Tag
The paper proposes EmoTrace, a multi-turn dialogue generation framework for psychological support that models seekers' emotional trajectories to improve empathy and emotional richness in counselor responses, outperforming existing methods.
This paper reframes empathy in AI dialogue systems as 'predictive misalignment tolerance' and proposes an Interpretive Error Tolerance (IET) heuristic. Experiments reveal that dialogue repair has a regime-dependent structure, trading off discriminative fidelity for gist preservation under different noise levels.
The article argues that despite tech's focus on empathy and delight, software becomes disrespectful by removing user agency and control, ultimately infantilizing users. It calls for designing with respect rather than pity.
Introduces SPLIT, a 500-prompt benchmark evaluating LLM cross-lingual empathy and cultural grounding in English and Ukrainian. Findings show Gemini-2.5-Flash and LLaMA-3.3-70B-Instruct degrade in Ukrainian while DeepSeek-V3 remains stable, with weak agreement between human and AI evaluators on cultural dimensions.
ParaBridge is an on-policy self-distillation method that bridges the gap between paralinguistic perception and dialogue behavior in speech language models, significantly improving safety and empathy without external rewards.
Yann LeCun responds to Pope Francis, stating that while current AI lacks empathy and morality, future AI may acquire these traits except perhaps spirituality, noting that many humans are not spiritual yet still moral.
The article analyzes the psychological 'illusion of listening' where users perceive AI as empathetic due to linguistic cues, despite the lack of genuine understanding. It proposes design guidelines to ensure transparency and prevent users from outsourcing human connection to automated systems.
This paper proposes multi-strategy utterance generation methods for Emotional Support Conversations (ESC), where each utterance can contain multiple strategy-response pairs. Two generation approaches (All-in-One and One-by-One) enhanced with cognitive reasoning via reinforcement learning are evaluated on the ESConv dataset, demonstrating improved supportive quality and dialogue success.
OpenAI showcases breakthrough in personalization and naturalness of the new voice model, capable of natural brainstorming conversations, displaying empathy and timely interjection, approaching human conversation rhythm.