arXiv Machine Learning
Jun 9
Helpful to a Fault: Measuring Illicit Assistance in Multi-Turn, Multilingual LLM Agents
arXiv:2602. 16346v4 Announce Type: replace-cross Abstract: LLM-based agents execute real-world workflows via tools and memory.
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.
Related stories
Hugging Face Trending Papers
Aug 3
EduZone: A Framework for Evaluating LLM Safety for K-12 Students and Teachers
Large language models (LLMs) are increasingly used across diverse tasks in K-12 education, yet existing safety evaluations rarely examine how harmful or inappropriate content appears in interactions between LLMs and students or teachers. To address this, we present EduZone, an evaluation framework for LLM safety across diverse educational scenarios.
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 10
PreAct-Bench: Benchmarking Predictive Monitoring in LLMs
arXiv:2606. 09890v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly deployed as autonomous agents capable of executing multi-step action trajectories toward a given objective.
arXiv AI
Aug 6
Temporal Context Awareness: A Defense Framework Against Multi-turn Manipulation Attacks on Large Language Models
arXiv:2503. 15560v1 Announce Type: cross Abstract: Large Language Models (LLMs) are increasingly vulnerable to sophisticated multi-turn manipulation attacks, where adversaries strategically build context through seemingly benign conversational turns to circumvent safety measures and elicit harmful or unauthorized responses.
arXiv Machine Learning
Jul 30
Forecasting Trajectory-Level Safety Risks in Black-Box Multi-Turn Interactions
arXiv:2607. 26820v1 Announce Type: new Abstract: As large language models (LLMs) evolve from standalone assistants into autonomous agents, ensuring their safety requires shifting beyond pointwise risk assessment to understand how risks emerge and unfold over long-horizon trajectories.
arXiv AI
1d ago
HarmProfile: Characterizing Harmful Distributions in Frontier LLMs
arXiv:2608. 14577v1 Announce Type: cross Abstract: Frontier large language models (LLMs) safety evaluation has largely treated harmful generation as an attack outcome rather than as an object of analysis.
arXiv AI
Jun 16
RoTRAG: Rule of Thumb Reasoning for Conversation Harm Detection with Retrieval-Augmented Generation
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.
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.
arXiv Machine Learning
Aug 4
Turn-Based Structural Triggers: Structure-Conditioned Backdoors in Multi-Turn LLMs
arXiv:2601. 14340v3 Announce Type: replace-cross Abstract: Large Language Models (LLMs) are increasingly deployed as multi-turn assistants and customized through instruction tuning with project-specific training components.
arXiv AI
Aug 11
Automating Deception: Scalable Multi-Turn LLM Jailbreaks
arXiv:2511. 19517v3 Announce Type: replace-cross Abstract: Multi-turn conversational attacks, which leverage psychological principles like Foot-in-the-Door (FITD), where a small initial request paves the way for a more significant one, to bypass safety alignments, pose a persistent threat to Large Language Models (LLMs).
Hugging Face Trending Papers
Jun 4
Safety Paradox: How Enhanced Safety Awareness Leaves LLMs Vulnerable to Posterior Attack
Large language models (LLMs) are rigorously aligned to refuse harmful requests, a process that inherently cultivates a latent capacity to evaluate and recognize unsafe content. In this work, we reveal that this advanced safety awareness inadvertently introduces a fatal vulnerability.