← Search

Niraj Kumar

2 accepted papers

2025

A Unified Framework for Provably Efficient Algorithms to Estimate Shapley Values

NeurIPS 2025poster

Shapley values have emerged as a critical tool for explaining which features impact the decisions made by machine learning models. However, computing exact Shapley values is difficult, generally requiring an exponential (in the feature dimension) number of model evaluations. To address this, many mo…

Cited by 0SourceScholar
2025

HG-InsightLog: Context Prioritization and Reduction for Question Answering with Non-Natural Language Construct Log Data

ACL 2025finding

Modern IT systems generate vast amounts of log data, which pose challenges for Large Language Models (LLMs) due to their large size, irrelevant entries, and non-Natural Language (non-NL) construct (e.g., domain-specific jargon, error codes, file paths, and abbreviations). Traditional methods like Re…

Cited by 0SourcePDFScholar