arXiv:2604. 17301v2 Announce Type: replace-cross Abstract: Detecting harmful content in multi turn dialogue requires reasoning over the full conversational context rather than isolated utterances.
Summary generated by The Flow from the publisher's feed. The full article lives at arXiv AI.
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.
arXiv:2606. 03812v1 Announce Type: new Abstract: Operational safety in high-stakes domains such as industrial process control, autonomous, and safety-critical systems, demand reliable hazard identification.
arXiv:2607. 19361v1 Announce Type: cross Abstract: Most safety guardrails for large language models (LLMs) evaluate each prompt-response pair in isolation, which misses failures that arise only over a dialogue as benign turns compose into harm.
arXiv:2606. 10380v1 Announce Type: cross Abstract: Real-world crisis intervention is inherently conversational, yet existing research largely focuses on static texts.
arXiv:2603. 03536v2 Announce Type: replace-cross Abstract: Current LLM-based conversational recommender systems (CRS) primarily optimize recommendation accuracy and user satisfaction.
arXiv:2606. 04867v1 Announce Type: new Abstract: As AI companion platforms such as Replika and Character.