Regressive Side Effects of Training Language Models to Mimic Student Misconceptions

• URL: http://arxiv.org/abs/2404.15156v1
• Date: Tue, 23 Apr 2024 15:57:55 GMT
• Title: Regressive Side Effects of Training Language Models to Mimic Student Misconceptions
• Authors: Shashank Sonkar, Naiming Liu, Richard G. Baraniuk,
• Abstract summary: We highlight the problem that as Large Language Models are trained to more accurately mimic student misconceptions, there is a compromise in the factual integrity and reasoning ability of the models. To combat these side effects, we introduced a "hallucination token" technique. This token, appended at the beginning of each student response during training, instructs the model to switch between mimicking student misconceptions and providing factually accurate responses.
• Score: 25.90420385230675
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: This paper presents a novel exploration into the regressive side effects of training Large Language Models (LLMs) to mimic student misconceptions for personalized education. We highlight the problem that as LLMs are trained to more accurately mimic student misconceptions, there is a compromise in the factual integrity and reasoning ability of the models. Our work involved training an LLM on a student-tutor dialogue dataset to predict student responses. The results demonstrated a decrease in the model's performance across multiple benchmark datasets, including the ARC reasoning challenge and TruthfulQA, which evaluates the truthfulness of model's generated responses. Furthermore, the HaluEval Dial dataset, used for hallucination detection, and MemoTrap, a memory-based task dataset, also reported a decline in the model accuracy. To combat these side effects, we introduced a "hallucination token" technique. This token, appended at the beginning of each student response during training, instructs the model to switch between mimicking student misconceptions and providing factually accurate responses. Despite the significant improvement across all datasets, the technique does not completely restore the LLM's baseline performance, indicating the need for further research in this area. This paper contributes to the ongoing discussion on the use of LLMs for student modeling, emphasizing the need for a balance between personalized education and factual accuracy.

