Publications

Dheeraj Mekala, Jason Weston, Jack Lanchantin, Roberta Raileanu, Maria Lomeli, Jingbo Shang, Jane Dwivedi-Yu (2024). TOOLVERIFIER: Generalization to New Tools via Self-Verification. Arxiv.

Dheeraj Mekala, Alex Nguyen, Jingbo Shang (2024). Smaller Language Models are capable of selecting Instruction-Tuning Training Data for Larger Language Models. Arxiv.

Yasaman Jafari, Dheeraj Mekala, Rose Yu, Taylor Berg-Kirkpatrick (2024). MORL-Prompt: An Empirical Analysis of Multi-Objective Reinforcement Learning for Discrete Prompt Optimization. Arxiv.

Dheeraj Mekala, Adithya Samavedhi, Chengyu Dong, Jingbo Shang (2023). SELFOOD: Self-Supervised Out-Of-Distribution Detection via Learning to Rank. EMNLP Findings 2023.

Dheeraj Mekala, Jason Wolfe, Subhro Roy (2022). ZEROTOP: Zero-Shot Task-Oriented Semantic Parsing using Large Language Models. EMNLP 2023.

Dheeraj Mekala, Chengyu Dong, Jingbo Shang (2022). LOPS: Learning Order Inspired Pseudo-Label Selection for Weakly Supervised Text Classification. EMNLP Findings 2022.

Dheeraj Mekala, Tu Vu, Timo Schick, Jingbo Shang (2022). Leveraging QA Datasets to Improve Generative Data Augmentation. EMNLP 2022.

Sudhanshu Ranjan, Dheeraj Mekala, Jingbo Shang (2022). Progressive Sentiment Analysis for Code-Switched Text Data. EMNLP Findings 2022.

Dheeraj Mekala, Varun Gangal, Jingbo Shang (2021). Coarse2Fine: Fine-grained Text Classification on Coarsely-grained Annotated Data. EMNLP 2021.

Zichao Li, Dheeraj Mekala, Chengyu Dong, Jingbo Shang (2021). BFClass: A Backdoor-free Text Classification Framework. EMNLP Findings 2021.

Zihan Wang, Dheeraj Mekala, Jingbo Shang (2021). X-Class: Text Classification with Extremely Weak Supervision. NAACL 2021.

Dheeraj Mekala, Xinyang Zhang, Jingbo Shang (2020). META: Metadata-Empowered Weak Supervision for Text Classification. EMNLP 2020.

Dheeraj Mekala, Jingbo Shang (2020). Contextualized Weak Supervision for Text Classification. ACL 2020.

Rahul Wadbude, Vivek Gupta, Dheeraj Mekala, Harish Karnick (2018). User Bias Removal in Review Score Prediction. CODS-COMAD 2018.

Dheeraj Mekala, Vivek Gupta, Bhargavi Paranjape, Harish Karnick (2017). SCDV : Sparse Composite Document Vectors using soft clustering over distributional representations. EMNLP 2017.

PDF Code Slides Video

Dheeraj Mekala, Vivek Gupta, Purushottam Kar, Harish Karnick (2017). Bayes-optimal Hierarchical Classification over Asymmetric Tree-Distance Loss. Preprint.