Papers by Pragya Srivastava

2 papers
Evaluating LLMs’ Mathematical Reasoning in Financial Document Question Answering (2024.findings-acl)

Copied to clipboard

Challenge: Large Language Models excel in natural language understanding, but their capability for complex mathematical reasoning with a hybrid of structured tables and unstructured text remain uncertain.
Approach: They propose a prompting technique tailored to semi-structured documents that matches or outperforms baselines performance while providing a nuanced understanding of LLMs' abilities.
Outcome: The proposed prompting technique outperforms baseline prompting techniques while providing a nuanced understanding of LLMs' abilities.
NICE: To Optimize In-Context Examples or Not? (2024.acl-long)

Copied to clipboard

Challenge: Recent work shows that in-context learning and optimization of in-const examples (ICE) can improve the accuracy of large language models on a wide range of tasks.
Approach: They propose a task-specific metric called Normalized Invariability to Choice of Examples (NICE) metric measures the learnability of tasks from a given instruction and provides a heuristic to decide whether to optimize ICE for a new task.
Outcome: The proposed metric predicts the utility of optimizing ICE for a given task compared to random ICE.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations