arXiv Computation and Language

ALTSTEER: Selective Safety Steering for Moving Beyond Hard Refusals to Constructive Alternatives

arXiv Machine Learning

Jun 4

Expert-Aware Refusal Steering

arXiv:2606. 04160v1 Announce Type: cross Abstract: Safety alignment in instruction-tuned large language models (LLMs) depends on a model's ability to reliably refuse to respond to harmful or disallowed requests.

By Anna C. Marbut, Daniel R. Olson, Travis J. Wheeler

llms safety

arXiv Machine Learning

Jul 14

Safe responses matter: Output-aware safety guardrail mitigate over-refusal in MLLMs

arXiv:2607. 09697v1 Announce Type: new Abstract: Existing safety mechanisms for multimodal large language models (MLLMs) face a fundamental trade-off between safety and utility.

By Jiayi Li, Kun Zhan

llms fine-tuning multimodal safety

arXiv Machine Learning

Jul 14

Selective Safety Steering via Value-Filtered Decoding

arXiv:2605. 14746v2 Announce Type: replace Abstract: While large language models (LLMs) are trained to align with human values, their generations may still violate safety constraints.

By Bat-Sheva Einbinder, Hen Davidov, Yee Whye Teh, Yarin Gal, Yaniv Romano

llms safety

arXiv Machine Learning

Aug 11

Safety Cost of Steering Vectors Is Separable and Reducible

arXiv:2608. 08383v1 Announce Type: cross Abstract: Steering vectors are a lightweight tool for controlling LLM behavior.

By Yuxiao Li, Gjergji Kasneci

llms benchmarks safety

arXiv AI

Jun 6

From Risk Classification to Action Plan Remediation: A Guardrail Feedback Driven Framework for LLM Agents

arXiv:2606. 05805v1 Announce Type: new Abstract: LLM-based guardrails typically safeguard agents by evaluating proposed actions or inputs before execution, producing safety signals such as binary allow/deny decisions, risk categories, and/or explanatory rationales about potential policy violations.

By Yuhao Sun, Jiacheng Zhang, Shaanan Cohney, Zhexin Zhang, Feng Liu, Xingliang Yuan

llms agents safety

arXiv AI

Jul 7

Oyster-II: Reinforcement Learning for Constructive Safety Alignment in Large Language Models

arXiv:2607. 02914v1 Announce Type: new Abstract: Large language models (LLMs) have demonstrated remarkable capabilities across diverse applications, yet ensuring their simultaneous safety, helpfulness, and trustworthiness remains a persistent challenge.

By Jiyang Guan, Yong Xie, Jun Chen, Jiexi Liu, Zipeng Ye, Defeng Li, Jiayu Shen, Jialing Tao, Hui Xue

llms reinforcement-learning fine-tuning benchmarks safety

arXiv AI

Jul 3

Safety Targeted Embedding Exploit via Refinement

arXiv:2607. 01859v1 Announce Type: new Abstract: Safety training for large language models (LLMs) is conducted predominantly in English, leaving uncertain how well safety mechanisms generalize to low-resource languages and mixed-language code-switching.

By Joshua Adrian Cahyono

llms rag safety

arXiv AI

Jul 1

The Geometry of Refusal: Linear Instability in Safety-Aligned LLMs

arXiv:2606. 22686v2 Announce Type: replace-cross Abstract: Modern Large Language Models (LLMs) rely on extensive safety alignment, yet the mechanistic basis of refusal remains opaque.

By Shivam Ratnakar, Kartikeya Vats

llms multimodal safety

arXiv Machine Learning

Jul 1

Addressing Over-Refusal in LLMs with Competing Rewards

arXiv:2606. 31748v1 Announce Type: new Abstract: Safety training on language models often induces over-refusal: improved safety on harmful prompts at the cost of increased refusal on harmless ones.

By Taeyoun Kim, Aviral Kumar

llms reinforcement-learning safety

arXiv AI

Jul 3

Conformal Policy Control

arXiv:2603. 02196v3 Announce Type: replace Abstract: An agent must try new behaviors to explore and improve.

By Drew Prinster, Clara Fannjiang, Ji Won Park, Kyunghyun Cho, Anqi Liu, Suchi Saria, Samuel Stanton

agents nlp safety

arXiv AI

3d ago

Beyond Token-Level Guidance: Inference-Time Alignment of Specialized LLMs via Cross-Family Representation Steering

arXiv:2608.30319v1 Announce Type: cross Abstract: Large language models (LLMs) finetuned for specialized domains represent crucial high-impact applications. Inference-time alignment improves safety d...

By Jin Gan, Xin Li, Jun Luo

llms fine-tuning benchmarks safety

arXiv Machine Learning

Jun 25

Do Thinking Tokens Help with Safety?

arXiv:2606. 25013v1 Announce Type: new Abstract: Today's reasoning models use thinking tokens to attain stronger performance on benchmarks than their instruction-tuned counterparts.

By Narutatsu Ri, Abhishek Panigrahi, Sanjeev Arora

llms benchmarks safety

Related stories