EmoStance: Response-Side Affective-Orientation Control for Empathetic Response Generation via Emoji Weak Supervision
arXiv cs.AIen
arXiv:2609.02133v1 Announce Type: new Abstract: Empathetic response generation requires models to decide not only what to say, but also how to respond to the previous speaker's affective situation. We formulate this as response-side affective-orientation control and use multi-annotator emoji distributions as weak affective--attitudinal evidence, rather than as output symbols or gold labels, to induce a latent control space that operationally approximates listener stance. We construct EmojiDialogue, an utterance-level extension of EmpatheticDialogues with emoji votes and confidence scores, and propose EmoStance, which models source-side affective expression, predicts a soft response-side orie
This is a short summary published by AI Global Wire. The full article is owned and hosted by arXiv cs.AI — open it there to read it in full.
Read the full story at arXiv cs.AI- Verktyg
- Forskning
Related AI news
- OpenAI is building 'automated shutdown' capabilities for AI tools, letter to lawmakers saysEconomic Times Tech · September 3, 2026
- The LA Unified School District bars ~378,000 students from using AI tools on district-provided laptops and tablets as officials review AI's role in classrooms (Julia Szymanski/LAmag)Techmeme · September 3, 2026
- Architecting Conversational Data Systems for Stateless LLM APIs: The Hydration Proxy PatternarXiv cs.AI · September 3, 2026
- FUSE: An Evaluating Framework for Dangerous Capabilities of LLMsarXiv cs.AI · September 3, 2026
- Looped Transformers under the Jacobian Lens: Does the Global Workspace Survive Recurrence?arXiv cs.AI · September 3, 2026
- When Does Information Sharing Improve Decentralized Discovery? Aggregation, Independent Rescue, and Equilibrium SelectionarXiv cs.AI · September 3, 2026