1 citations · 3 across the 9 of their papers we have counts for
9 papers
LLMs Get Smarter from Targeted Synthetic Multilingual Data
Ishika Agarwal, Arkajyoti Charaborty, Tanner Sorensen +2
Language-specific competency (LSC) is the phenomenon of a language model performing better or worse depending on the language of the prompt. In other words, a language model output…
AcquisitionSynthesis: Targeted Data Generation using Acquisition Functions
Ishika Agarwal, Sofia Stoica, Emre Can Acikgoz +4
Data quality remains a critical bottleneck in developing capable, competitive models. Researchers have explored many ways to generate top quality samples. Some works rely on reject…
A Rising Tide Lifts All Boats: MTQE Rewards for Idioms Improve General Translation Quality
Ishika Agarwal, Zhenlin He, Dhruva Patil +1
Non-compositional expressions (e.g., idioms, proverbs, and metaphors) pose significant challenges for neural machine translation systems because their meanings cannot be derived fr…
Language Specific Knowledge: Do Models Know Better in X than in English?
Ishika Agarwal, Nimet Beyza Bozdag, Nisval Patel +1
Often, multilingual language models are trained with the objective to map semantically similar content (in different languages) in the same latent space. In this paper, we show a n…
Tree-of-Debate: Multi-Persona Debate Trees Elicit Critical Thinking for Scientific Comparative Analysis
Priyanka Kargupta, Ishika Agarwal, Tal August +1
With the exponential growth of research facilitated by modern technology and improved accessibility, scientific discoveries have become increasingly fragmented within and across fi…
Neural Networks for Learnable and Scalable Influence Estimation of Instruction Fine-Tuning Data
Ishika Agarwal, Dilek Hakkani-Tür
Influence functions provide crucial insights into model training, but existing methods suffer from large computational costs and limited generalization. Particularly, recent works…
DELIFT: Data Efficient Language model Instruction Fine Tuning
Ishika Agarwal, Krishnateja Killamsetty, Lucian Popa +1
Fine-tuning large language models (LLMs) is essential for enhancing their performance on specific tasks but is often resource-intensive due to redundant or uninformative data. To a…
Instruct, Not Assist: LLM-based Multi-Turn Planning and Hierarchical Questioning for Socratic Code Debugging
Priyanka Kargupta, Ishika Agarwal, Dilek Hakkani-Tur +1
Socratic questioning is an effective teaching strategy, encouraging critical thinking and problem-solving. The conversational capabilities of large language models (LLMs) show grea…
Neural Active Learning Beyond Bandits
Yikun Ban, Ishika Agarwal, Ziwei Wu +4
We study both stream-based and pool-based active learning with neural network approximations. A recent line of works proposed bandit-based approaches that transformed active learni…