Shashank Sonkar

47 papers A 2B 3Journal 28Unranked 13

Year	Rank	Type	Title / Venue / Authors
2026	—	`conf`	CLEAR-3K: Assessing Causal Explanatory Capabilities in Language Models. EACL (Findings) Naiming Liu, Richard G. Baraniuk, Shashank Sonkar
2026	J	`jnl`	Can LLMs Model Incorrect Student Reasoning? A Case Study on Distractor Generation. CoRR Yanick Zengaffinen, Andreas Opedal, Donya Rooein, KV Aditya Srivatsa, Shashank Sonkar, Mrinmaya Sachan
2026	J	`jnl`	Circuit Complexity of Hierarchical Knowledge Tracing and Implications for Log-Precision Transformers. CoRR Naiming Liu, Richard G. Baraniuk, Shashank Sonkar
2026	J	`jnl`	FoundationalASSIST: An Educational Dataset for Foundational Knowledge Tracing and Pedagogical Grounding of LLMs. CoRR Eamon Worden, Cristina Heffernan, Neil T. Heffernan, Shashank Sonkar
2026	J	`jnl`	MalruleLib: Large-Scale Executable Misconception Reasoning with Step Traces for Modeling Student Thinking in Mathematics. CoRR Xinghe Chen, Naiming Liu, Shashank Sonkar
2026	J	`jnl`	MetaCLASS: Metacognitive Coaching for Learning with Adaptive Self-regulation Support. CoRR Naiming Liu, Richard G. Baraniuk, Shashank Sonkar
2026	J	`jnl`	Scalable Generation and Validation of Isomorphic Physics Problems with GenAI. CoRR Naiming Liu, Leo Murch, Spencer Moore, Tong Wan, Shashank Sonkar, Richard G. Baraniuk, Zhongzhou Chen
2026	J	`jnl`	When Can We Trust LLM Graders? Calibrating Confidence for Automated Assessment. CoRR Robinson Ferrer, Damla Turgut, Zhongzhou Chen, Shashank Sonkar
2025	A	`conf`	Atomic Learning Objectives and LLMs Labeling: A High-Resolution Approach for Physics Education. LAK Naiming Liu, Shashank Sonkar, Debshila Basu Mallick, Richard G. Baraniuk, Zhongzhou Chen
2025	J	`jnl`	CLEAR-3K: Assessing Causal Explanatory Capabilities in Language Models. CoRR Naiming Liu, Richard G. Baraniuk, Shashank Sonkar
2025	J	`jnl`	Do LLMs Make Mistakes Like Students? Exploring Natural Alignment between Language Models and Human Error Patterns. CoRR Naiming Liu, Shashank Sonkar, Richard G. Baraniuk
2025	—	`conf`	Do LLMs Make Mistakes Like Students? Exploring Natural Alignments Between Language Models and Human Error Patterns. AIED (4) Naiming Liu, Shashank Sonkar, Richard G. Baraniuk
2025	—	`conf`	Many-Shot Regurgitation Prompting. AIED (5) Shashank Sonkar, Naiming Liu, Richard G. Baraniuk
2025	J	`jnl`	The Imitation Game for Educational AI. CoRR Shashank Sonkar, Naiming Liu, Xinghe Chen, Richard G. Baraniuk
2025	—	`conf`	Turing-Like Test for Personalized Educational AI. AIED (6) Shashank Sonkar, Naiming Liu, Xinghe Chen, Richard G. Baraniuk
2024	J	`jnl`	Atomic Learning Objectives Labeling: A High-Resolution Approach for Physics Education. CoRR Naiming Liu, Shashank Sonkar, Debshila Basu Mallick, Richard G. Baraniuk, Zhongzhou Chen
2024	—	`conf`	Automated Long Answer Grading with RiceChem Dataset. AIED (1) Shashank Sonkar, Kangqi Ni, Lesa Tran Lu, Kristi Kincaid, John S. Hutchinson, Richard G. Baraniuk
2024	J	`jnl`	Automated Long Answer Grading with RiceChem Dataset. CoRR Shashank Sonkar, Kangqi Ni, Lesa Tran Lu, Kristi Kincaid, John S. Hutchinson, Richard G. Baraniuk
2024	A	`conf`	Code Soliloquies for Accurate Calculations in Large Language Models. LAK Shashank Sonkar, Xinghe Chen, Myco Le, Naiming Liu, Debshila Basu Mallick, Richard G. Baraniuk
2024	—	`ed.`	Joint Proceedings of the Human-Centric eXplainable AI in Education and the Leveraging Large Language Models for Next Generation Educational Technologies Workshops (HEXED-L3MNGET 2024) co-located with 17th International Conference on Educational Data Mining (EDM 2024), Atlanta, Georgia, USA, July 14, 2024. HEXED/L3MNGET@EDM Juan D. Pinto, Eamon Worden, Anthony Botelho, Lea Cohausz, Clayton Cohn, Mingyu Feng, Neil T. Heffernan, Arto Hellas, Lan Jiang, David Joyner, Tanja Käser, Juho Kim, Andrew S. Lan, Chenglu Li, Joshua Littenberg-Tobias, Qianhui Liu, Christopher MacLellan, Steven Moore, Maciej Pankiewicz, Luc Paquette, Zach A. Pardos, Anna N. Rafferty, Adish Singla, Shashank Sonkar, Vinitra Swamy, Rose E. Wang, Candace A. Walkington
2024	J	`jnl`	LLM-based Cognitive Models of Students with Misconceptions. CoRR Shashank Sonkar, Xinghe Chen, Naiming Liu, Richard G. Baraniuk, Mrinmaya Sachan
