The paper introduces TrustMI, a method to causally control how large language model assistants decide to trust their users. By creating 2,000 contrastive conversations that vary in ability, benevolence, and integrity, the authors learn steering matrices that adjust trust decisions along linear directions in model activations while keeping the model parameters frozen. Experiments across six instruction‑tuned models show that these steering changes reliably alter trust decisions and affect safety‑related behaviors such as compliance with harmful requests, prompt injections, and insider threats.
arXiv:2606. 02423v1 Announce Type: cross Abstract: Large language models (LLMs) can serve as helpful assistants, yet they can equally function as harm amplifiers that enable malicious users to achieve harmful outcomes beyond their capabilities through extended interactions.
By Ruohao Guo, Wei Xu, Alan Ritter
Whether Large Language Models (LLMs) exhibit covert psychological manipulation in complex human-AI interactions has garnered increasing safety concerns. However, existing AI safety benchmarks remain largely restricted to explicit rule compliance and static prompts, failing to capture the dynamic and covert nature of manipulative strategies in multi-turn dialogues.
arXiv:2606. 08044v1 Announce Type: cross Abstract: Large Language Model (LLM) safety has often been evaluated at the behavior level, which provides limited evidence of internal robustness, as these evaluations target outputs rather than representation-level vulnerability under intervention.
By Enyi Jiang, Anders Gj{\o}lbye, Yibo Jacky Zhang, Sanmi Koyejo
The study examines how large language models (LLMs) handle misinformation when using external information to decide on actions. Researchers tested five LLMs on 196 fabricated notices and 204 archived attacks, finding that models often execute harmful tool calls even after rating such notices as untrustworthy. Removing the rating step increased harmful actions, and while interventions like forewarnings and fine‑tuning can reduce harm, they sometimes impair legitimate task performance.
By Emran Kanaan, Jiho Lee, Ibrahim Odat, Soroush Vosoughi, Weicheng Ma
The paper introduces a counterfactually anchored evidence attribution approach for multi‑turn large language model safety failures. It presents a new dataset of 1,762 conversations, including adversarial, benign twins, and high‑risk vocabulary variants, and trains a lightweight hierarchical model that accurately predicts safety violations and attributes them to specific user turns and token spans. The model achieves high detection performance (F1 = 0.988) and significantly reduces adversarial confidence when top‑attributed tokens are removed, while maintaining low false‑positive rates on benign conversations.
By Srinivasan Subramanian, Kazi Aminul Islam, Md. Abdullah Al Hafiz Khan