Author

Dipto Sumit

h-index 1 View on Semantic Scholar

We have 2 of 5 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Jul 2026

When Does Knowledge Distillation Hurt? Reliability-Aware Distillation for Low-Resource Language Summarization

The stronger method is evaluated across 15 typologically diverse XL-Sum languages organised into three sets, beating the CE-only baseline on 10/15 languages; gains are most reliable where the two teachers contribute complementary signal, and weakest where they have saturated or jointly weak target-language coverage.

Dipto Sumit, Ankan Kumar Roy Srizon, Sadia Khair Rodela et al. · arXiv.org · 0 citations

#natural language process... Preprint Aug 2026

Below the Noise Floor: Bimodal Seed Collapse and Distinct Failure Modes in Small-Model Knowledge Distillation

On a 740-instance healthcare API routing task with a 1.5B Qwen student and a 20B teacher, eight KD variants are compared against supervised cross-entropy, finding single-seed evaluation is unable to detect central failure modes in small-model KD.

Dipto Sumit, Sakib Ul Haque, Farig Sadeque · 0 citations