Mitigating Over-Refusal in Aligned Large Language Models via Inference-Time Activation Energy (2026.acl-long)
Copied to clipboard
Eric Hanchen Jiang, Weixuan Ou, Run Liu, Shengyuan Pang, Guancheng Wan, Ranjie Duan, Wei Dong, Kai-Wei Chang, XiaoFeng Wang, Ying Nian Wu, Xinfeng Li
| Challenge: | Existing safety alignment techniques prioritize mitigating harmful responses at the expense of overcautious behavior, leading models to incorrectly refuse benign requests. |
| Approach: | They propose a fine-tuning free framework to improve safety and reduce false refusals by dynamic, inference-time intervention. |
| Outcome: | The proposed framework raises compliance on the ORB-H benchmark from 57.3% to 82.6% while maintaining the baseline safety performance. |
Similar Papers
Jailbreaks as Inference-Time Alignment: A Framework for Understanding Safety Failures in LLMs (2026.eacl-long)
Copied to clipboard
| Challenge: | Large language models are safety-aligned to prevent harmful response generation . prior work on jailbreak effectiveness has focused on analyzing success rate of jailbreaks . |
| Approach: | They propose to frame jailbreaks as inference-time alignment and draw suboptimal bounds . they also propose a Safety-Net to measure how vulnerable an LLM is to jailbreak attacks . |
| Outcome: | a new framework allows researchers to show how vulnerable an LLM is to jailbreaks . a Safety-Net measures how vulnerable the model is to attacks, the authors say . |
SafeConstellations: Mitigating Over-Refusals in LLMs Through Task-Aware Representation Steering (2026.acl-long)
Copied to clipboard
| Challenge: | Current safety alignment methods fail to identify intended benign task before refusing to respond. |
| Approach: | They propose a method that uses inference-time trajectory-shifting to guide model behavior . they show that LLMs persist in refusing inputs containing harmful content . |
| Outcome: | The proposed approach reduces over-refusals with minimal impact on utility. |
EOP-LLM: Energy Oriented Pruning for Large Language Models (2026.findings-acl)
Copied to clipboard
| Challenge: | Inference energy consumption has grown rapidly in large language models (LLMs) but existing methods focus on reducing FLOPs or latency rather than modeling or enforcing end-to-end inference energy constraints. |
| Approach: | They propose an energy-oriented dynamic pruning framework that enables LLM inference under explicit per-sequence energy budgets. |
| Outcome: | EOP-LLM outperforms state-of-the-art dynamic pruning baselines while adhering to per-sequence energy constraints. |
AdaSteer: Your Aligned LLM is Inherently an Adaptive Jailbreak Defender (2025.emnlp-main)
Copied to clipboard
Weixiang Zhao, Jiahe Guo, Yulin Hu, Yang Deng, An Zhang, Xingyu Sui, Xinyang Han, Yanyan Zhao, Bing Qin, Tat-Seng Chua, Ting Liu
| Challenge: | Activation steering offers training-free defense but relies on fixed steering coefficients, resulting in suboptimal protection and increased false rejections of benign inputs. |
| Approach: | They propose an adaptive activation steering method that dynamically adjusts model behavior based on input characteristics. |
| Outcome: | The proposed method outperforms baseline methods across multiple jailbreak attacks with minimal impact on utility. |
Beyond Surface Alignment: Rebuilding LLMs Safety Mechanism via Probabilistically Ablating Refusal Direction (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Jailbreak attacks pose persistent threats to large language models . current safety alignment methods have insufficient safety alignment depth and unrobust internal defense mechanisms. |
| Approach: | a new safety alignment framework is developed to overcome jailbreak attacks . the framework forces the model to dynamically rebuild its refusal mechanisms from jailbreak states . |
| Outcome: | a new safety alignment framework reduces attack success rates by approximately 95% on four open-source LLM families and six representative attacks. |
On Weaponization-Resistant Large Language Models with Prospect Theoretic Alignment (2025.coling-main)
Copied to clipboard
| Challenge: | Existing safeguards for large language models are inadequate for open-weight models as minimal fine-tuning can bypass them. |
| Approach: | They propose a framework that prioritizes maximizing generative utility rather than a singular optimization metric and integrates prospect theory into LLM training to strengthen LLMs against misuse and weaponization. |
| Outcome: | The proposed framework strengthens LLMs against misuse and weaponization while maintaining high performance even after extensive fine-tuning. |
SAFER: Advancing Safety Alignment via Efficient Ex-Ante Reasoning (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing alignment methods struggle to cover diverse safety scenarios and remain vulnerable to adversarial attacks. |
| Approach: | They propose a framework for 'S**afety' alignment via e**F**ficient' E**x-Ante-R**easoning that instantiates structured Ex-Ance reasoning and embeds predefined safety rules. |
| Outcome: | The proposed framework enhances safety performance while maintaining usefulness and efficiency. |
Compiling Activation Steering into Weights via Null-Space Constraints for Stealthy Backdoors (2026.acl-long)
Copied to clipboard
Rui Yin, Tianxu Han, Naen Xu, Changjiang Li, Ping He, Chunyi Zhou, Jun Wang, Zhihui Fu, Tianyu Du, Jinbao Li, Shouling Ji
| Challenge: | Existing methods to inject safety-aligned large language models rely on token-level mappings, which do not guarantee sustained harmful output. |
| Approach: | They propose a method that directly modifies model weights to map a trigger to an attacker-specified response. |
| Outcome: | The proposed method achieves high triggered attack success while maintaining non-triggered safety and general utility. |
A Simple Yet Effective Method for Non-Refusing Context Relevant Fine-grained Safety Steering in LLMs (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods for fine-tuning large language models to meet safety policies are costly and impractical. |
| Approach: | They propose a method to fine-tune large language models to meet evolving safety policies by applying a gradient-free, unsupervised approach. |
| Outcome: | The proposed method provides precise control, avoids blanket refusals, and directs models to generate safe, relevant content. |
The Unintended Trade-off of AI Alignment: Balancing Hallucination Mitigation and Safety in LLMs (2026.findings-eacl)
Copied to clipboard
| Challenge: | Hallucination in large language models has been studied, but a side effect remains unrecognized . a new study examines the trade-off between truthfulness and safety alignment . |
| Approach: | They propose a method that disentangles hallucination from hallucinian features using sparse autoencoders. |
| Outcome: | The proposed method preserves refusal behavior and task utility while maintaining safety alignment. |