arXiv Computation and Language October 16, 2026 By Giovana Kerche Bon\'as, Thales Sales Almeida, Marcelo da Silva Reis, Rodrigo Nogueira, Marcos Meideiros Raimundo

PRISM: Transfer and Limits of Activation Interventions in Tool-Calling Language Models

Read the original on arXiv Computation and Language →

PRISM is a framework that evaluates how activation interventions transfer across precision, languages, and model scales to mitigate unsafe tool‑calling behaviors in language models. By leveraging lower‑resource settings such as quantized NF4 labels and cross‑lingual transfer, PRISM demonstrates that alignment improvements can be achieved with minimal scenarios and that these gains transfer to held‑out languages and larger models. The study shows that auxiliary supervision from compressed models and multilingual data can effectively uncover and reduce hazardous tool‑calling behaviors across different model families.

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 Computation and Language.

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

Jun 18

Beyond Safe Data: Pretraining-Stage Alignment with Regular Safety Reflection

arXiv:2606. 19168v1 Announce Type: new Abstract: To achieve deeper safety alignment for large language models (LLMs), recent efforts have studied how to push safety interventions earlier into the pretraining stage, primarily by filtering unsafe data or rewriting it into safer forms.

By Jinhan Li, Kexian Tang, Yihan Xu, Zhuorui Ye, Kaifeng Lyu

llms fine-tuning safety

Hugging Face Trending Papers

Jul 2

Safety Targeted Embedding Exploit via Refinement

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. We show that this creates an epistemic gap in which models confidently generate harmful responses for inputs that fall outside the distribution of their safety training.

llms rag safety

arXiv Machine Learning

Jun 4

Few Tokens, Big Leverage: Preserving Safety Alignment by Constraining Safety Tokens during Fine-tuning

arXiv:2603. 07445v2 Announce Type: replace-cross Abstract: Large language models (LLMs) often require fine-tuning (FT) to perform well on downstream tasks, but FT can induce safety-alignment drift even when the training dataset contains only benign data.

By Guoli Wang, Haonan Shi, Tu Ouyang, An Wang

llms fine-tuning safety

arXiv AI

Jun 30

The Heterogeneous Safety Impacts of Benign Multilingual Fine-Tuning

arXiv:2606. 28843v1 Announce Type: cross Abstract: Fine-tuning a large language model is a ubiquitous method for enhancing its capability on a specific downstream task.

By Will Hawkins, Kaivalya Rawal, Jonathan Rystr{\o}m, Stratis Tsirtsis, Zihao Fu, Greta Warren, Ryan Brown, Eoin Delaney, Sandra Wachter, Brent Mittelstadt, Chris Russell

llms fine-tuning safety

arXiv AI

Jun 16

CHILLGuard: Towards Fine-Grained Chinese LLM Safety Guardrail with Scalable Data Construction and Model-aware Preference Alignment

arXiv:2606. 15396v1 Announce Type: cross Abstract: Malicious content generated from large language models (LLMs) could pose severe safety risks and ethical concerns.

By Wenbo Yu, Bohua Wang, Hao Fang, Kuofeng Gao, Jingru Zeng, Xiaochen Yang, Tianyi Zhang, Xiaoxiao Ma, Jiawei Kong, Hao Wu, Bin Chen, Shu-Tao Xia, Min Zhang

llms rag benchmarks safety

One email a morning, machine-written

Related stories

Safety Targeted Embedding Exploit via Refinement

Beyond Safe Data: Pretraining-Stage Alignment with Regular Safety Reflection

Safety Targeted Embedding Exploit via Refinement

Few Tokens, Big Leverage: Preserving Safety Alignment by Constraining Safety Tokens during Fine-tuning

The Heterogeneous Safety Impacts of Benign Multilingual Fine-Tuning

CHILLGuard: Towards Fine-Grained Chinese LLM Safety Guardrail with Scalable Data Construction and Model-aware Preference Alignment