Papers by Kaushal Kumar Maurya
LLMs cannot spot math errors, even when allowed to peek into the solution (2025.emnlp-main)
Copied to clipboard
| Challenge: | Large language models (LLMs) demonstrate impressive performance on existing reasoning benchmarks, but struggle with meta-reasoning tasks such as locating the first error step in student solutions. |
| Approach: | They propose an approach that generates an intermediate corrected student solution, aligning more closely with the original student’s solution, which helps improve performance. |
| Outcome: | The proposed approach generates an intermediate corrected student solution, aligning more closely with the original student’s solution, which helps improve performance. |
SelectLLM: Query-Aware Efficient Selection Algorithm for Large Language Models (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing large language models struggle with complex tasks such as factually-grounded reasoning and planning due to inherent training biases, model size constraints, and the quality or diversity of pre-training datasets. |
| Approach: | They propose a novel algorithm to select the most suitable LLMs from a large pool and use it to efficiently generalize and perform tasks. |
| Outcome: | The proposed model outperforms existing ensemble-based baselines and achieves competitive performance with similarly sized top-performing LLMs while maintaining efficiency. |
AITutor-EvalKit: Exploring the Capabilities of AI Tutors (2026.eacl-demo)
Copied to clipboard
| Challenge: | Personalized one-on-one tutoring is an effective educational approach, yet its widespread adoption is constrained by the limited availability of qualified tutors and the high costs associated with tutor training. |
| Approach: | They propose an evaluation tool that uses language technology to evaluate the pedagogical quality of AI tutors. |
| Outcome: | The proposed evaluation tool is aimed at education stakeholders as well as the *ACL community at large, as it supports learning and can also collect user feedback and annotation. |
ZmBART: An Unsupervised Cross-lingual Transfer Framework for Language Generation (2021.findings-acl)
Copied to clipboard
| Challenge: | Recent advances in NLP focus on large annotated training data. |
| Approach: | They propose an unsupervised framework that does not use parallel or pseudo-parallel/back-translated data. |
| Outcome: | The proposed framework does not use parallel or pseudo-parallel/back-translated data. |
Unifying AI Tutor Evaluation: An Evaluation Taxonomy for Pedagogical Ability Assessment of LLM-Powered AI Tutors (2025.naacl-long)
Copied to clipboard
| Challenge: | Existing evaluations of large language models have been limited to subjective protocols and benchmarks. |
| Approach: | They propose a unified evaluation taxonomy with eight pedagogical dimensions based on key learning sciences principles to assess the pedagical value of LLM-powered AI tutor responses grounded in student mistakes or confusions in the mathematical domain. |
| Outcome: | The proposed taxonomy, benchmark, and human-annotated labels will streamline the evaluation process and help track the progress in AI tutors’ development. |