TRACE is a reference-free multi-dimensional evaluation framework for tool-augmented LLM reasoning trajectories that uses an evidence bank and is validated on a new meta-evaluation dataset of flawed trajectories.
Is safety standard same for everyone? user-specific safety evaluation of large language models.arXiv preprint arXiv:2502.15086,
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
years
2025 3verdicts
UNVERDICTED 3roles
background 2polarities
support 2representative citing papers
LLMs fail to detect hidden harmful intent, allowing systematic bypass of safety mechanisms through framing techniques, with reasoning modes often worsening the issue.
This paper proposes a taxonomy of LLM harms in five categories and suggests mitigation strategies plus a dynamic auditing system for responsible development.
citing papers explorer
-
Beyond the Final Answer: Evaluating the Reasoning Trajectories of Tool-Augmented Agents
TRACE is a reference-free multi-dimensional evaluation framework for tool-augmented LLM reasoning trajectories that uses an evidence bank and is validated on a new meta-evaluation dataset of flawed trajectories.
-
Beyond Context: Large Language Models' Failure to Grasp Users' Intent
LLMs fail to detect hidden harmful intent, allowing systematic bypass of safety mechanisms through framing techniques, with reasoning modes often worsening the issue.
-
LLM Harms: A Taxonomy and Discussion
This paper proposes a taxonomy of LLM harms in five categories and suggests mitigation strategies plus a dynamic auditing system for responsible development.