SafeSwitch: Steering Unsafe LLM Behavior via Internal Activation Signals (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Existing safety mechanisms for large language models (LLMs) are inadequate to fully leverage their internal cognitive processes. |
| Approach: | They propose a framework that regulates unsafe outputs by utilizing the prober-based internal state monitor that actively detects harmful intentions. |
| Outcome: | The proposed framework reduces harmful outputs by approximately 80% while maintaining strong utility. |
Similar Papers
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. |
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. |
Separate the Wheat from the Chaff: A Post-Hoc Approach to Safety Re-Alignment for Fine-Tuned Language Models (2025.findings-acl)
Copied to clipboard
| Challenge: | Large language models achieve effective safety alignment at the time of release, but fine-tuning often compromises safety mechanisms. |
| Approach: | They propose a method that performs safety realignment for large language models . they identify unsafe delta parameters from the fine-tuned models and recalibrate the retained parameters . |
| Outcome: | The proposed method improves safety performance on safety benchmarks and jailbreak attacks while maintaining their performance on downstream tasks. |
SafeMERGE: Preserving Safety Alignment in Fine-Tuned Large Language Models via Selective Layer-Wise Model Merging (2026.findings-acl)
Copied to clipboard
| Challenge: | Recent studies show that fine-tuning can erode safety alignment, causing LLMs to respond to harmful or unethical prompts. |
| Approach: | They propose a lightweight framework that restores safety while maintaining downstream performance. |
| Outcome: | The proposed framework reduces harmful outputs compared to other defenses, with negligible impact on utility. |
Safety is Not Only About Refusal: Reasoning-Enhanced Fine-tuning for Interpretable LLM Safety (2025.findings-acl)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) are vulnerable to jailbreak attacks that exploit weaknesses in traditional safety alignment. |
| Approach: | They propose a framework that trains models to engage in explicit safe reasoning before response . they propose RATIONAL, which allows models to reject harmful prompts while providing meaningful and context-aware responses. |
| Outcome: | The proposed framework fine-tunes models to reason about query intent, ethics, and potential harm. |
Interpretation Meets Safety: A Survey on Interpretation Methods and Tools for Improving LLM Safety (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing surveys focus on interpretation or safety, but safety and understanding are core motivations for interpretation research. |
| Approach: | They propose a framework that connects interpretation methods, enhancements they inform, and tools that operationalize them. |
| Outcome: | The proposed framework summarizes nearly 70 studies at their intersections and concludes with open challenges and future directions. |
SafeConf: A Confidence-Calibrated Safety Self-Evaluation Method for Large Language Models (2025.findings-emnlp)
Copied to clipboard
Bo Zhang, Cong Gao, Linkang Yang, Bingxu Han, Minghao Hu, Zhunchen Luo, Guotong Geng, Xiaoying Bai, Jun Zhang, Wen Yao, Zhong Wang
| Challenge: | Large language models (LLMs) have many advantages but they also pose significant safety risks. |
| Approach: | They propose a method to enhance the safety self-evaluation capability of LLMs . they perform semantic mutations on the original safety evaluation questions . |
| Outcome: | The proposed method improves safety self-evaluation accuracy by 5.86% and 7.79% over baseline methods on Chinese and English datasets. |
Representation Bending for Large Language Model Safety (2025.acl-long)
Copied to clipboard
Ashkan Yousefpour, Taeheon Kim, Ryan Sungmo Kwon, Seungbeen Lee, Wonje Jeung, Seungju Han, Alvin Wan, Harrison Ngan, Youngjae Yu, Jonghyun Choi
| Challenge: | Existing safety-enhancing techniques, such as fine-tuning with human feedback or adversarial training, are still vulnerable as they address specific threats and fail to generalize across unseen attacks. |
| Approach: | They propose a new approach that disrupts representations underlying harmful behaviors in Large Language Models by using loss-based fine-tuning. |
| Outcome: | The proposed approach outperforms existing methods such as Circuit Breaker, RMU, and NPO with 95% reduction in attack success rates across diverse jailbreak benchmarks. |
Root Defense Strategies: Ensuring Safety of LLM at the Decoding Level (2025.acl-long)
Copied to clipboard
| Challenge: | Existing methods to detect harmful outputs from prefill-level lacks utilization of the model’s decoding outputs, leading to relatively lower effectiveness and robustness. |
| Approach: | They propose a robust decoding mechanism that corrects harmful queries directly rather than rejecting them outright. |
| Outcome: | The proposed model improves model security without compromising reasoning speed. |
Shaping the Safety Boundaries: Understanding and Defending Against Jailbreaks in Large Language Models (2025.acl-long)
Copied to clipboard
| Challenge: | Understanding how jailbreaking works remains limited, hindering the development of effective defense strategies. |
| Approach: | They propose a new mechanism that adaptively constrains activations within the safety boundary and propose 'Activation Boundary Defense' to enhance its effectiveness. |
| Outcome: | The proposed defense achieves an average Defense Success Rate (DSR) of over 98% against various jailbreak attacks, with less than 2% impact on the model’s general capabilities. |