most citedNovice Learner and Expert Tutor: Evaluating Math Reasoning Abilities of Large Language Models with Misconceptions

2 citations · 5 across the 6 of their papers we have counts for

collaborators

6 papers

cs.CL20241 cited

Automated Long Answer Grading with RiceChem Dataset

Shashank Sonkar, Kangqi Ni, Lesa Tran Lu +3

We introduce a new area of study in the field of educational Natural Language Processing: Automated Long Answer Grading (ALAG). Distinguishing itself from Automated Short Answer Gr…

cs.CL2024

Marking: Visual Grading with Highlighting Errors and Annotating Missing Bits

Shashank Sonkar, Naiming Liu, Debshila B. Mallick +1

In this paper, we introduce "Marking", a novel grading task that enhances automated grading systems by performing an in-depth analysis of student responses and providing students w…

cs.CL2023

Code Soliloquies for Accurate Calculations in Large Language Models

Shashank Sonkar, MyCo Le, Xinghe Chen +3

High-quality conversational datasets are crucial for the successful development of Intelligent Tutoring Systems (ITS) that utilize a Large Language Model (LLM) backend. Synthetic s…

cs.CL20232 cited

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

Naiming Liu, Shashank Sonkar, Zichao Wang +2

We propose novel evaluations for mathematical reasoning capabilities of Large Language Models (LLMs) based on mathematical misconceptions. Our primary approach is to simulate LLMs…

cs.CL20231 cited

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

Shashank Sonkar, Richard G. Baraniuk

This paper investigates the key role of Feed-Forward Networks (FFNs) in transformer models by utilizing the Parallel Attention and Feed-Forward Net Design (PAF) architecture, and c…

cs.CL20231 cited

Deduction under Perturbed Evidence: Probing Student Simulation Capabilities of Large Language Models

Shashank Sonkar, Richard G. Baraniuk

We explore whether Large Language Models (LLMs) are capable of logical reasoning with distorted facts, which we call Deduction under Perturbed Evidence (DUPE). DUPE presents a uniq…