Papers by Vishal Sharma
Adaptive LLM Routing under Budget Constraints (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) have revolutionized natural language processing, but their varying capabilities and costs pose challenges in practical applications. |
| Approach: | They propose to use LLM routing as a contextual bandit problem to enable adaptive decision-making . they use offline human preference data to refine the embeddings through online bandit feedback . |
| Outcome: | The proposed model is based on a contextual bandit problem enabling adaptive decision-making . it learns from offline human preference data and refines it through online bandit feedback. |
Search Query Spell Correction with Weak Supervision in E-commerce (2023.acl-industry)
Copied to clipboard
| Challenge: | Misspelled search queries can lead to empty or irrelevant products . only 29% of the population in india is proficient in english . |
| Approach: | They propose to group spell errors into error classes and then leverage a Transformer model for contextual spell correction. |
| Outcome: | The proposed model improves on tough spell mistakes without human intervention without human input. |