Fairness Evaluation and Inference Level Mitigation in LLMs

arXiv:2510.18914v4 Announce Type: replace-cross Abstract: Large language models often display undesirable behaviors embedded in their internal representations, undermining fairness, inconsistency drift, amplification of harmful content, and the propagation of unwanted patterns during extended dialogue and conversations. Although training-time or data-centric methods attempt to reduce these effects, they are computationally expensive, irreversible once deployed, and slow to adapt to new conversational contexts. Pruning-based methods provide a flexible and transparent way to reduce bias by adjusting the neurons responsible for certain behaviors. However, most existing approaches are static; once a neuron is removed, the model loses the ability to adapt when the conversation or context changes. To address this, we propose a dynamic, reversible, pruning-based framework that detects context-aware neuron activations and applies adaptive masking to modulate their influence during generation. Our inference-time solution provides fine-grained, memory-aware mitigation with knowledge-preserved, more coherent behavior across multilingual single- and multi-turn dialogues, enabling dynamic fairness control in real-world conversational AI.

Related

• FineSteer: A Unified Framework for Fine-Grained Inference-Time Steering in Large Language Models
• Deliberative Alignment is Deep, but Uncertainty Remains: Inference time safety improvement in reasoning via attribution of unsafe behavior to base model
• Large Language Models Generate Harmful Content Using a Distinct, Unified Mechanism
• ASGuard: Activation-Scaling Guard to Mitigate Targeted Jailbreaking Attack

Source: arXiv cs.AI | 2026-04-24