias! Investigating and Mitigating Prompt Bias in Factual Knowledge Extraction [56.17020601803071]
Recent research shows that pre-trained language models (PLMs) suffer from "prompt bias" in factual knowledge extraction. This paper aims to improve the reliability of existing benchmarks by thoroughly investigating and mitigating prompt bias.
arXiv Detail & Related papers (2024-03-15T02:04:35Z)
ReEval: Automatic Hallucination Evaluation for Retrieval-Augmented Large Language Models via Transferable Adversarial Attacks [91.55895047448249]
This paper presents ReEval, an LLM-based framework using prompt chaining to perturb the original evidence for generating new test cases. We implement ReEval using ChatGPT and evaluate the resulting variants of two popular open-domain QA datasets. Our generated data is human-readable and useful to trigger hallucination in large language models.
arXiv Detail & Related papers (2023-10-19T06:37:32Z)
ADEPT: A DEbiasing PrompT Framework [64.54665501064659]
Finetuning is an applicable approach for debiasing contextualized word embeddings.<n> discrete prompts with semantic meanings have shown to be effective in debiasing tasks.<n>We propose ADEPT, a method to debias PLMs using prompt tuning while maintaining the delicate balance between removing biases and ensuring representation ability.
arXiv Detail & Related papers (2022-11-10T08:41:40Z)

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