# When to Invoke: Refining LLM Fairness with Toxicity Assessment

arXiv: https://arxiv.org/abs/2601.09250 · HTML: https://mlsanity.com/paper/2601.09250/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 31 of its 50 references that are in the map.
- First posted on arXiv 14 Jan 2026.

## Builds on (most cited first, 30 of 31)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [DeBERTa: Decoding-enhanced BERT with Disentangled Attention](https://mlsanity.com/paper/2006.03654/) (2020)
- [RealToxicityPrompts: Evaluating Neural Toxic Degeneration in Language Models](https://mlsanity.com/paper/2009.11462/) (2020)
- [DeBERTaV3: Improving DeBERTa using ELECTRA-Style Pre-Training with Gradient-Disentangled Embedding Sharing](https://mlsanity.com/paper/2111.09543/) (2021)
- [CrowS-Pairs: A Challenge Dataset for Measuring Social Biases in Masked Language Models](https://mlsanity.com/paper/2010.00133/) (2020)
- [BBQ: A Hand-Built Bias Benchmark for Question Answering](https://mlsanity.com/paper/2110.08193/) (2021)
- [Gender Bias in Coreference Resolution: Evaluation and Debiasing Methods](https://mlsanity.com/paper/1804.06876/) (2018)
- [Gender Bias in Coreference Resolution](https://mlsanity.com/paper/1804.09301/) (2018)
- [ToxiGen: A Large-Scale Machine-Generated Dataset for Adversarial and Implicit Hate Speech Detection](https://mlsanity.com/paper/2203.09509/) (2022)
- [Nuanced Metrics for Measuring Unintended Bias with Real Data for Text Classification](https://mlsanity.com/paper/1903.04561/) (2019)
- [True Few-Shot Learning with Language Models](https://mlsanity.com/paper/2105.11447/) (2021)
- [Latent Hatred: A Benchmark for Understanding Implicit Hate Speech](https://mlsanity.com/paper/2109.05322/) (2021)
- [HateBERT: Retraining BERT for Abusive Language Detection in English](https://mlsanity.com/paper/2010.12472/) (2020)
- [Societal Biases in Language Generation: Progress and Challenges](https://mlsanity.com/paper/2105.04054/) (2021)
- [A New Generation of Perspective API: Efficient Multilingual Character-level Transformers](https://mlsanity.com/paper/2202.11176/) (2022)
- [Towards Debiasing Sentence Representations](https://mlsanity.com/paper/2007.08100/) (2020)
- ["I'm sorry to hear that": Finding New Biases in Language Models with a Holistic Descriptor Dataset](https://mlsanity.com/paper/2205.09209/) (2022)
- [It's All in the Name: Mitigating Gender Bias with Name-Based Counterfactual Data Substitution](https://mlsanity.com/paper/1909.00871/) (2019)
- [Challenges in Automated Debiasing for Toxic Language Detection](https://mlsanity.com/paper/2102.00086/) (2021)
- [Reasoning Implicit Sentiment with Chain-of-Thought Prompting](https://mlsanity.com/paper/2305.11255/) (2023)
- [Handling Bias in Toxic Speech Detection: A Survey](https://mlsanity.com/paper/2202.00126/) (2022)
- [Human and LLM Biases in Hate Speech Annotations: A Socio-Demographic Analysis of Annotators and Targets](https://mlsanity.com/paper/2410.07991/) (2024)
- [FairGT: A Fairness-aware Graph Transformer](https://mlsanity.com/paper/2404.17169/) (2024)
- [Can LLMs Recognize Toxicity? A Structured Investigation Framework and Toxicity Metric](https://mlsanity.com/paper/2402.06900/) (2024)
- [ADEPT: A DEbiasing PrompT Framework](https://mlsanity.com/paper/2211.05414/) (2022)
- [Cultural Bias Matters: A Cross-Cultural Benchmark Dataset and Sentiment-Enriched Model for Understanding Multimodal Metaphors](https://mlsanity.com/paper/2506.06987/) (2025)
- [Assessing Classifier Fairness with Collider Bias](https://mlsanity.com/paper/2010.03933/) (2020)
- [Fairness Evaluation with Item Response Theory](https://mlsanity.com/paper/2411.02414/) (2024)
- [Unbiased Reasoning for Knowledge-Intensive Tasks in Large Language Models via Conditional Front-Door Adjustment](https://mlsanity.com/paper/2508.16910/) (2025)
- [Unified Game Moderation: Soft-Prompting and LLM-Assisted Label Transfer for Resource-Efficient Toxicity Detection](https://mlsanity.com/paper/2506.06347/) (2025)

## Built on by (most cited first, 2 of 2)

- [Examining Agents' Bias Amplification versus Suppression in Multi-Agent Systems](https://mlsanity.com/paper/2605.28098/) (2026)
- [Operational Evidence Gaps for LLMs in Fraud Detection and Trust-and-Safety Workflows](https://mlsanity.com/paper/2607.13078/) (2026)

## Abstract (arXiv)

Large Language Models (LLMs) are increasingly used for toxicity assessment in online moderation systems, where fairness across demographic groups is essential for equitable treatment. However, LLMs often produce inconsistent toxicity judgements for subtle expressions, particularly those involving implicit hate speech, revealing underlying biases that are difficult to correct through standard training. This raises a key question that existing approaches often overlook: when should corrective mechanisms be invoked to ensure fair and reliable assessments? To address this, we propose FairToT, an inference-time framework that enhances LLM fairness through prompt-guided toxicity assessment. FairToT identifies cases where demographic-related variation is likely to occur and determines when additional assessment should be applied. In addition, we introduce two interpretable fairness indicators that detect such cases and improve inference consistency without modifying model parameters. Experiments on benchmark datasets show that FairToT reduces group-level disparities while maintaining stable and reliable toxicity predictions, demonstrating that inference-time refinement offers an effective and practical approach for fairness improvement in LLM-based toxicity assessment systems. The source code can be found at https://aisuko.github.io/fair-tot/.