Dimensions overall score 5.0

GitHub Code Pulse

No public code linked for this paper yet.

• Static emotional prefixes in user queries produce only small changes in accuracy across most LLM tasks.result 90%
• Emotional framing effects are more variable in socially grounded tasks compared to other domains.result 85%
• Stronger emotional wording induces only modest extra change in LLM performance.result 80%
• Human-written emotional prefixes produce the same qualitative pattern as LLM-generated ones.result 85%
• No single emotion is consistently beneficial across different queries and tasks.result 90%
• Adaptive emotional prompting (EmotionRL) yields more reliable gains than fixed emotional prompting.result 90%
• Emotional tone is a weak and input-dependent signal rather than a dominant driver of LLM performance.result 90%
• The paper introduces EmotionRL, an adaptive emotional prompting framework that selects emotional framing adaptively for each query.method 95%

Competitive landscape

Competitor map is still being generated for this paper. Enable generation or check back soon.

Startup potential card