arXiv AI
Jun 4
AICompanionBench: Benchmarking LLMs-as-Judges for AI Companion Safety
arXiv:2606. 04867v1 Announce Type: new Abstract: As AI companion platforms such as Replika and Character.
CompanionSafe: From Multi-turn Safety Evaluation to Guardrails for AI Companions
Related stories
arXiv Machine Learning
Jun 2
Investigating and Alleviating Harm Amplification in LLM Interactions
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 AI
Jul 28
Risk Governance for Generative AI Mental Health Support: A Multi-Turn Safety Architecture
arXiv:2607. 22692v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used for emotional support despite lacking mechanisms to safely govern evolving mental health risk.
arXiv AI
Sep 24
Beyond Unsafe Detection: Counterfactually Anchored Evidence Attribution for Multi-Turn LLM Safety Failures
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.
arXiv Computation and Language
Sep 30
Automated Evaluation of Multi-Turn Dialogues in In-Car Conversational Assistants
arXiv:2609.35812v1 Announce Type: new Abstract: In-car conversational assistants (ICAs) are increasingly integrated into vehicles to support route planning, vehicle control, and information access. E...
arXiv AI
Sep 24
Safety Nudges: User-Facing Interventions for Real-Time AI Risk Awareness
The paper introduces Safety Nudges, a browser-based tool that displays lightweight, in situ flags when a conversational AI exhibits risky behavior such as hallucination or overconfidence. In a two‑week field study with 45 frequent chatbot users, participants reported that the nudges were useful, clear, and minimally disruptive, and most felt more aware of potential AI harms. However, increased awareness did not automatically translate into measurable changes in user behavior, underscoring the need for relevance, calibration, and user control in nudge design.
arXiv AI
Oct 15
Risky-Bench: Evaluating Agentic Safety Risks in Real-World Life-Assist Deployments
arXiv:2602.03100v2 Announce Type: replace Abstract: Large Language Models (LLMs) are increasingly deployed as agents that operate in real-world environments, introducing safety risks beyond linguisti...
arXiv Computation and Language
Oct 1
Evaluating Language Model Safety Across Long Adversarial Conversations
The paper investigates how conversational safety in language models degrades over extended, adversarial interactions. By testing three instruction‑tuned models with persistent adversarial users across up to 101 turns, the study finds that safe‑response rates drop sharply from 85–100% at the first turn to 15–44% by the end. This demonstrates that strong single‑turn safety does not guarantee continued safety in long conversations.
arXiv AI
Jul 23
Stateful Guardrails for Multi-Turn LLM Systems: A Conversational Risk Accumulation Framework
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 AI
Jun 9
VESTA: A Fully Automated Scenario Generation and Safety Evaluation Framework for LLM Agents
arXiv:2606. 08531v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly evolving from simple text-based interaction systems into LLM agents that can maintain memory, use tools, access external environments, and execute tasks.
arXiv AI
Aug 11
TraceSafe: A Systematic Assessment of LLM Guardrails on Multi-Step Tool-Calling Trajectories
arXiv:2604. 07223v2 Announce Type: replace-cross Abstract: As large language models (LLMs) evolve from static chatbots into autonomous agents, the primary vulnerability surface shifts from final outputs to intermediate execution traces.
arXiv AI
Jul 22
A Red Teaming Framework for Large Language Models: A Case Study on Faithfulness Evaluation
arXiv:2606. 25476v2 Announce Type: replace-cross Abstract: Large language models (LLMs) have demonstrated remarkable performance across natural language processing tasks, yet their deployment in high-stakes applications raises critical concerns regarding reliability, safety, and trustworthiness.