Papers by Kseniia Petukhova
A Fully Automated Pipeline for Conversational Discourse Annotation: Tree Scheme Generation and Labeling with Large Language Models (2025.findings-acl)
Copied to clipboard
| Challenge: | Recent advances in Large Language Models (LLMs) have shown promise in automating discourse annotation for conversations. |
| Approach: | They propose a pipeline that uses large language models to construct and perform annotations using speech functions and the Switchboard-DAMSL taxonomies. |
| Outcome: | The proposed pipeline outperforms existing tree annotation schemes and can match or surpass human annotations while significantly reducing time required for annotation. |
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. |
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. |