Can LLMs Identify Gaps and Misconceptions in Students' Code Explanations?

• URL: http://arxiv.org/abs/2501.10365v1
• Date: Mon, 09 Dec 2024 19:42:23 GMT
• Title: Can LLMs Identify Gaps and Misconceptions in Students' Code Explanations?
• Abstract summary: This paper investigates various approaches using Large Language Models (LLMs) to identify gaps and misconceptions in students' self-explanations of specific instructional material.<n>With simple prompting, GPT-4 consistently outperformed LLaMA3 and Mistral in identifying gaps and misconceptions.<n>Our results suggest that fine-tuned large language models are more effective at identifying gaps in students' explanations.
• Score: 0.3015291944961405
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: This paper investigates various approaches using Large Language Models (LLMs) to identify gaps and misconceptions in students' self-explanations of specific instructional material, in our case explanations of code examples. This research is a part of our larger effort to automate the assessment of students' freely generated responses, focusing specifically on their self-explanations of code examples during activities related to code comprehension. In this work, we experiment with zero-shot prompting, Supervised Fine-Tuning (SFT), and preference alignment of LLMs to identify gaps in students' self-explanation. With simple prompting, GPT-4 consistently outperformed LLaMA3 and Mistral in identifying gaps and misconceptions, as confirmed by human evaluations. Additionally, our results suggest that fine-tuned large language models are more effective at identifying gaps in students' explanations compared to zero-shot and few-shot prompting techniques. Furthermore, our findings show that the preference optimization approach using Odds Ratio Preference Optimization (ORPO) outperforms SFT in identifying gaps and misconceptions in students' code explanations.

Related papers

• LC-ICL: Label-Guided Contrastive In-Context Learning for Robust Information Extraction [5.542001452666451]
  In this paper, we present LC-ICL, a novel few-shot technique that leverages both correct and incorrect sample constructions to create in-context learning demonstrations.<n>Our experiments on various datasets indicate that LC-ICL outperforms previous few-shot in-context learning methods.
  arXiv  Detail & Related papers  (2026-06-28T14:01:52Z)
• From latent factors to language: a user study on LLM-generated explanations for an inherently interpretable matrix-based recommender system [8.280161440212504]
  We investigate whether large language models (LLMs) can generate effective, user-facing explanations from a mathematically interpretable recommendation model.<n>We conduct a study with 326 participants who assessed the quality of the explanations across five key dimensions.<n>Our analysis reveals that all explanation types are generally well received, with moderate statistical differences between strategies.
  arXiv  Detail & Related papers  (2025-09-23T13:30:03Z)
• Can Large Language Models Match Tutoring System Adaptivity? A Benchmarking Study [0.0]
  Large Language Models (LLMs) hold promise as dynamic instructional aids. Yet, it remains unclear whether LLMs can replicate the adaptivity of intelligent tutoring systems (ITS)
  arXiv  Detail & Related papers  (2025-04-07T23:57:32Z)
• Source Code Summarization in the Era of Large Language Models [23.715005053430957]
  Large language models (LLMs) have led to a great boost in the performance of code-related tasks. In this paper, we undertake a systematic and comprehensive study on code summarization in the era of LLMs.
  arXiv  Detail & Related papers  (2024-07-09T05:48:42Z)
• Evaluating Human Alignment and Model Faithfulness of LLM Rationale [66.75309523854476]
  We study how well large language models (LLMs) explain their generations through rationales. We show that prompting-based methods are less "faithful" than attribution-based explanations.
  arXiv  Detail & Related papers  (2024-06-28T20:06:30Z)
• Aligning Language Models with Demonstrated Feedback [58.834937450242975]
  Demonstration ITerated Task Optimization (DITTO) directly aligns language model outputs to a user's demonstrated behaviors. We evaluate DITTO's ability to learn fine-grained style and task alignment across domains such as news articles, emails, and blog posts.
  arXiv  Detail & Related papers  (2024-06-02T23:13:56Z)
• Instruction Tuning with Retrieval-based Examples Ranking for Aspect-based Sentiment Analysis [7.458853474864602]
  Aspect-based sentiment analysis (ABSA) identifies sentiment information related to specific aspects and provides deeper market insights to businesses and organizations. Recent studies have proposed using fixed examples for instruction tuning to reformulate ABSA as a generation task. This study proposes an instruction learning method with retrieval-based example ranking for ABSA tasks.
  arXiv  Detail & Related papers  (2024-05-28T10:39:10Z)
• C-ICL: Contrastive In-context Learning for Information Extraction [54.39470114243744]
  c-ICL is a novel few-shot technique that leverages both correct and incorrect sample constructions to create in-context learning demonstrations. Our experiments on various datasets indicate that c-ICL outperforms previous few-shot in-context learning methods.
  arXiv  Detail & Related papers  (2024-02-17T11:28:08Z)
• LogicAsker: Evaluating and Improving the Logical Reasoning Ability of Large Language Models [63.14196038655506]
  We introduce LogicAsker, a novel approach for evaluating and enhancing the logical reasoning capabilities of large language models (LLMs) Our methodology reveals significant gaps in LLMs' learning of logical rules, with identified reasoning failures ranging from 29% to 90% across different models. We leverage these findings to construct targeted demonstration examples and fine-tune data, notably enhancing logical reasoning in models like GPT-4o by up to 5%.
  arXiv  Detail & Related papers  (2024-01-01T13:53:53Z)
• Unlocking the Potential of Large Language Models for Explainable Recommendations [55.29843710657637]
  It remains uncertain what impact replacing the explanation generator with the recently emerging large language models (LLMs) would have. In this study, we propose LLMXRec, a simple yet effective two-stage explainable recommendation framework. By adopting several key fine-tuning techniques, controllable and fluent explanations can be well generated.
  arXiv  Detail & Related papers  (2023-12-25T09:09:54Z)
• Automated Assessment of Students' Code Comprehension using LLMs [0.3293989832773954]
  Large Language Models (LLMs) and encoder-based Semantic Textual Similarity (STS) models are assessed. Our findings indicate that LLMs, when prompted in few-shot and chain-of-thought setting, perform comparable to fine-tuned encoder-based models in evaluating students' short answers in programming domain.
  arXiv  Detail & Related papers  (2023-12-19T20:39:12Z)
• Language models are weak learners [71.33837923104808]
  We show that prompt-based large language models can operate effectively as weak learners. We incorporate these models into a boosting approach, which can leverage the knowledge within the model to outperform traditional tree-based boosting. Results illustrate the potential for prompt-based LLMs to function not just as few-shot learners themselves, but as components of larger machine learning pipelines.
  arXiv  Detail & Related papers  (2023-06-25T02:39:19Z)
• Complementary Explanations for Effective In-Context Learning [77.83124315634386]
  Large language models (LLMs) have exhibited remarkable capabilities in learning from explanations in prompts. This work aims to better understand the mechanisms by which explanations are used for in-context learning.
  arXiv  Detail & Related papers  (2022-11-25T04:40:47Z)

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.