Papers by Richard Baraniuk
CLASS: A Design Framework for Building Intelligent Tutoring Systems Based on Learning Science principles (2023.findings-emnlp)
Copied to clipboard
| Challenge: | CLASS empowers ITS with two key capabilities: first, it equips it with essential problem-solving strategies, and second, it facilitates natural language interactions, fostering engaging student-tutor conversations. |
| Approach: | They propose a design framework called Conversational Learning with Analytical Step-by-Step Strategies (CLASS) that empowers ITS with two key capabilities: first, a carefully curated dataset and second, facilitating natural language interactions. |
| Outcome: | The proposed framework empowers ITS with two key capabilities: first, it equips it with essential problem-solving strategies, and second, it facilitates natural language interactions, fostering engaging student-tutor conversations. |
Open-ended Knowledge Tracing for Computer Science Education (2022.emnlp-main)
Copied to clipboard
| Challenge: | Knowledge tracing (KT) is a method used to estimate student mastery of concepts/skills/knowledge components from their responses to questions and to predict future performance. |
| Approach: | They propose a student knowledge-guided code generation approach that combines program synthesis methods with student knowledge tracing methods to solve the OKT problem. |
| Outcome: | The proposed method is based on a student knowledge-guided code generation approach and validates on coding questions. |
Attention Word Embedding (2020.coling-main)
Copied to clipboard
| Challenge: | Word embedding models learn semantically rich vector representations of words . popular word embedders include word2vec, GloVe, and fastText . |
| Approach: | They propose an AWE-S model which integrates the attention mechanism into the CBOW model and incorporates subword information. |
| Outcome: | The proposed model outperforms the state-of-the-art model on word similarity datasets and when used for initialization of NLP models. |
CLEAR-3K: Assessing Causal Explanatory Capabilities in Language Models (2026.findings-eacl)
Copied to clipboard
| Challenge: | Existing natural language understanding benchmarks inadequately address the ability to evaluate causal relationships. |
| Approach: | They propose to use CLEAR-3K to evaluate whether language models can determine if one statement causally explains another. |
| Outcome: | The proposed questions show that language models often confuse semantic similarity with causality, relying on lexical and semantic overlap instead of inferring actual causal explanatory relationships. |
Math Word Problem Generation with Mathematical Consistency and Problem Context Constraints (2021.emnlp-main)
Copied to clipboard
| Challenge: | Existing approaches to generate arithmetic math word problems are invalid or have unsatisfactory language quality. |
| Approach: | They propose a method for automatically generating arithmetic math word problems from equations and context. |
| Outcome: | The proposed approach improves language quality and mathematical validity on three real-world MWP datasets. |
Student Data Paradox and Curious Case of Single Student-Tutor Model: Regressive Side Effects of Training LLMs for Personalized Learning (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) are being developed to provide personalized tutoring systems that can understand and adapt to individual student needs. |
| Approach: | They propose to train large language models on student-tutor dialogue datasets to understand student behavior and evaluate their performance across multiple benchmarks. |
| Outcome: | The proposed model performance declines across multiple benchmarks, indicating a broad impact on their capabilities when trained to model student behavior. |
MalAlgoQA: Pedagogical Evaluation of Counterfactual Reasoning in Large Language Models and Implications for AI in Education (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Using a novel dataset, we evaluate the counterfactual reasoning capabilities of Large Language Models (LLMs) . |
| Approach: | They propose a dataset to evaluate the counterfactual reasoning capabilities of Large Language Models (LLMs) using a pedagogical approach. |
| Outcome: | The proposed method mimics how educators anticipate and model potential student misconceptions by creating plausible but incorrect answer options by envisioning hypothetical scenarios and logically coherent reasoning paths. |
Pedagogical Alignment of Large Language Models (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) are often used without pedagogical fine-tuning and provide immediate answers rather than guiding students through the problem-solving process. |
| Approach: | They propose a method for constructing large-scale preference datasets using synthetic data generation techniques that eliminates the need for manual annotation. |
| Outcome: | The proposed methods outperform standard supervised fine-tuning (SFT) and improve alignment accuracy by 13.1% and 8.7% respectively. |