Introduces ToM-PD task and ToM-BPD dataset plus TTBYS dual-knowledge framework, with Qwen3-8B outperforming GPT-5 on desire, belief, and strategy prediction.
Towards emotional support dialog systems
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 2verdicts
UNVERDICTED 2roles
background 1polarities
background 1representative citing papers
Interviews with 18 older adults show that AI safety interventions frequently disrupt emotional support-seeking, leading to calls for designs that respect users' pacing and preserve agency.
citing papers explorer
-
Think Thrice Before You Speak: Dual knowledge-enhanced Theory-of-Mind Reasoning for Persuasive Agents
Introduces ToM-PD task and ToM-BPD dataset plus TTBYS dual-knowledge framework, with Qwen3-8B outperforming GPT-5 on desire, belief, and strategy prediction.
-
Designing with Tensions: Older Adults' Emotional Support-Seeking Under System-Level Constraints in Conversational AI
Interviews with 18 older adults show that AI safety interventions frequently disrupt emotional support-seeking, leading to calls for designs that respect users' pacing and preserve agency.