{"slug": "emostance-response-side-affective-orientation-control-for-empathetic-response", "title": "EmoStance: Response-Side Affective-Orientation Control for Empathetic Response Generation via Emoji Weak Supervision", "summary": "Researchers introduced EmoStance, a method that uses emoji distributions as weak supervision to control the affective orientation of empathetic response generation, achieving a 62.2% decisive win rate in blind pairwise evaluations with 20 annotators and 800 judgments. The team also released EmojiDialogue, an utterance-level extension of EmpatheticDialogues with emoji votes and confidence scores, along with code and annotation metadata on GitHub.", "body_md": "arXiv:2609.02133v1 Announce Type: new\nAbstract: 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 orientation from dialogue context and speaker roles, and steers a frozen instruction-tuned LLM through continuous prefix embeddings. In blind pairwise evaluation with 20 annotators and 800 judgments, EmoStance achieves a 62.2% decisive win rate, with the clearest gains in contextual specificity and perceived responsiveness, while remaining complementary to external-knowledge methods. Code, annotation metadata, and reconstruction scripts are available in our GitHub repository: https://github.com/18277390221/EmoStance.", "url": "https://wpnews.pro/news/emostance-response-side-affective-orientation-control-for-empathetic-response", "canonical_source": "https://www.machinebrief.com/news/emostance-response-side-affective-orientation-control-for-em-2ynl", "published_at": "2026-09-03 04:00:00+00:00", "updated_at": "2026-09-03 04:53:28.280065+00:00", "lang": "en", "topics": ["artificial-intelligence", "natural-language-processing", "large-language-models", "ai-research"], "entities": ["EmoStance", "EmojiDialogue", "EmpatheticDialogues", "GitHub"], "alternates": {"html": "https://wpnews.pro/news/emostance-response-side-affective-orientation-control-for-empathetic-response", "markdown": "https://wpnews.pro/news/emostance-response-side-affective-orientation-control-for-empathetic-response.md", "text": "https://wpnews.pro/news/emostance-response-side-affective-orientation-control-for-empathetic-response.txt", "jsonld": "https://wpnews.pro/news/emostance-response-side-affective-orientation-control-for-empathetic-response.jsonld"}}