LLM tutors leak answers under adversarial student attacks, but a fine-tuned jailbreak agent and simple defenses can benchmark and improve robustness.
McKee, Daniel Gillick, et al
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
years
2026 5representative citing papers
Behavioral signals from how students use AI tutor feedback in 10k code submissions reveal differences between tutors and correlate more strongly with perceived helpfulness than pedagogical quality alone.
Two controlled experiments show multi-agent LLM configurations with both tutors and peers deliver higher learning gains and less homogeneous outputs than single-LLM tutoring in math problem-solving and essay writing.
AI explanations in language learning often fail across six dimensions like diagnostic accuracy and self-regulation support, creating hidden risks that demand better evaluation frameworks such as L2-Bench.
Priority PayGo keeps multi-agent tutoring responses under 4 seconds even at 50 concurrent users, while costs stay below textbook prices per student.
citing papers explorer
-
Evaluating Answer Leakage Robustness of LLM Tutors against Adversarial Student Attacks
LLM tutors leak answers under adversarial student attacks, but a fine-tuned jailbreak agent and simple defenses can benchmark and improve robustness.
-
The Missing Evaluation Axis: What 10,000 Student Submissions Reveal About AI Tutor Effectiveness
Behavioral signals from how students use AI tutor feedback in 10k code submissions reveal differences between tutors and correlate more strongly with perceived helpfulness than pedagogical quality alone.
-
Beyond the AI Tutor: Social Learning with LLM Agents
Two controlled experiments show multi-agent LLM configurations with both tutors and peers deliver higher learning gains and less homogeneous outputs than single-LLM tutoring in math problem-solving and essay writing.
-
Ceci n'est pas une explication: Evaluating Explanation Failures as Explainability Pitfalls in Language Learning Systems
AI explanations in language learning often fail across six dimensions like diagnostic accuracy and self-regulation support, creating hidden risks that demand better evaluation frameworks such as L2-Bench.
-
Latency and Cost of Multi-Agent Intelligent Tutoring at Scale
Priority PayGo keeps multi-agent tutoring responses under 4 seconds even at 50 concurrent users, while costs stay below textbook prices per student.