6 papers
CRAFT: Cost-aware Refinement And Front-aware Tuning of Prompts
Shanu Kumar, Shubhanshu Khandelwal, Akhila Yesantarao Venkata +3
Prompts tuned for accuracy often grow long, raising inference cost on every model call. The best accuracy-cost trade-off depends on the task and the budget, so prompt optimization…
Towards Safer Pretraining: Analyzing and Filtering Harmful Content in Webscale datasets for Responsible LLMs
Sai Krishna Mendu, Harish Yenala, Aditi Gulati +2
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. W…
SCULPT: Systematic Tuning of Long Prompts
Shanu Kumar, Akhila Yesantarao Venkata, Shubhanshu Khandelwal +3
Prompt optimization is essential for effective utilization of large language models (LLMs) across diverse tasks. While existing optimization methods are effective in optimizing sho…
READ: Reinforcement-based Adversarial Learning for Text Classification with Limited Labeled Data
Rohit Sharma, Shanu Kumar, Avinash Kumar
Pre-trained transformer models such as BERT have shown massive gains across many text classification tasks. However, these models usually need enormous labeled data to achieve impr…
Socio-Culturally Aware Evaluation Framework for LLM-Based Content Moderation
Shanu Kumar, Gauri Kholkar, Saish Mendke +3
With the growth of social media and large language models, content moderation has become crucial. Many existing datasets lack adequate representation of different groups, resulting…
Enhancing Zero-shot Chain of Thought Prompting via Uncertainty-Guided Strategy Selection
Shanu Kumar, Saish Mendke, Karody Lubna Abdul Rahman +3
Chain-of-thought (CoT) prompting has significantly enhanced the capability of large language models (LLMs) by structuring their reasoning processes. However, existing methods face…