Shashank Sonkar

Orcid: 0000-0002-4409-1341

According to our database1, Shashank Sonkar authored at least 40 papers between 2020 and 2026.

Collaborative distances:

Timeline

Legend:

Book  In proceedings  Article  PhD thesis  Dataset  Other 

Links

Online presence:

On csauthors.net:

Bibliography

2026
Misconception Acquisition Dynamics in Large Language Models.
CoRR, April, 2026

When Can We Trust LLM Graders? Calibrating Confidence for Automated Assessment.
CoRR, March, 2026

Circuit Complexity of Hierarchical Knowledge Tracing and Implications for Log-Precision Transformers.
CoRR, March, 2026

Can LLMs Model Incorrect Student Reasoning? A Case Study on Distractor Generation.
CoRR, March, 2026

Scalable Generation and Validation of Isomorphic Physics Problems with GenAI.
CoRR, February, 2026

MetaCLASS: Metacognitive Coaching for Learning with Adaptive Self-regulation Support.
CoRR, February, 2026

FoundationalASSIST: An Educational Dataset for Foundational Knowledge Tracing and Pedagogical Grounding of LLMs.
CoRR, February, 2026

MalruleLib: Large-Scale Executable Misconception Reasoning with Step Traces for Modeling Student Thinking in Mathematics.
CoRR, January, 2026

CLEAR-3K: Assessing Causal Explanatory Capabilities in Language Models.
Proceedings of the Findings of the Association for Computational Linguistics: EACL 2026, 2026

2025
Do LLMs Make Mistakes Like Students? Exploring Natural Alignment between Language Models and Human Error Patterns.
CoRR, February, 2025

The Imitation Game for Educational AI.
CoRR, February, 2025

Atomic Learning Objectives and LLMs Labeling: A High-Resolution Approach for Physics Education.
Proceedings of the 15th International Learning Analytics and Knowledge Conference, 2025

Large Language Models for Education: Understanding the Needs of Stakeholders, Current Capabilities and the Path Forward.
Proceedings of the 20th Workshop on Innovative Use of NLP for Building Educational Applications, 2025

Turing-Like Test for Personalized Educational AI.
Proceedings of the Artificial Intelligence in Education - 26th International Conference, 2025

Many-Shot Regurgitation Prompting.
Proceedings of the Artificial Intelligence in Education - 26th International Conference, 2025

Do LLMs Make Mistakes Like Students? Exploring Natural Alignments Between Language Models and Human Error Patterns.
Proceedings of the Artificial Intelligence in Education - 26th International Conference, 2025

2024
Atomic Learning Objectives Labeling: A High-Resolution Approach for Physics Education.
CoRR, 2024

LLM-based Cognitive Models of Students with Misconceptions.
CoRR, 2024

MalAlgoQA: A Pedagogical Approach for Evaluating Counterfactual Reasoning Abilities.
CoRR, 2024

Many-Shot Regurgitation (MSR) Prompting.
CoRR, 2024

Regressive Side Effects of Training Language Models to Mimic Student Misconceptions.
CoRR, 2024

Code Soliloquies for Accurate Calculations in Large Language Models.
Proceedings of the 14th Learning Analytics and Knowledge Conference, 2024

Pedagogical Alignment of Large Language Models.
Proceedings of the Findings of the Association for Computational Linguistics: EMNLP 2024, 2024

MalAlgoQA: Pedagogical Evaluation of Counterfactual Reasoning in Large Language Models and Implications for AI in Education.
Proceedings of the Findings of the Association for Computational Linguistics: EMNLP 2024, 2024

Student Data Paradox and Curious Case of Single Student-Tutor Model: Regressive Side Effects of Training LLMs for Personalized Learning.
Proceedings of the Findings of the Association for Computational Linguistics: EMNLP 2024, 2024


Automated Long Answer Grading with RiceChem Dataset.
Proceedings of the Artificial Intelligence in Education - 25th International Conference, 2024

Marking: Visual Grading with Highlighting Errors and Annotating Missing Bits.
Proceedings of the Artificial Intelligence in Education - 25th International Conference, 2024

2023
Novice Learner and Expert Tutor: Evaluating Math Reasoning Abilities of Large Language Models with Misconceptions.
CoRR, 2023

Deduction under Perturbed Evidence: Probing Student Simulation Capabilities of Large Language Models.
CoRR, 2023

Investigating the Role of Feed-Forward Networks in Transformers Using Parallel Attention and Feed-Forward Net Design.
CoRR, 2023

CLASS Meet SPOCK: An Education Tutoring Chatbot based on Learning Science Principles.
CoRR, 2023

MANER: Mask Augmented Named Entity Recognition for Extreme Low-Resource Languages.
Proceedings of The Fourth Workshop on Simple and Efficient Natural Language Processing, 2023

CLASS: A Design Framework for Building Intelligent Tutoring Systems Based on Learning Science principles.
Proceedings of the Findings of the Association for Computational Linguistics: EMNLP 2023, 2023

Deduction under Perturbed Evidence: Probing Student Simulation (Knowledge Tracing) Capabilities of Large Language Models.
Proceedings of the Workshop on Empowering Education with LLMs, 2023

2022
A Visual Tour Of Current Challenges In Multimodal Language Models.
CoRR, 2022

2021
NePTuNe: Neural Powered Tucker Network for Knowledge Graph Completion.
CoRR, 2021

NePTuNe: Neural Powered Tucker Networkfor Knowledge Graph Completion.
Proceedings of the IJCKG'21: The 10th International Joint Conference on Knowledge Graphs, Virtual Event, Thailand, December 6, 2021

2020
qDKT: Question-centric Deep Knowledge Tracing.
Proceedings of the 13th International Conference on Educational Data Mining, 2020

Attention Word Embedding.
Proceedings of the 28th International Conference on Computational Linguistics, 2020


  Loading...