@inproceedings{ravikiran-etal-2025-indra,
    title = "{INDRA}: Iterative Difficulty Refinement Attention for {MCQ} Difficulty Estimation for {I}ndic Languages",
    author = "Ravikiran, Manikandan  and
      Saluja, Rohit  and
      Bhavsar, Arnav",
    editor = "Bhattacharya, Arnab  and
      Goyal, Pawan  and
      Ghosh, Saptarshi  and
      Ghosh, Kripabandhu",
    booktitle = "Proceedings of the 1st Workshop on Benchmarks, Harmonization, Annotation, and Standardization for Human-Centric AI in Indian Languages (BHASHA 2025)",
    month = dec,
    year = "2025",
    address = "Mumbai, India",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-ijcnlp-aacl/2025.bhasha-1.4/",
    pages = "37--51",
    ISBN = "979-8-89176-313-5",
    abstract = "Estimating the difficulty of multiple-choice questions (MCQs) is central to adaptive testing and learner modeling. We introduce \textbf{INDRA} (Iterative Difficulty Refinement Attention), a novel attention mechanism that unifies psychometric priors with neural refinement for Indic MCQ difficulty estimation. INDRA incorporates three key innovations: (i) \textit{IRT-informed initialization}, which assigns token-level discrimination and difficulty scores to embed psychometric interpretability; (ii) \textit{entropy-driven iterative refinement}, which progressively sharpens attention to mimic the human process of distractor elimination; and (iii) \textit{Indic Aware Graph Coupling}, which propagates plausibility across morphologically and semantically related tokens, a critical feature for Indic languages. Experiments on TEEMIL-H and TEEMIL-K datasets show that INDRA achieves consistent improvements, with absolute gains of up to +1.02 F1 and +1.68 F1 over state-of-the-art, while demonstrating through ablation studies that psychometric priors, entropy refinement, and graph coupling contribute complementary gains to accuracy and robustness."
}