Papers by Shanu Kumar
Multi Task Learning For Zero Shot Performance Prediction of Multilingual Models (2022.acl-long)
Copied to clipboard
| Challenge: | Massively Multilingual Transformer based Language Models have been shown to be effective on zero-shot transfer across languages, though performance varies from language to language depending on pivot language(s) used for fine-tuning. |
| Approach: | They propose to combine multi-task learning problems with multi-lingual Transformers to model zero-shot transfer across languages. |
| Outcome: | The proposed model can predict zero-shot transfer across languages with a multi-task learning problem with pretraining data in very few languages. |
”Diversity and Uncertainty in Moderation” are the Key to Data Selection for Multilingual Few-shot Transfer (2022.findings-naacl)
Copied to clipboard
| Challenge: | Existing approaches for few-shot transfer show significant gain over zero-shot transfers . language resource distribution is skewed across the world's languages . proposed methods use multiple measures such as data entropy and gradient embedding . |
| Approach: | They propose a loss embedding method for sequence labeling tasks that induces diversity and uncertainty sampling similar to gradient embeddment. |
| Outcome: | The proposed methods outperform baseline methods for POS tagging, NER, and NLI tasks for up to 20 languages. |
DiTTO: A Feature Representation Imitation Approach for Improving Cross-Lingual Transfer (2023.eacl-main)
Copied to clipboard
| Challenge: | Zero-shot cross-lingual transfer has been shown to be sub-optimal across low-resource languages due to the skew in resource distribution in languages. |
| Approach: | They propose to jointly reduce feature incongruity between the source and target language and increase generalization capabilities of pre-trained multilingual transformers. |
| Outcome: | Empirical results show that the proposed approach outperforms the standard zero-shot fine-tuning method on multiple datasets across all languages using only unlabeled instances in the target language. |
SCULPT: Systematic Tuning of Long Prompts (2025.acl-long)
Copied to clipboard
Shanu Kumar, Akhila Yesantarao Venkata, Shubhanshu Khandelwal, Bishal Santra, Parag Agrawal, Manish Gupta
| Challenge: | Existing methods for prompt optimization struggle with longer, more complex ones, often risking information loss and being sensitive to small perturbations. |
| Approach: | They propose a framework that treats prompt optimization as a hierarchical tree refinement problem and uses a Critic-Actor framework to generate reflections and apply actions to refine the prompt. |
| Outcome: | The proposed framework produces more stable and interpretable prompt modifications, ensuring better generalization across tasks. |
Navigating the Cultural Kaleidoscope: A Hitchhiker’s Guide to Sensitivity in Large Language Models (2025.naacl-long)
Copied to clipboard
Somnath Banerjee, Sayan Layek, Hari Shrawgi, Rajarshi Mandal, Avik Halder, Shanu Kumar, Sagnik Basu, Parag Agrawal, Rima Hazra, Animesh Mukherjee
| Challenge: | Cultural harm arises when LLMs misrepresent or normalize values, identities, and practices in ways that conflict with the norms of diverse cultural groups. |
| Approach: | They propose a cultural harm test dataset and a preference dataset to assess model outputs across different cultural contexts. |
| Outcome: | The proposed model improves model behavior significantly reducing the likelihood of generating culturally insensitive or harmful content. |
Enhancing Zero-shot Chain of Thought Prompting via Uncertainty-Guided Strategy Selection (2025.coling-main)
Copied to clipboard
Shanu Kumar, Saish Mendke, Karody Lubna Abdul Rahman, Santosh Kurasa, Parag Agrawal, Sandipan Dandapat
| Challenge: | Existing methods for chain-of-thought (CoT) prompting are limited by handcrafted demonstrations and trigger phrases are prone to inaccuracies. |
| Approach: | They propose a method that generates rationales using a trigger phrase to select effective demonstrations without accessing model parameters. |
| Outcome: | The proposed method outperforms existing methods across four reasoning benchmarks and is robust and scalable. |