AIConfPaper
← Search

Shanu Kumar

8 accepted papers

2025

Enhancing Zero-shot Chain of Thought Prompting via Uncertainty-Guided Strategy Selection

Shanu Kumar, Saish Mendke, Karody Lubna Abdul Rahman, Santosh Kurasa, Parag Agrawal, Sandipan Dandapat
COLING 2025main

Chain-of-thought (CoT) prompting has significantly enhanced the the capability of large language models (LLMs) by structuring their reasoning processes. However, existing methods face critical limitations: handcrafted demonstrations require extensive human expertise, while trigger phrases are prone…

Cited by 0Source ↗PDF ↗Scholar ↗
2025

Navigating the Cultural Kaleidoscope: A Hitchhiker’s Guide to Sensitivity in Large Language Models

Somnath Banerjee, Sayan Layek, Hari Shrawgi, Rajarshi Mandal, Avik Halder, Shanu Kumar +4
NAACL 2025long

Cultural harm stems in LLMs whereby these models fail to align with specific cultural norms, resulting in misrepresentations or violations of cultural values. This work addresses the challenges of ensuring cultural sensitivity in LLMs, especially in small-parameter models that often lack the extensi…

Cited by 3Source ↗PDF ↗code ↗Scholar ↗
2025

SCULPT: Systematic Tuning of Long Prompts

Shanu Kumar, Akhila Yesantarao Venkata, Shubhanshu Khandelwal, Bishal Santra, Parag Agrawal, Manish Gupta
ACL 2025long

Prompt optimization is essential for effective utilization of large language models (LLMs) across diverse tasks. While existing optimization methods are effective in optimizing short prompts, they struggle with longer, more complex ones, often risking information loss and being sensitive to small pe…

Cited by 0Source ↗PDF ↗Scholar ↗
2025

SafeInfer: Context Adaptive Decoding Time Safety Alignment for Large Language Models

Somnath Banerjee, Sayan Layek, Soham Tripathy, Shanu Kumar, Animesh Mukherjee, Rima Hazra
AAAI 2025technical

Language models aligned for safety often exhibit fragile and imbalanced mechanisms, increasing the chances of producing unsafe content. In addition, editing techniques to incorporate new knowledge can further compromise safety. To tackle these issues, we propose SafeInfer, a context-adaptive, decodi…

Cited by 7Source ↗PDF ↗code ↗Scholar ↗
2025

Towards Safer Pretraining: Analyzing and Filtering Harmful Content in Webscale Datasets for Responsible LLMs

Sai Krishna Mendu, Harish Yenala, Aditi Gulati, Shanu Kumar, Parag Agrawal
IJCAI 2025

Large language models (LLMs) have become integral to various real-world applications, leveraging massive, web-sourced datasets like Common Crawl, C4, and FineWeb for pretraining. While these datasets provide linguistic data essential for high-quality natural language generation, they often contain h

Cited by 0Source ↗PDF ↗code ↗Scholar ↗
2022

Multi Task Learning For Zero Shot Performance Prediction of Multilingual Models

Kabir Ahuja, Shanu Kumar, Sandipan Dandapat, Monojit Choudhury
ACL 2022long

Massively Multilingual Transformer based Language Models have been observed to be surprisingly effective on zero-shot transfer across languages, though the performance varies from language to language depending on the pivot language(s) used for fine-tuning. In this work, we build upon some of the ex…

Cited by 22Source ↗PDF ↗code ↗Scholar ↗
2022

”Diversity and Uncertainty in Moderation” are the Key to Data Selection for Multilingual Few-shot Transfer

Shanu Kumar, Sandipan Dandapat, Monojit Choudhury
NAACL 2022findings

Few-shot transfer often shows substantial gain over zero-shot transfer (CITATION), which is a practically useful trade-off between fully supervised and unsupervised learning approaches for multilingual pretained model-based systems. This paper explores various strategies for selecting data for annot…

Cited by 6Source ↗PDF ↗Scholar ↗