From misuse to mastery: Enhancing code generation with knowledge-driven ai chaining

X Ren, X Ye, D Zhao, Z **ng… - 2023 38th IEEE/ACM …, 2023 - ieeexplore.ieee.org
Large Language Models (LLMs) have shown promising results in automatic code
generation by improving coding efficiency to a certain extent. However, generating high …

An Investigation of Neuron Activation as a Unified Lens to Explain Chain-of-Thought Eliciting Arithmetic Reasoning of LLMs

D Rai, