Ishika Agarwal

13 papers A* 2Journal 7Unranked 4
YearRankTypeTitle / Venue / Authors
2026 J jnl
A Rising Tide Lifts All Boats: MTQE Rewards for Idioms Improve General Translation Quality.
CoRR
Ishika Agarwal, Zhenlin He, Dhruva Patil, Dilek Hakkani-Tür
2025 A* conf
DELIFT: Data Efficient Language model Instruction Fine-Tuning.
ICLR
Ishika Agarwal, Krishnateja Killamsetty, Lucian Popa, Marina Danilevsky
2025 J jnl
Data Valuation using Neural Networks for Efficient Instruction Fine-Tuning.
CoRR
Ishika Agarwal, Dilek Hakkani-Tür
2025 J jnl
Language Specific Knowledge: Do Models Know Better in X than in English?
CoRR
Ishika Agarwal, Nimet Beyza Bozdag, Dilek Hakkani-Tür
2025 — conf
Tree-of-Debate: Multi-Persona Debate Trees Elicit Critical Thinking for Scientific Comparative Analysis.
ACL (1)
Priyanka Kargupta, Ishika Agarwal, Tal August, Jiawei Han
2025 J jnl
Tree-of-Debate: Multi-Persona Debate Trees Elicit Critical Thinking for Scientific Comparative Analysis.
CoRR
Priyanka Kargupta, Ishika Agarwal, Tal August, Jiawei Han
2024 J jnl
DELIFT: Data Efficient Language model Instruction Fine Tuning.
CoRR
Ishika Agarwal, Krishnateja Killamsetty, Lucian Popa, Marina Danilevksy
2024 — conf
Instruct, Not Assist: LLM-based Multi-Turn Planning and Hierarchical Questioning for Socratic Code Debugging.
EMNLP (Findings)
Priyanka Kargupta, Ishika Agarwal, Dilek Hakkani-Tür, Jiawei Han
2024 J jnl
Instruct, Not Assist: LLM-based Multi-Turn Planning and Hierarchical Questioning for Socratic Code Debugging.
CoRR
Priyanka Kargupta, Ishika Agarwal, Dilek Hakkani-Tur, Jiawei Han
2024 A* conf
Neural Active Learning Beyond Bandits.
ICLR
Yikun Ban, Ishika Agarwal, Ziwei Wu, Yada Zhu, Kommy Weldemariam, Hanghang Tong, Jingrui He
2024 J jnl
Neural Active Learning Beyond Bandits.
CoRR
Yikun Ban, Ishika Agarwal, Ziwei Wu, Yada Zhu, Kommy Weldemariam, Hanghang Tong, Jingrui He
2023 — conf
QuickAns: A Virtual Teaching Assisstant.
AIMLSystems
Ishika Agarwal, Shradha Sehgal, Varun Goyal, Prathamesh Sonawane
2022 — conf
HiSaRL: A Hierarchical Framework for Safe Reinforcement Learning.
SafeAI@AAAI
Zikang Xiong, Ishika Agarwal, Suresh Jagannathan