Evaluating Answer Leakage Robustness of LLM Tutors against Adversarial Student Attacks

• URL: http://arxiv.org/abs/2604.18660v1
• Date: Mon, 20 Apr 2026 11:29:22 GMT
• Title: Evaluating Answer Leakage Robustness of LLM Tutors against Adversarial Student Attacks
• Abstract summary: We study scenarios where students behave adversarially and aim to obtain the correct answer from the tutor.<n>We evaluate a broad set of LLM-based tutor models, including different model families, pedagogically aligned models, and a multi-agent design.<n>We present simple but effective defense strategies that reduce answer leakage and strengthen the robustness of LLM-based tutors.
• Score: 9.471800828517496
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large Language Models (LLMs) are increasingly used in education, yet their default helpfulness often conflicts with pedagogical principles. Prior work evaluates pedagogical quality via answer leakage-the disclosure of complete solutions instead of scaffolding-but typically assumes well-intentioned learners, leaving tutor robustness under student misuse largely unexplored. In this paper, we study scenarios where students behave adversarially and aim to obtain the correct answer from the tutor. We evaluate a broad set of LLM-based tutor models, including different model families, pedagogically aligned models, and a multi-agent design, under a range of adversarial student attacks. We adapt six groups of adversarial and persuasive techniques to the educational setting and use them to probe how likely a tutor is to reveal the final answer. We evaluate answer leakage robustness using different types of in-context adversarial student agents, finding that they often fail to carry out effective attacks. We therefore introduce an adversarial student agent that we fine-tune to jailbreak LLM-based tutors, which we propose as the core of a standardized benchmark for evaluating tutor robustness. Finally, we present simple but effective defense strategies that reduce answer leakage and strengthen the robustness of LLM-based tutors in adversarial scenarios.

Related papers

• Self-Explanation Tutor for Active Study of CS1 Worked Examples [1.7504194797252353]
  We build a self-explanation tutor for introductory programming, ESSE, in which students explain lines of worked examples.<n>We ask whether the LLM judges student explanations well enough to serve as the engine of the tutor.<n>We find that its feedback leads students to persist and revise rather than abandon a line.
  arXiv  Detail & Related papers  (2026-08-25T21:54:47Z)
• Measuring Whether LLM Tutors Teach or Solve: A Diagnostic for Educational Impact [4.6840536642016195]
  We study whether public tutoring benchmarks distinguish learning-supportive behavior from mere answer production.<n>We propose a lightweight diagnostic rubric based on the gap between solving-oriented and pedagogy-oriented benchmark performance.
  arXiv  Detail & Related papers  (2026-06-15T04:32:18Z)
• CASTLE: A Comprehensive Benchmark for Evaluating Student-Tailored Personalized Safety in Large Language Models [55.0103764229311]
  We propose the concept of Student-Tailored Personalized Safety and construct CASTLE based on educational theories.<n>This benchmark covers 15 educational safety risks and 14 student attributes, comprising 92,908 bilingual scenarios.
  arXiv  Detail & Related papers  (2026-02-05T13:13:19Z)
• PATS: Personality-Aware Teaching Strategies with Large Language Model Tutors [66.56586559631516]
  Large language models (LLMs) have potential as educational tutors.<n>But different tutoring strategies benefit different student personalities.<n>Despite this, current LLM tutoring systems do not take into account student personality traits.
  arXiv  Detail & Related papers  (2026-01-13T10:17:26Z)
• TutorBench: A Benchmark To Assess Tutoring Capabilities Of Large Language Models [10.963195858672627]
  TutorBench is a dataset and evaluation benchmark designed to rigorously evaluate the core tutoring skills of large language models (LLMs)<n>Samples are drawn from three common tutoring tasks: (i) generating adaptive explanations tailored to a student's confusion, (ii) providing actionable feedback on a student's work, and (iii) promoting active learning through effective hint generation.<n>We evaluate 16 frontier LLMs on TutorBench and present a detailed analysis of their performance and behavior.
  arXiv  Detail & Related papers  (2025-10-03T01:41:09Z)
• Teaching Language Models To Gather Information Proactively [53.85419549904644]
  Large language models (LLMs) are increasingly expected to function as collaborative partners.<n>In this work, we introduce a new task paradigm: proactive information gathering.<n>We design a scalable framework that generates partially specified, real-world tasks, masking key information.<n>Within this setup, our core innovation is a reinforcement finetuning strategy that rewards questions that elicit genuinely new, implicit user information.
  arXiv  Detail & Related papers  (2025-07-28T23:50:09Z)
• From Problem-Solving to Teaching Problem-Solving: Aligning LLMs with Pedagogy using Reinforcement Learning [82.50157695987558]
  Large language models (LLMs) can transform education, but their optimization for direct question-answering often undermines effective pedagogy.<n>We propose an online reinforcement learning (RL)-based alignment framework that can quickly adapt LLMs into effective tutors.
  arXiv  Detail & Related papers  (2025-05-21T15:00:07Z)
• Single-Agent vs. Multi-Agent LLM Strategies for Automated Student Reflection Assessment [16.145339327301816]
  Large Language Models (LLMs) can transform student reflections into quantitative scores.<n>LLMs can effectively automate reflection assessment, reduce educators' workload, and enable timely support for students.
  arXiv  Detail & Related papers  (2025-04-08T06:34:15Z)
• Stepwise Verification and Remediation of Student Reasoning Errors with Large Language Model Tutors [78.53699244846285]
  Large language models (LLMs) present an opportunity to scale high-quality personalized education to all. LLMs struggle to precisely detect student's errors and tailor their feedback to these errors. Inspired by real-world teaching practice where teachers identify student errors and customize their response based on them, we focus on verifying student solutions.
  arXiv  Detail & Related papers  (2024-07-12T10:11:40Z)
• Toward Optimal LLM Alignments Using Two-Player Games [86.39338084862324]
  In this paper, we investigate alignment through the lens of two-agent games, involving iterative interactions between an adversarial and a defensive agent. We theoretically demonstrate that this iterative reinforcement learning optimization converges to a Nash Equilibrium for the game induced by the agents. Experimental results in safety scenarios demonstrate that learning in such a competitive environment not only fully trains agents but also leads to policies with enhanced generalization capabilities for both adversarial and defensive agents.
  arXiv  Detail & Related papers  (2024-06-16T15:24:50Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.