# Harnessing LLM for Noise-Robust Cognitive Diagnosis in Web-Based Intelligent Education Systems

arXiv: https://arxiv.org/abs/2510.04093 · HTML: https://mlsanity.com/paper/2510.04093/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Discrete and text diffusion, one of 14 directions in Diffusion models.
- Builds on 18 of its 47 references that are in the map.
- First posted on arXiv 5 Oct 2025.

## Placed in

- Diffusion models / [Discrete and text diffusion](https://mlsanity.com/diffusion/discrete-and-text-diffusion/)

## Builds on (most cited first, 18 of 18)

- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [FiLM: Visual Reasoning with a General Conditioning Layer](https://mlsanity.com/paper/1709.07871/) (2017)
- [LightGCN: Simplifying and Powering Graph Convolution Network for Recommendation](https://mlsanity.com/paper/2002.02126/) (2020)
- [HaloScope: Harnessing Unlabeled LLM Generations for Hallucination Detection](https://mlsanity.com/paper/2409.17504/) (2024)
- [Neural Cognitive Diagnosis for Intelligent Education Systems](https://mlsanity.com/paper/1908.08733/) (2019)
- [Generative Students: Using LLM-Simulated Student Profiles to Support Question Item Evaluation](https://mlsanity.com/paper/2405.11591/) (2024)
- [Position-aware Structure Learning for Graph Topology-imbalance by Relieving Under-reaching and Over-squashing](https://mlsanity.com/paper/2208.08302/) (2022)
- [Hyperbolic Geometric Graph Representation Learning for Hierarchy-imbalance Node Classification](https://mlsanity.com/paper/2304.05059/) (2023)
- [Inductive Cognitive Diagnosis for Fast Student Learning in Web-Based Online Intelligent Education Systems](https://mlsanity.com/paper/2404.11290/) (2024)
- [Self-supervised Graph Learning for Long-tailed Cognitive Diagnosis](https://mlsanity.com/paper/2210.08169/) (2022)
- [Knowledge is Power: Harnessing Large Language Models for Enhanced Cognitive Diagnosis](https://mlsanity.com/paper/2502.05556/) (2025)
- [Mitigating Propensity Bias of Large Language Models for Recommender Systems](https://mlsanity.com/paper/2409.20052/) (2024)
- [Poincar'e Differential Privacy for Hierarchy-Aware Graph Embedding](https://mlsanity.com/paper/2312.12183/) (2023)
- [Fairness Evaluation with Item Response Theory](https://mlsanity.com/paper/2411.02414/) (2024)
- [ORCDF: An Oversmoothing-Resistant Cognitive Diagnosis Framework for Student Learning in Online Education Systems](https://mlsanity.com/paper/2407.17476/) (2024)
- [Unbiased Reasoning for Knowledge-Intensive Tasks in Large Language Models via Conditional Front-Door Adjustment](https://mlsanity.com/paper/2508.16910/) (2025)
- [Exploring Heterogeneity and Uncertainty for Graph-based Cognitive Diagnosis Models in Intelligent Education](https://mlsanity.com/paper/2403.05559/) (2024)
- [An Item Response Theory-based R Module for Algorithm Portfolio Analysis](https://mlsanity.com/paper/2408.14025/) (2024)

## Abstract (arXiv)

Cognitive diagnostics in the Web-based Intelligent Education System (WIES) aims to assess students' mastery of knowledge concepts from heterogeneous, noisy interactions. Recent work has tried to utilize Large Language Models (LLMs) for cognitive diagnosis, yet LLMs struggle with structured data and are prone to noise-induced misjudgments. Specially, WIES's open environment continuously attracts new students and produces vast amounts of response logs, exacerbating the data imbalance and noise issues inherent in traditional educational systems. To address these challenges, we propose DLLM, a Diffusion-based LLM framework for noise-robust cognitive diagnosis. DLLM first constructs independent subgraphs based on response correctness, then applies relation augmentation alignment module to mitigate data imbalance. The two subgraph representations are then fused and aligned with LLM-derived, semantically augmented representations. Importantly, before each alignment step, DLLM employs a two-stage denoising diffusion module to eliminate intrinsic noise while assisting structural representation alignment. Specifically, unconditional denoising diffusion first removes erroneous information, followed by conditional denoising diffusion based on graph-guided to eliminate misleading information. Finally, the noise-robust representation that integrates semantic knowledge and structural information is fed into existing cognitive diagnosis models for prediction. Experimental results on three publicly available web-based educational platform datasets demonstrate that our DLLM achieves optimal predictive performance across varying noise levels, which demonstrates that DLLM achieves noise robustness while effectively leveraging semantic knowledge from LLM.