RESEARCH · RESEARCH · #2870
PromptSense: sentiment-aware mental-health chatbot framework with dynamic prompting (arXiv:2610.38044v1)
This arXiv preprint introduces PromptSense, a framework that integrates sentiment and depression analysis plus rule-based filtering to build dynamic prompts for LLM-based mental-health chatbots. The authors evaluate four model strategies and two prompt-engineering variants on metrics including empathy, helpfulness, clarity, relevance, safety, and toxicity (via Perspective API), reporting prompt-engineering gains of 1.8% over DSFT and 1.1% over RLAIF.
KEY POINTS
- This arXiv preprint introduces PromptSense, a framework that integrates sentiment and depression analysis plus rule-based filtering to build dynamic prompts for LLM-based mental-health chatbots.
- The authors evaluate four model strategies and two prompt-engineering variants on metrics including empathy, helpfulness, clarity, relevance, safety, and toxicity (via Perspective API), reporting prompt-engineering gains of 1.8% over DSFT and 1.1% over RLAIF.
- If robust, integrating sentiment/depression signals and pre-inference filtering could improve empathy and safety in LLM mental-health chatbots, but this is an early arXiv result requiring further validation.
WHY IT MATTERS
If robust, integrating sentiment/depression signals and pre-inference filtering could improve empathy and safety in LLM mental-health chatbots, but this is an early arXiv result requiring further validation.