PIVOT: Preference-based Intervention Vectors for Pedagogical Tutor Steering
Quick summary
arXiv:2608.07509v1 Announce Type: cross Abstract: LLMs are increasingly used for conversational tutoring, but effective tutoring requires more than correct answers. Tutors must choose when to scaffold reasoning, hint, give feedback, explain, or invite reflection. Existing prompting and training methods improve pedagogical alignment, but lack reliable inference-time control over pedagogical strategies. We introduce PIVOT, an activation-steering framework that learns preference-based intervention vectors online for frozen LLM tutors. PIVOT uses a seven-category tutor-move taxonomy and a generate
Key takeaways
- arXiv:2608.07509v1 Announce Type: cross Abstract: LLMs are increasingly used for conversational tutoring, but effective tutoring requires more than correct answers.
- Tutors must choose when to scaffold reasoning, hint, give feedback, explain, or invite reflection.
- Existing prompting and training methods improve pedagogical alignment, but lack reliable inference-time control over pedagogical strategies.
Why it matters
“PIVOT: Preference-based Intervention Vectors for Pedagogical Tutor Steering” should be evaluated beyond branding and benchmark scores. Its practical importance will emerge in task accuracy, latency, unit cost, safety and integration with real workflows.
Member comments