Instruct, Not Assist: LLM-based Multi-Turn Planning and Hierarchical Questioning for Socratic Code Debugging (2024 · 16 citations)
LLM tutors tend to act like helpful assistants and simply hand students the fix. This undermines learning. The authors target programming education and propose TreeInstruct, an Instructor agent that teaches debugging through Socratic questioning without revealing the answer.
Language Specific Knowledge: Do Models Know Better in X than in English? (2025 · 1 citation)
Multilingual LLMs are usually assumed to encode meaning in a shared space regardless of input language. The authors show this assumption fails in practice. A model may answer the same question correctly in one language and wrongly in another. They call this Language Specific Knowledge (LSK) and define the Language…

All works

3 works of theirs in our library, the most cited first; 2 with a page here, the others link their original until we summarise them.

Instruct, Not Assist: LLM-based Multi-Turn Planning and Hierarchical Questioning for Socratic Code DebuggingFindings of the Association for Computational LinguisticsPriyanka Kargupta, Ishika Agarwal, Dilek Hakkani Tur, et al.2024 · 16 citations
Language Specific Knowledge: Do Models Know Better in X than in English?arXiv:2505.14990Ishika Agarwal, Nimet Beyza Bozdag, Dilek Hakkani-Tur2025 · 1 citation
A Rising Tide Lifts All Boats: MTQE Rewards for Idioms Improve General Translation Quality ↗arXiv:2601.06307 · no summary yetIshika Agarwal et al.2026

Co-authors here

4 co-authors with a page, the most papers together first.

Where their works here were published, the most works first, with the editions of those that have a page.

Papers of our library cite their works 9 times (of the 149,439 papers whose bibliographies we read); 2 citing papers with a page here →.

Updated 3 November 2026