arXiv AI September 15, 2026 By Roberto Campbell, Momin Abbass, Muneeza Azmat, Michal Ulewicz, Raya Horesh, Kristjan Greenewald, Rog\'erio Abreu de Paula, Nathalie Baracaldo

An Efficient and Modular Framework for Targeted Harm Mitigation in LLMS

Read the original on arXiv AI →

The paper introduces a modular correction framework for large language models that uses Activated LoRA adapters and a context-aware routing mechanism to mitigate harmful outputs. By allowing expert adapters to activate mid-sequence without invalidating the KV cache, the system achieves low-latency, targeted correction during generation. Experiments show improved alignment on safety benchmarks while maintaining task performance, presenting a lightweight, scalable approach to safer LLM deployments.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

arXiv Machine Learning

Aug 14

HiRoute: Hierarchical Routed Prompt Tuning for Safety Alignment of Large Language Models

arXiv:2608. 12821v1 Announce Type: new Abstract: Large language models (LLMs) remain vulnerable to harmful requests and jailbreak attacks.

By Fangzhou Chen, Shiji Zhao, Mengyang Wang, Qihui Zhu, Ranjie Duan, Maoxun Yuan, Xingxing Wei

llms rag benchmarks safety

arXiv Machine Learning

Jun 2

Dialectics of Alignment: Harnessing Unsafe Knowledge for Dynamic Safety Routing

arXiv:2606. 00686v1 Announce Type: new Abstract: The prevailing paradigm in large language model (LLM) alignment operates via erasure, filtering unsafe data or training models to strictly refuse harmful prompts.

By Maryam Hashemzadeh, Jerry Huang, Minseon Kim, Marc-Alexandre C\^ot\'e, Sarath Chandar

llms fine-tuning benchmarks safety

arXiv AI

Aug 24

CLEAR: Continuous Latent Adapter Routing for Utility-Preserving LLM Safety Alignment

CLEAR is a conditional safety adaptation framework that employs a lightweight hidden‑state gate to continuously control the activation strength of a safety low‑rank adapter. It aims to reduce harmful completions while preserving the performance of the frozen backbone on benign prompts. Experiments on safety and utility benchmarks, including HarmBench and GSM8K, show that CLEAR significantly lowers HarmBench ASR and improves utility compared to globally applied safety tuning methods such as SFT or standard LoRA.

By Chengxiao Wang, Enyi Jiang, Xiaojing Liao, Sanmi Koyejo

llms fine-tuning multimodal benchmarks safety

arXiv Machine Learning

Jun 9

Distilling Safe LLM Systems via Soft Prompts for On Device Settings

arXiv:2606. 09388v1 Announce Type: new Abstract: Deploying safe large language models (LLMs) on resource-constrained edge devices presents a critical challenge: while dual-model systems combining LLMs with guard models provide effective safety guarantees, their substantial memory and computational demands make them prohibitively expensive for on-device deployment.

By Motasem Alfarra, Cristina Pinneri, Dana Kianfar, Mohammed Almousa, Christos Louizos

llms fine-tuning efficiency benchmarks safety

arXiv AI

Jul 23

Matching Ranks Over Probability Yields Truly Deep Safety Alignment

arXiv:2512. 05518v2 Announce Type: replace-cross Abstract: Open-source Large Language Models (LLMs) play a critical role in the democratization of AI, yet their "open" nature introduces more avenues for malicious actors to misuse them for harmful purposes.

By Jason Vega, Gagandeep Singh

llms fine-tuning safety

arXiv Machine Learning

Jun 15

NeST: Neuron Selective Tuning for LLM Safety

arXiv:2602. 16835v2 Announce Type: replace-cross Abstract: Safety alignment is essential for the responsible deployment of Large Language Models (LLMs).

By Sasha Behrouzi, Lichao Wu, Mohamadreza Rostami, Ahmad-Reza Sadeghi

llms fine-tuning multimodal safety

One email a morning, machine-written

Related stories

HiRoute: Hierarchical Routed Prompt Tuning for Safety Alignment of Large Language Models

Dialectics of Alignment: Harnessing Unsafe Knowledge for Dynamic Safety Routing

CLEAR: Continuous Latent Adapter Routing for Utility-Preserving LLM Safety Alignment

Distilling Safe LLM Systems via Soft Prompts for On Device Settings

Matching Ranks Over Probability Yields Truly Deep Safety Alignment

NeST: Neuron Selective Tuning for LLM Safety