Research map / Large language models / Language, safety and interpretability
Eliciting Positive Emotion through Affect-Sensitive Dialogue Response Generation: A Neural Network Approach
Nurul Lubis, Sakriani Sakti, Koichiro Yoshino, Satoshi Nakamura
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| fine-tune only emotion encoder and utterance decoder (selective) instead of all parameters (ablation) | HRED · pos_sem test | perplexity: 121.44 -> 100.94 | Improved |
| selective fine-tuning with sem data (ablation) | HRED · pos_sem test | perplexity: 185.66 -> 151.77 | Improved |
| add emotion encoder (Emo-HRED vs HRED), selective, pos sem (ablation) | HRED · pos_sem test | perplexity: 100.94 -> 51.34 | Improved |
| add emotion encoder, selective, sem (ablation) | HRED · pos_sem test | perplexity: 151.77 -> 69.66 | Improved |
| fine-tune on positive-emotion eliciting responses (pos sem) instead of sem (ablation) | Emo-HRED · pos_sem test | perplexity: 69.66 -> 51.34 | Improved |
| add emotion encoder, pos sem data (ablation) | HRED · Human eval | naturalness: 3.26 -> 3.59 | Improved |
| add emotion encoder, pos sem data (ablation) | HRED · Human eval | emotional impact: 3.22 -> 3.58 | Improved |
| fine-tune on pos sem instead of sem (ablation) | HRED · Human eval | emotional impact: 2.56 -> 3.22 | Improved |
| fine-tune on pos sem instead of sem (ablation) | HRED · Human eval | naturalness: 2.71 -> 3.26 | Improved |
Closest papers by meaning
- Infusing Multi-Source Knowledge with Heterogeneous Graph Neural Network for Emotional Conversation Generation (AAAI 2021 · similarity 0.89)
- Emotional Chatting Machine: Emotional Conversation Generation with Internal and External Memory (AAAI 2018 · similarity 0.89)
- Knowledge Bridging for Empathetic Dialogue Generation (AAAI 2022 · similarity 0.89)
- Nano-EmoX: Unifying Multimodal Emotional Intelligence from Perception to Empathy (CVPR 2026 · similarity 0.85)
- The Good, The Bad, and Why: Unveiling Emotions in Generative AI (ICML 2024 · similarity 0.85)
- RLVER: Reinforcement Learning with Verifiable Emotion Rewards for Empathetic Agents (ICLR 2026 · similarity 0.85)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
