The paper introduces RESCUE-BENCH, a benchmark for relation-aware multi‑party emotional support conversation systems. It is built from real couple and family interview data, comprising 191 samples, 7,079 annotated turns, and 1,064.8 minutes of video, and defines six tasks that assess relational understanding and relation‑sensitive support. Experiments with ten large language models show that while they handle local emotional cues reasonably well, they struggle with tasks that require modeling interpersonal relations, such as predicting relation patterns, viewpoints, and support strategies.
Existing emotional support conversation systems mainly focus on one-on-one seeker-supporter interactions and individual emotional states, leaving interpersonal relations in multi-party scenarios under...
The study evaluates PAIR, a theory-based emotion‑regulation companion, over 14 days with 19 participants, analyzing 1,093 sessions. Emotion estimates from the agent aligned better with participants’ self‑reported valence and dominance than arousal, and guided conversations led to higher valence and state‑dependent arousal changes. Participants reported feeling understood, and the perceived helpfulness of guided conversations increased over time, highlighting the role of memory updates and cross‑session personalization in sustained emotional support.
arXiv:2504. 11837v3 Announce Type: replace-cross Abstract: Emotional support conversation (ESC) aims to alleviate people's emotional distress through effective conversations.
arXiv:2607.23648v2 Announce Type: replace Abstract: Using large language models (LLMs) to assist psychological counseling is an important task in the field of natural language processing. The constru...
arXiv:2608.21925v1 Announce Type: new Abstract: Emotional Support Conversation (ESC) systems aim to provide holistic support by balancing professional therapeutic competence with natural empathy. How...
arXiv:2607. 28648v1 Announce Type: cross Abstract: Large Language Models (LLMs) are increasingly used for emotional support tasks, such as negative thought reframing.
Humans possess an innate ability to understand fine-grained interpersonal relationships, which is central to everyday social interactions. Although such reasoning is inherently multimodal, it remains largely unexplored by existing multimodal large language models (MLLMs).
PIVOTSBench is a benchmark designed to assess multimodal large language models’ ability to reason about fine‑grained interpersonal relationships. It is constructed from Social‑IQ 2.0 and YouTube data and evaluates models on predicting bidirectional relationship dimensions grounded in psychology research. The benchmark also includes auxiliary tasks that test models’ capacity to identify and use critical visual cues, and it examines the impact of visual modalities, social role information, and different prediction settings on model performance.
arXiv:2607. 07824v1 Announce Type: cross Abstract: Large Language Models (LLMs) have substantially advanced persona-based dialogue agents for emotion-sensitive role simulation in healthcare, education, counseling, customer service, and interactive storytelling.
Emotional dialogue research includes two influential strategy traditions. Empathetic dialogue prioritizes understanding a speaker's emotional experience.
arXiv:2603. 25031v2 Announce Type: replace Abstract: In psychological support and emotional companionship scenarios, the core limitation of large language models (LLMs) lies not merely in response quality, but in their reliance on local next-token prediction, which prevents them from maintaining the temporal continuity, stage awareness, and user consent boundaries required for multi-turn intervention.
The paper introduces the Romantic Relationship Advice-Seeking Prompts (RRASP) dataset, comprising 2,400 prompts across five relationship themes, to study how query formulation affects sycophancy in large language models. Using the ELEPHANT framework, the authors evaluated GPT‑5 Mini and Gemini 3 Flash, finding that grammatical mood alone does not drive sycophantic behavior, whereas perspective‑driven framing does, with models increasingly accepting user premises over successive turns. Gemini 3 Flash showed smaller increases in moral sycophancy than GPT‑5 Mini, indicating greater resistance to reinforcing ethically problematic positions.