arXiv · cs.AI · Deeraj S K, Sadhana Devarajan, Krishna Mehra, Sudhakar Mishra · 9 小时前模型评分44
能否攻破 RLVER？探究 RL 训练共情智能体的对抗鲁棒性
Can You Break RLVER? Probing Adversarial Robustness of RL-Trained Empathetic Agents
导读
研究提出对抗共情基准（AEB，Adversarial Empathy Benchmark）和情感一致性分数（ECS，Emotional Consistency Score），用六类对抗轨迹测试经可验证情感奖励强化学习（RLVER，Reinforcement Learning from Verifiable Emotion Rewards）训练的共情模型。
分类置信度
中 · 待人工复核
- 只有单一媒体来源，需要人工复核。
来源级别：媒体与个人
事件类型：研究发布
证据摘录
- “We introduce the Adversarial Empathy Benchmark (AEB), six adversarial trajectory types whose discriminative rewards penalize formulaic comfort, and the Emotional Consistency Score (ECS), which separates whether a model \emph{improves} the user's emotional state from whether that state stays legible in the transcript.”
来源：arXiv · cs.AI · arxiv.org