Published in (soon to appear) WASSA @ EACL 2026, 2026
We propose an agentic data augmentation method for Aspect-Based Sentiment Analysis (ABSA) that uses iterative generation and verification to produce high-quality synthetic training examples.
Published in Findings of ACL, 2025
Through a simple integration of hyperbolic representations with an encoder-decoder model, we perform a controlled and comprehensive set of experiments to compare the capacity of hyperbolic space versus Euclidean space in multi-hop reasoning.
Published in LLMSEC Workshop @ ACL, 2025
We propose ArithmAttack to examine how robust the LLMs are when they encounter noisy prompts that contain extra noise in the form of punctuation marks.
Published in C3NLP Workshop @ ACL, 2024
We investigate the effect of multilingual training on bias mitigation by systematically training six LLMs of identical size (2.6B parameters) and architecture: five monolingual models (English, German, French, Italian, and Spanish) and one multilingual model trained on an equal distribution of data across these languages, all using publicly available data.
Published in Findings of EMNLP, 2021
This paper proposes AEDA (An Easier Data Augmentation) technique to help improve the performance on text classification tasks.
Published in ICPR, 2020
We propose a novel architecture called BERT Adversarial Training (BAT) to utilize adversarial training for the two major tasks of Aspect Extraction and Aspect Sentiment Classification in sentiment analysis.