Hugging Face Trending Papers

EmoStance: Response-Side Affective-Orientation Control for Empathetic Response Generation via Emoji Weak Supervision

Read the original on Hugging Face Trending Papers →

The paper introduces EmoStance, a method for controlling the affective orientation of empathetic responses in dialogue systems. It leverages weak supervision from multi‑annotator emoji distributions to create a latent control space that approximates listener stance, and uses a frozen instruction‑tuned LLM steered by continuous prefix embeddings. Evaluation shows a 62.2% decisive win rate over baselines, especially in contextual specificity and perceived responsiveness.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at Hugging Face Trending Papers.

arXiv AI
Sep 3

EmoStance: Response-Side Affective-Orientation Control for Empathetic Response Generation via Emoji Weak Supervision

The paper introduces EmoStance, a method for controlling the affective orientation of empathetic responses by leveraging weak supervision from emoji distributions. It builds the EmojiDialogue dataset, extending EmpatheticDialogues with emoji votes and confidence scores, and uses a frozen instruction‑tuned LLM steered by continuous prefix embeddings to generate responses that align with the listener’s stance. In blind pairwise evaluations, EmoStance achieves a 62.2% decisive win rate, notably improving contextual specificity and perceived responsiveness compared to baselines.

By Ziyuan Jin, Yuxuan Ge, Zheng Tian
arXiv Computation and Language
Aug 27

Controllable Affective Generation via Latent Vector Steering

The paper introduces EmoVec, a lightweight framework that enables controllable affective generation in large language models by steering latent vectors. EmoVec identifies emotion-specific directions from paired neutral and emotion-conditioned responses using contrastive activation addition, then refines these directions through task-specific debiasing and principal subspace removal. During inference, the refined vectors are injected into the final residual stream with static or scenario-adaptive scaling, allowing continuous control over emotional intensity without updating model weights, and experiments across three LLMs and eight emotions demonstrate improved emotional salience while preserving semantic content, fluency, and coherence.

By Xixian Yong, Siyuan Chang, Yingying Zhang, Xian Wu, Xiao Zhou