Research map / Large language models / Language, safety and interpretability
CEM: Commonsense-Aware Empathetic Response Generation
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| Add commonsense-based affective and cognitive context refinement | empathetic response generation · EmpatheticDialogues test | PPL: 36.93 -> 36.11 | Helped |
| Add commonsense-based affective and cognitive context refinement | empathetic response generation · EmpatheticDialogues test | Dist-1: 0.47 -> 0.66 | Helped |
| Add commonsense-based affective and cognitive context refinement | empathetic response generation · EmpatheticDialogues test | Dist-2: 2.10 -> 2.99 | Helped |
| Add commonsense-based affective and cognitive context refinement | empathetic response generation · EmpatheticDialogues test | emotion accuracy: 33.57 -> 39.11 | Helped |
| Add commonsense-based affective and cognitive context refinement | empathetic response generation · EmpatheticDialogues human evaluation vs. MoEL | informativeness win rate: 61.0 | Helped |
| Add commonsense-based affective and cognitive context refinement | empathetic response generation · EmpatheticDialogues human evaluation vs. MIME | informativeness win rate: 48.6 | No clear effect |
| Add the affective and affection-refined encoders (ablation) | CEM · EmpatheticDialogues test | emotion accuracy: 33.76 -> 39.11 | Helped |
| Add the affective and affection-refined encoders (ablation) | CEM · EmpatheticDialogues test | Dist-2: 2.52 -> 2.99 | Helped |
| Add the cognitive and cognition-refined encoders (ablation) | CEM · EmpatheticDialogues test | emotion accuracy: 36.42 -> 39.11 | Helped |
| Add the cognitive and cognition-refined encoders (ablation) | CEM · EmpatheticDialogues test | Dist-2: 2.47 -> 2.99 | Helped |
| Add the diversity loss (ablation) | CEM · EmpatheticDialogues test | Dist-1: 0.48 -> 0.66 | Helped |
| Add the diversity loss (ablation) | CEM · EmpatheticDialogues test | Dist-2: 1.96 -> 2.99 | Helped |
Closest papers by meaning
- EmpathyChat: Structured Cognitive Reasoning in Empathetic Spoken Dialogue (NeurIPS 2026 · similarity 0.89)
- Apathetic or Empathetic? Evaluating LLMs' Emotional Alignments with Humans (NeurIPS 2024 · similarity 0.86)
- The Illusion of Empathy: How AI Chatbots Shape Conversation Perception (AAAI 2025 · similarity 0.85)
- SocialSim: Towards Socialized Simulation of Emotional Support Conversation (AAAI 2025 · similarity 0.85)
- CAREBench: Evaluating LLMs' Emotion Understanding by Assessing Cognitive Appraisal Reasoning (NeurIPS 2026 · similarity 0.84)
- HumanSense: From Multimodal Perception to Empathetic Context-Aware Responses Through Reasoning MLLMs (AAAI 2026 · similarity 0.83)
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.