PPaperPicks

Yara Rizk

5 papers at tracked venues · 1 at CORE A* · active 20242026

Venues

Frequent coauthors

Papers

  1. How Good Are LLMs at Processing Tool Outputs?
  2. NESTFUL: A Benchmark for Evaluating LLMs on Nested Sequences of API Calls
  3. Towards LLMs Robustness to Changes in Prompt Format Styles
  4. Granite-Function Calling Model: Introducing Function Calling Abilities via Multi-task Learning of Granular Tasks
  5. Who Knows the Answer? Finding the Best Model and Prompt for Each Query Using Confidence-Based Search