ESConv
PulseAugur coverage of ESConv — every cluster mentioning ESConv across labs, papers, and developer communities, ranked by signal.
2 day(s) with sentiment data
-
New study suggests affirmation is key to quality in AI-assisted counseling
A new study published on arXiv introduces 'Affirmation' as a key behavioral marker for high-quality text-based counseling, potentially surpassing 'Reflection' in importance. Researchers analyzed the KokoroChat dataset, …
-
New methods improve LLM judging in open-ended dialogue
Researchers have developed new methods for evaluating Large Language Models (LLMs) in open-ended dialogue scenarios. These methods, collectively termed Multi-Expert Conformal Risk Control (CRC), aim to improve the accur…
-
New research paradigm CSED prioritizes long-term user well-being in emotional dialogue systems
A new research paradigm called Capability-Sustaining Emotional Dialogue (CSED) is proposed to advance emotional dialogue systems. Current research often focuses on immediate relief rather than long-term user well-being …
-
New DESG model improves AI therapist evaluation beyond LLM judges
Researchers have developed a new model-agnostic evaluator called Dynamic Emotional Signature Graphs (DESG) to assess the quality of AI-generated responses in mental health dialogues. This method moves beyond simple text…