ProfiLLM infers chatbot users' IT/cybersecurity proficiency from their prompts, achieving a rapid initial reduction in profiling error in synthetic and limited human evaluations.
Let the llms talk: Simulating human-to-human conversational qa via zero-shot llm-to-llm interactions
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
ProfiLLM: An LLM-Based Framework for Implicit Profiling of Chatbot Users
ProfiLLM infers chatbot users' IT/cybersecurity proficiency from their prompts, achieving a rapid initial reduction in profiling error in synthetic and limited human evaluations.