An Efficient and Modular Framework for Targeted Harm Mitigation in LLMS

• URL: http://arxiv.org/abs/2609.13624v1
• Date: Sat, 12 Sep 2026 00:24:49 GMT
• Title: An Efficient and Modular Framework for Targeted Harm Mitigation in LLMS
• Abstract summary: Large Language Models (LLMs) are powerful zero-shot learners but remain prone to misalignment with human preferences.<n>We propose a modular correction framework that augments pretrained LLMs with Activated LoRA adapters and a context-aware routing mechanism.
• Score: 3.37470725921294
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large Language Models (LLMs) are powerful zero-shot learners but remain prone to misalignment with human preferences, often producing biased, toxic, or otherwise harmful outputs. Existing alignment methods, while effective, are costly and tightly coupled to the model, limiting flexibility and scalability. We propose a modular correction framework that augments pretrained LLMs with Activated LoRA (aLoRA) adapters and a context-aware routing mechanism to eliminate harms from misaligned model responses. Our approach enables expert adapters to activate mid-sequence without invalidating the KV cache, allowing low-latency, targeted correction during generation. Each expert is trained to detect and mitigate specific harms, such as bias or toxicity. A learned router dynamically selects appropriate experts based on the models intermediate outputs. We demonstrate that our system improves alignment on standard safety benchmarks while preserving task performance, offering a lightweight and efficient path toward safer and more controllable LLM deployments.

Related papers

• Distilling Safe LLM Systems via Soft Prompts for On Device Settings [15.154042788412879]
  This paper presents a study of parameter-efficient safety alignment methods for resource-constrained settings.<n>We identify that soft prompts combined with distillation-based training consistently outperform alternative methods.
  arXiv  Detail & Related papers  (2026-06-08T12:03:51Z)
• RISER: Orchestrating Latent Reasoning Skills for Adaptive Activation Steering [62.63376387138257]
  We propose a plug-and-play intervention framework that adaptively steers large language models (LLMs) reasoning in activation space.<n>RISER constructs a library of reusable reasoning vectors and employs a lightweight Router to dynamically compose them for each input.<n>The Router is optimized via reinforcement learning under task-level rewards, activating latent cognitive primitives in an emergent and compositional manner.
  arXiv  Detail & Related papers  (2026-01-14T08:04:33Z)
• Taxonomy-Adaptive Moderation Model with Robust Guardrails for Large Language Models [3.710103086278309]
  Large Language Models (LLMs) are typically aligned for safety during the post-training phase.<n>They may still generate inappropriate outputs that could potentially pose risks to users.<n>This challenge underscores the need for robust safeguards that operate across both model inputs and outputs.
  arXiv  Detail & Related papers  (2025-12-05T00:43:55Z)
• SEQR: Secure and Efficient QR-based LoRA Routing [53.52716967527183]
  Low-Rank Adaptation (LoRA) has become a standard technique for parameter-efficient fine-tuning of large language models.<n> Efficiently selecting the correct LoRA adapter for a given input remains a challenge.<n>We introduce SEQR, an unsupervised LoRA routing algorithm designed to maximize efficiency while providing strict routing guarantees.
  arXiv  Detail & Related papers  (2025-09-22T17:59:38Z)
• Attribution-guided Pruning for Compression, Circuit Discovery, and Targeted Correction in LLMs [15.23174472320989]
  Large Language Models (LLMs) are central to many contemporary AI applications.<n>Recent works in eXplainable AI (XAI) suggest that interpretability can also enable model compression.
  arXiv  Detail & Related papers  (2025-06-16T17:38:36Z)
• Robust Anti-Backdoor Instruction Tuning in LVLMs [53.766434746801366]
  We introduce a lightweight, certified-agnostic defense framework for large visual language models (LVLMs)<n>Our framework finetunes only adapter modules and text embedding layers under instruction tuning.<n>Experiments against seven attacks on Flickr30k and MSCOCO demonstrate that ours reduces their attack success rate to nearly zero.
  arXiv  Detail & Related papers  (2025-06-04T01:23:35Z)
• Guiding Giants: Lightweight Controllers for Weighted Activation Steering in LLMs [8.085475675888045]
  Activation steering provides an alternative for inference-time control.<n>We introduce a novel approach using a lightweight, trainable controller network integrated during inference.
  arXiv  Detail & Related papers  (2025-05-22T01:48:38Z)
• Attribute Controlled Fine-tuning for Large Language Models: A Case Study on Detoxification [76.14641982122696]
  We propose a constraint learning schema for fine-tuning Large Language Models (LLMs) with attribute control. We show that our approach leads to an LLM that produces fewer inappropriate responses while achieving competitive performance on benchmarks and a toxicity detection task.
  arXiv  Detail & Related papers  (2024-10-07T23:38:58Z)
• RigorLLM: Resilient Guardrails for Large Language Models against Undesired Content [62.685566387625975]
  Current mitigation strategies, while effective, are not resilient under adversarial attacks. This paper introduces Resilient Guardrails for Large Language Models (RigorLLM), a novel framework designed to efficiently moderate harmful and unsafe inputs.
  arXiv  Detail & Related papers  (2024-03-19T07:25:02Z)
• InferAligner: Inference-Time Alignment for Harmlessness through Cross-Model Guidance [56.184255657175335]
  We develop textbfInferAligner, a novel inference-time alignment method that utilizes cross-model guidance for harmlessness alignment. Experimental results show that our method can be very effectively applied to domain-specific models in finance, medicine, and mathematics. It significantly diminishes the Attack Success Rate (ASR) of both harmful instructions and jailbreak attacks, while maintaining almost unchanged performance in downstream tasks.
  arXiv  Detail & Related papers  (2024-01-20T10:41:03Z)

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

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.