ConceptualGrader: Interactive Provenance and Eligibility Techniques for Auditing Large Language Models in Grading

Under review. A human-AI interaction system for auditing LLM grading of conceptual answers.

Authors: Iman YeckehZaare · Venue/status: UIST

This working manuscript presents grouped eligibility authoring, sentence-linked evidence highlighting, and override workflows for auditing LLM grading decisions.

Public artifact boundary: this route exposes status, authorship, visual summary, citation metadata, and the contribution boundary; manuscript files are posted only when review and prepublication rules allow it.

The rendered manuscript page adds status, visual summary, review boundary, citation metadata, and contribution notes. Key links: home, systems, papers, manuscripts, Google Scholar, GitHub, LinkedIn, ORCID, MIT profile, and CV PDF.