近期论文11
- GPT-4 Is Too Smart To Be Safe: Stealthy Chat with LLMs via Cipher第 4 位,共 7 位作者ICLR 2024 · 441 次引用
- On the Humanity of Conversational AI: Evaluating the Psychological Portrayal of LLMs第 1 位,共 9 位作者ICLR 2024 · 85 次引用
- Apathetic or Empathetic? Evaluating LLMs' Emotional Alignments with Humans第 1 位,共 9 位作者NeurIPS 2024 · 63 次引用
- All Languages Matter: On the Multilingual Safety of LLMs第 5 位,共 7 位作者ACL Findings 2024 · 21 次引用
- LogicAsker: Evaluating and Improving the Logical Reasoning Ability of Large Language Models第 5 位,共 8 位作者EMNLP 2024 · 10 次引用
- On the Reliability of Psychological Scales on Large Language Models第 1 位,共 6 位作者EMNLP 2024 · 6 次引用
- InCharacter: Evaluating Personality Fidelity in Role-Playing Agents through Psychological Interviews第 3 位,共 13 位作者ACL 2024
- ParroT: Translating during Chat using Large Language Models tuned with Human Translation and Feedback第 2 位,共 8 位作者EMNLP Findings 2023 · 28 次引用
- Improving the Transferability of Adversarial Samples by Path-Augmented Method第 2 位,共 8 位作者CVPR 2023
- Improving Adversarial Transferability via Neuron Attribution-based Attacks第 3 位,共 8 位作者CVPR 2022 · 140 次引用
- AEON: a method for automatic evaluation of NLP test cases第 1 位,共 6 位作者ISSTA 2022 · 18 次引用
