1 code implementation • 29 Mar 2024 • Fangxu Yu, Junjie Guo, Zhen Wu, Xinyu Dai
To achieve this, we utilize label encodings as anchors to guide the learning of utterance representations and design an auxiliary loss to ensure the effective separation of anchors for similar emotions.
Ranked #5 on Emotion Recognition in Conversation on MELD
1 code implementation • 13 Feb 2024 • Xingang Guo, Fangxu Yu, huan zhang, Lianhui Qin, Bin Hu
Based on this connection, we adapt the Energy-based Constrained Decoding with Langevin Dynamics (COLD), a state-of-the-art, highly efficient algorithm in controllable text generation, and introduce the COLD-Attack framework which unifies and automates the search of adversarial LLM attacks under a variety of control requirements such as fluency, stealthiness, sentiment, and left-right-coherence.