# Tailoring Diagnostic Modeling to Individual Learners: Personalized Distractor Generation via MCTS-Guided Reasoning Reconstruction

arXiv: https://arxiv.org/abs/2508.11184 · HTML: https://mlsanity.com/paper/2508.11184/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 31 of its 61 references that are in the map.
- First posted on arXiv 15 Aug 2025.

## Builds on (most cited first, 30 of 31)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [C-Eval: A Multi-Level Multi-Discipline Chinese Evaluation Suite for Foundation Models](https://mlsanity.com/paper/2305.08322/) (2023)
- [ReST-MCTS*: LLM Self-Training via Process Reward Guided Tree Search](https://mlsanity.com/paper/2406.03816/) (2024)
- [AlphaMath Almost Zero: Process Supervision without Process](https://mlsanity.com/paper/2405.03553/) (2024)
- [Accessing GPT-4 level Mathematical Olympiad Solutions via Monte Carlo Tree Self-refine with LLaMa-3 8B](https://mlsanity.com/paper/2406.07394/) (2024)
- [Bridging the Novice-Expert Gap via Models of Decision-Making: A Case Study on Remediating Math Mistakes](https://mlsanity.com/paper/2310.10648/) (2023)
- [AutoGeo: Automating Geometric Image Dataset Creation for Enhanced Geometry Understanding](https://mlsanity.com/paper/2409.09039/) (2024)
- [Distractor Generation in Multiple-Choice Tasks: A Survey of Methods, Datasets, and Evaluation](https://mlsanity.com/paper/2402.01512/) (2024)
- [Embracing Imperfection: Simulating Students with Diverse Cognitive Levels Using LLM-based Agents](https://mlsanity.com/paper/2505.19997/) (2025)
- [Results and Insights from Diagnostic Questions: The NeurIPS 2020 Education Challenge](https://mlsanity.com/paper/2104.04034/) (2021)
- [LLM-based Cognitive Models of Students with Misconceptions](https://mlsanity.com/paper/2410.12294/) (2024)
- [Distractor generation for multiple-choice questions with predictive prompting and large language models](https://mlsanity.com/paper/2307.16338/) (2023)
- [Towards Transformer-Based Aligned Generation with Self-Coherence Guidance](https://mlsanity.com/paper/2503.17675/) (2025)
- [Improving Automated Distractor Generation for Math Multiple-choice Questions with Overgenerate-and-rank](https://mlsanity.com/paper/2405.05144/) (2024)
- [Option Tracing: Beyond Correctness Analysis in Knowledge Tracing](https://mlsanity.com/paper/2104.09043/) (2021)
- [ModelGPT: Unleashing LLM's Capabilities for Tailored Model Generation](https://mlsanity.com/paper/2402.12408/) (2024)
- [Knowledge is Power: Harnessing Large Language Models for Enhanced Cognitive Diagnosis](https://mlsanity.com/paper/2502.05556/) (2025)
- [No Task Left Behind: Multi-Task Learning of Knowledge Tracing and Option Tracing for Better Student Assessment](https://mlsanity.com/paper/2204.14006/) (2022)
- [Generating Plausible Distractors for Multiple-Choice Questions via Student Choice Prediction](https://mlsanity.com/paper/2501.13125/) (2025)
- [Multiple-Choice Question Generation Using Large Language Models: Methodology and Educator Insights](https://mlsanity.com/paper/2506.04851/) (2025)
- [DiVERT: Distractor Generation with Variational Errors Represented as Text for Math Multiple-choice Questions](https://mlsanity.com/paper/2406.19356/) (2024)
- [LookAlike: Consistent Distractor Generation in Math MCQs](https://mlsanity.com/paper/2505.01903/) (2025)
- [A Comprehensive Exploration of Personalized Learning in Smart Education: From Student Modeling to Personalized Recommendations](https://mlsanity.com/paper/2402.01666/) (2024)
- [DisGeM: Distractor Generation for Multiple Choice Questions with Span Masking](https://mlsanity.com/paper/2409.18263/) (2024)
- [Sigma: Differential Rescaling of Query, Key and Value for Efficient Language Models](https://mlsanity.com/paper/2501.13629/) (2025)
- [Diff-Prompt: Diffusion-Driven Prompt Generator with Mask Supervision](https://mlsanity.com/paper/2504.21423/) (2025)
- [WisdomBot: Tuning Large Language Models with Artificial Intelligence Knowledge](https://mlsanity.com/paper/2501.12877/) (2025)

## Built on by (most cited first, 3 of 3)

- [Mnemis: Dual-Route Retrieval on Hierarchical Graphs for Long-Term LLM Memory](https://mlsanity.com/paper/2602.15313/) (2026)
- [Cognitive-Level Adaptive Generation via Capability-Aware Retrieval and Style Adaptation](https://mlsanity.com/paper/2509.19336/) (2025)
- [When LLM Meets Tree Search: A Systematic View of Inference as Search in Large Language Models](https://mlsanity.com/paper/2608.30395/) (2026)

## Abstract (arXiv)

Distractors-incorrect yet plausible answer choices in multiple-choice questions (MCQs)-are vital in educational assessments, as they help identify student misconceptions by presenting potential reasoning errors. Current distractor generation methods typically produce shared distractors for all students, ignoring the individual variations in reasoning, which limits their diagnostic effectiveness. To tackle this challenge, we introduce the task of Personalized Distractor Generation, which tailors distractors to each student's specific cognitive flaws, inferred from their past question-answering (QA) history. While promising, this task is particularly demanding due to the limited number of QA records available for each student, which are insufficient for training, as well as the absence of their underlying reasoning process. To overcome this, we propose a novel, training-free two-stage framework. In the first stage, Monte Carlo Tree Search (MCTS) is used to reconstruct the student's reasoning process from past errors, creating a student-specific misconception prototype. In the second stage, this prototype guides the simulation of the student's reasoning on new questions, generating personalized distractors that resonate with their individual misconceptions. Our experiments, conducted on 1,361 students across 6 subjects, demonstrate that this approach outperforms existing methods in generating plausible, personalized distractors, and also effectively adapts to group-level settings, highlighting its robustness and versatility.