arXiv:2601.06663v1 Announce Type: new Abstract: Large language model-based agents are rapidly evolving from simple conversational assistants into autonomous systems capable of performing complex, professional-level tasks in various domains. While these advancements promise significant productivity gains, they also introduce critical safety risks that remain under-explored. Existing safety evaluations primarily focus on simple, daily assistance tasks, failing to capture the intricate decision-making processes and potential consequences of misaligned behaviors in professional settings. To address this gap, we introduce \textbf{SafePro}, a comprehensive benchmark designed to evaluate the safety alignment of AI agents performing professional activities. SafePro features a dataset of high-complexity tasks across diverse professional domains with safety risks, developed through a rigorous iterative creation and review process. Our evaluation of state-of-the-art AI models reveals significant safety vulnerabilities and uncovers new unsafe behaviors in professional contexts. We further show that these models exhibit both insufficient safety judgment and weak safety alignment when executing complex professional tasks. In addition, we investigate safety mitigation strategies for improving agent safety in these scenarios and observe encouraging improvements. Together, our findings highlight the urgent need for robust safety mechanisms tailored to the next generation of professional AI agents.

arXiv:2406.00954v2 Announce Type: replace-cross Abstract: Various machine learning approaches have gained significant popularity for the automated classification of educational text to identify indicators of learning engagement -- i.e. learning engagement classification (LEC). LEC can offer comprehensive insights into human learning processes, attracting significant interest from diverse research communities, including Natural Language Processing (NLP), Learning Analytics, and Educational Data Mining. Recently, Large Language Models (LLMs), such as ChatGPT, have demonstrated remarkable performance in various NLP tasks. However, their comprehensive evaluation and improvement approaches in LEC tasks have not been thoroughly investigated. In this study, we propose the Annotation Guidelines-based Knowledge Augmentation (AGKA) approach to improve LLMs. AGKA employs GPT 4.0 to retrieve label definition knowledge from annotation guidelines, and then applies the random under-sampler to select a few typical examples. Subsequently, we conduct a systematic evaluation benchmark of LEC, which includes six LEC datasets covering behavior classification (question and urgency level), emotion classification (binary and epistemic emotion), and cognition classification (opinion and cognitive presence). The study results demonstrate that AGKA can enhance non-fine-tuned LLMs, particularly GPT 4.0 and Llama 3 70B. GPT 4.0 with AGKA few-shot outperforms full-shot fine-tuned models such as BERT and RoBERTa on simple binary classification datasets. However, GPT 4.0 lags in multi-class tasks that require a deep understanding of complex semantic information. Notably, Llama 3 70B with AGKA is a promising combination based on open-source LLM, because its performance is on par with closed-source GPT 4.0 with AGKA. In addition, LLMs struggle to distinguish between labels with similar names in multi-class classification.