2024	B	`conf`	Leveraging Large Language Models for Next-Generation Educational Technologies. EDM Neil T. Heffernan, Rose E. Wang, Christopher MacLellan, Arto Hellas, Chenglu Li, Candace A. Walkington, Joshua Littenberg-Tobias, David Joyner, Steven Moore, Adish Singla, Zach A. Pardos, Maciej Pankiewicz, Juho Kim, Shashank Sonkar, Clayton Cohn, Anthony Botelho, Andrew S. Lan, Lan Jiang, Mingyu Feng, Tanja Käser, Eamon Worden
2024	J	`jnl`	MalAlgoQA: A Pedagogical Approach for Evaluating Counterfactual Reasoning Abilities. CoRR Naiming Liu, Shashank Sonkar, Myco Le, Richard G. Baraniuk
2024	—	`conf`	MalAlgoQA: Pedagogical Evaluation of Counterfactual Reasoning in Large Language Models and Implications for AI in Education. EMNLP (Findings) Shashank Sonkar, Naiming Liu, Myco Le, Richard G. Baraniuk
2024	J	`jnl`	Many-Shot Regurgitation (MSR) Prompting. CoRR Shashank Sonkar, Richard G. Baraniuk
2024	—	`conf`	Marking: Visual Grading with Highlighting Errors and Annotating Missing Bits. AIED (1) Shashank Sonkar, Naiming Liu, Debshila Basu Mallick, Richard G. Baraniuk
2024	J	`jnl`	Marking: Visual Grading with Highlighting Errors and Annotating Missing Bits. CoRR Shashank Sonkar, Naiming Liu, Debshila Basu Mallick, Richard G. Baraniuk
2024	—	`conf`	Pedagogical Alignment of Large Language Models. EMNLP (Findings) Shashank Sonkar, Kangqi Ni, Sapana Chaudhary, Richard G. Baraniuk
2024	J	`jnl`	Pedagogical Alignment of Large Language Models. CoRR Shashank Sonkar, Kangqi Ni, Sapana Chaudhary, Richard G. Baraniuk
2024	J	`jnl`	Regressive Side Effects of Training Language Models to Mimic Student Misconceptions. CoRR Shashank Sonkar, Naiming Liu, Richard G. Baraniuk
2024	—	`conf`	Student Data Paradox and Curious Case of Single Student-Tutor Model: Regressive Side Effects of Training LLMs for Personalized Learning. EMNLP (Findings) Shashank Sonkar, Naiming Liu, Richard G. Baraniuk
2023	J	`jnl`	CLASS Meet SPOCK: An Education Tutoring Chatbot based on Learning Science Principles. CoRR Shashank Sonkar, Lucy Liu, Debshila Basu Mallick, Richard G. Baraniuk
2023	—	`conf`	CLASS: A Design Framework for Building Intelligent Tutoring Systems Based on Learning Science principles. EMNLP (Findings) Shashank Sonkar, Naiming Liu, Debshila Basu Mallick, Richard G. Baraniuk
2023	J	`jnl`	Code Soliloquies for Accurate Calculations in Large Language Models. CoRR Shashank Sonkar, Myco Le, Xinghe Chen, Naiming Liu, Debshila Basu Mallick, Richard G. Baraniuk
2023	—	`conf`	Deduction under Perturbed Evidence: Probing Student Simulation (Knowledge Tracing) Capabilities of Large Language Models. LLM@AIED Shashank Sonkar, Richard G. Baraniuk
2023	J	`jnl`	Deduction under Perturbed Evidence: Probing Student Simulation Capabilities of Large Language Models. CoRR Shashank Sonkar, Richard G. Baraniuk
2023	J	`jnl`	Investigating the Role of Feed-Forward Networks in Transformers Using Parallel Attention and Feed-Forward Net Design. CoRR Shashank Sonkar, Richard G. Baraniuk
2023	—	`conf`	MANER: Mask Augmented Named Entity Recognition for Extreme Low-Resource Languages. SustaiNLP Shashank Sonkar, Zichao Wang, Richard G. Baraniuk
2023	J	`jnl`	Novice Learner and Expert Tutor: Evaluating Math Reasoning Abilities of Large Language Models with Misconceptions. CoRR Naiming Liu, Shashank Sonkar, Zichao Wang, Simon Woodhead, Richard G. Baraniuk
2022	J	`jnl`	A Visual Tour Of Current Challenges In Multimodal Language Models. CoRR Shashank Sonkar, Naiming Liu, Richard G. Baraniuk
2022	J	`jnl`	MANER: Mask Augmented Named Entity Recognition for Extreme Low-Resource Languages. CoRR Shashank Sonkar, Zichao Wang, Richard G. Baraniuk
2021	J	`jnl`	NePTuNe: Neural Powered Tucker Network for Knowledge Graph Completion. CoRR Shashank Sonkar, Arzoo Katiyar, Richard G. Baraniuk
2021	—	`conf`	NePTuNe: Neural Powered Tucker Networkfor Knowledge Graph Completion. IJCKG Shashank Sonkar, Arzoo Katiyar, Richard G. Baraniuk
2020	B	`conf`	Attention Word Embedding. COLING Shashank Sonkar, Andrew E. Waters, Richard G. Baraniuk
2020	J	`jnl`	Attention Word Embedding. CoRR Shashank Sonkar, Andrew E. Waters, Richard G. Baraniuk
2020	B	`conf`	qDKT: Question-centric Deep Knowledge Tracing. EDM Shashank Sonkar, Andrew S. Lan, Andrew E. Waters, Phillip Grimaldi, Richard G. Baraniuk
2020	J	`jnl`	qDKT: Question-centric Deep Knowledge Tracing. CoRR Shashank Sonkar, Andrew E. Waters, Andrew S. Lan, Phillip J. Grimaldi, Richard G. Baraniuk