Papers by Charles Clarke
Fréchet Distance for Offline Evaluation of Information Retrieval Systems with Sparse Labels (2024.eacl-long)
Copied to clipboard
| Challenge: | Obtaining high-quality labeled data that accurately represents complexity of real-world scenarios can be expensive, time-consuming, or even impractical. |
| Approach: | They propose to use Fréchet Inception Distance to measure distance between judged items and retrieved results. |
| Outcome: | The proposed method improves on a MS MARCO dataset and TREC Deep Learning Tracks query sets. |
Assessing and Verifying Task Utility in LLM-Powered Applications (2024.emnlp-main)
Copied to clipboard
Negar Arabzadeh, Siqing Huo, Nikhil Mehta, Qingyun Wu, Chi Wang, Ahmed Awadallah, Charles Clarke, Julia Kiseleva
| Challenge: | Rapid development of Large Language Models (LLMs) has led to a surge in applications that facilitate collaboration among multiple agents, assisting humans in their daily tasks. |
| Approach: | They propose a framework to propose criteria tailored to the unique purpose of any given application and propose corresponding criteria for the application. |
| Outcome: | The proposed framework provides a comprehensive assessment of the effectiveness and robustness of two open source datasets including Math Problem solving and ALFWorld House-hold related tasks. |
Evaluating Open-Domain Question Answering in the Era of Large Language Models (2023.acl-long)
Copied to clipboard
| Challenge: | Existing evaluation models fail to identify lexical matching failures for open-domain question answering. |
| Approach: | They manually evaluate open-domain QA models by manually evaluating their answers on a popular benchmark. |
| Outcome: | The proposed model performs better on NQ-open than existing models and more than 50% of lexical matching failures are attributed to semantically equivalent answers. |