Related papers

• EvaLearn: Quantifying the Learning Capability and Efficiency of LLMs via Sequential Problem Solving [61.99289768925256]
  EvaLearn is a benchmark designed to evaluate large language models (LLMs) on their learning capability and efficiency in challenging tasks.<n>We benchmark nine frontier models and observe varied performance profiles.<n>We observe that current LLMs with stronger static abilities do not show a clear advantage in learning capability across all tasks.
  arXiv  Detail & Related papers  (2025-06-03T09:18:33Z)
• MathEDU: Towards Adaptive Feedback for Student Mathematical Problem-Solving [3.2962799070467432]
  This paper explores the capabilities of large language models (LLMs) to assess students' math problem-solving processes and provide adaptive feedback.<n>We evaluate the model's ability to support personalized learning in two scenarios: one where the model has access to students' prior answer histories, and another simulating a cold-start context.
  arXiv  Detail & Related papers  (2025-05-23T15:59:39Z)
• From Problem-Solving to Teaching Problem-Solving: Aligning LLMs with Pedagogy using Reinforcement Learning [76.09281171131941]
  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)
• Personalized Student Knowledge Modeling for Future Learning Resource Prediction [0.0]
  We propose Knowledge Modeling and Material Prediction (KMaP) for personalized and simultaneous modeling of student knowledge and behavior.<n>KMaP employs clustering-based student profiling to create personalized student representations, improving predictions of future learning resource preferences.<n>Experiments on two real-world datasets confirm significant behavioral differences across student clusters.
  arXiv  Detail & Related papers  (2025-05-20T08:23:50Z)
• DistiLLM-2: A Contrastive Approach Boosts the Distillation of LLMs [58.4911494598431]
  DistiLLM-2 is a contrastive approach that simultaneously increases the likelihood of teacher responses and decreases that of student responses. Our experiments show that DistiLLM-2 not only builds high-performing student models across a wide range of tasks, but also supports diverse applications.
  arXiv  Detail & Related papers  (2025-03-10T08:51:32Z)
• Exploring LLM-based Student Simulation for Metacognitive Cultivation [33.346260553878984]
  We propose a pipeline for automatically generating and filtering high-quality simulated student agents. Our work paves the way for broader applications in personalized learning and educational assessment.
  arXiv  Detail & Related papers  (2025-02-17T11:12:47Z)
• Uncovering Student Engagement Patterns in Moodle with Interpretable Machine Learning [0.0]
  This study introduces a methodology for quantifying engagement across an entire module using virtual learning environment (VLE) activity log data. Using study session frequency, immediacy, and diversity, we create a cumulative engagement metric. In a case study of a computing module at University College London's Department of Statistical Science, we examine how delivery methods impact student behaviour.
  arXiv  Detail & Related papers  (2024-12-16T14:47:25Z)
• Students Rather Than Experts: A New AI For Education Pipeline To Model More Human-Like And Personalised Early Adolescences [11.576679362717478]
  This study focuses on language learning as a context for modeling virtual student agents. By curating a dataset of personalized teacher-student interactions with various personality traits, we conduct multi-dimensional evaluation experiments.
  arXiv  Detail & Related papers  (2024-10-21T07:18:24Z)
• LLM-based Cognitive Models of Students with Misconceptions [55.29525439159345]
  This paper investigates whether Large Language Models (LLMs) can be instruction-tuned to meet this dual requirement. We introduce MalAlgoPy, a novel Python library that generates datasets reflecting authentic student solution patterns. Our insights enhance our understanding of AI-based student models and pave the way for effective adaptive learning systems.
  arXiv  Detail & Related papers  (2024-10-16T06:51:09Z)
• 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)
• Evaluating and Optimizing Educational Content with Large Language Model Judgments [52.33701672559594]
  We use Language Models (LMs) as educational experts to assess the impact of various instructions on learning outcomes. We introduce an instruction optimization approach in which one LM generates instructional materials using the judgments of another LM as a reward function. Human teachers' evaluations of these LM-generated worksheets show a significant alignment between the LM judgments and human teacher preferences.
  arXiv  Detail & Related papers  (2024-03-05T09:09:15Z)
• Enhancing Student Performance Prediction on Learnersourced Questions with SGNN-LLM Synergy [11.735587384038753]
  We introduce an innovative strategy that synergizes the potential of integrating Signed Graph Neural Networks (SGNNs) and Large Language Model (LLM) embeddings. Our methodology employs a signed bipartite graph to comprehensively model student answers, complemented by a contrastive learning framework that enhances noise resilience.
  arXiv  Detail & Related papers  (2023-09-23T23:37:55Z)
• Opportunities and Challenges in Neural Dialog Tutoring [54.07241332881601]
  We rigorously analyze various generative language models on two dialog tutoring datasets for language learning. We find that although current approaches can model tutoring in constrained learning scenarios, they perform poorly in less constrained scenarios. Our human quality evaluation shows that both models and ground-truth annotations exhibit low performance in terms of equitable tutoring.
  arXiv  Detail & Related papers  (2023-01-24T11:00:17Z)
• Distantly-Supervised Named Entity Recognition with Adaptive Teacher Learning and Fine-grained Student Ensemble [56.705249154629264]
  Self-training teacher-student frameworks are proposed to improve the robustness of NER models. In this paper, we propose an adaptive teacher learning comprised of two teacher-student networks. Fine-grained student ensemble updates each fragment of the teacher model with a temporal moving average of the corresponding fragment of the student, which enhances consistent predictions on each model fragment against noise.
  arXiv  Detail & Related papers  (2022-12-13T12:14:09Z)
• Large Language Models with Controllable Working Memory [64.71038763708161]
  Large language models (LLMs) have led to a series of breakthroughs in natural language processing (NLP) What further sets these models apart is the massive amounts of world knowledge they internalize during pretraining. How the model's world knowledge interacts with the factual information presented in the context remains under explored.
  arXiv  Detail & Related papers  (2022-11-09T18:58:29Z)
• Student-centric Model of Learning Management System Activity and Academic Performance: from Correlation to Causation [2.169383034643496]
  In recent years, there is a lot of interest in modeling students' digital traces in Learning Management System (LMS) to understand students' learning behavior patterns. This paper explores a student-centric analytical framework for LMS activity data that can provide not only correlational but causal insights mined from observational data. We envision that those insights will provide convincing evidence for college student support groups to launch student-centered and targeted interventions.
  arXiv  Detail & Related papers  (2022-10-27T14:08:25Z)
• Knowledge Tracing for Complex Problem Solving: Granular Rank-Based Tensor Factorization [6.077274947471846]
  We propose a novel student knowledge tracing approach, Granular RAnk based TEnsor factorization (GRATE) GRATE selects student attempts that can be aggregated while predicting students' performance in problems and discovering the concepts presented in them. Our experiments on three real-world datasets demonstrate the improved performance of GRATE, compared to the state-of-the-art baselines.
  arXiv  Detail & Related papers  (2022-10-06T06:22:46Z)

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.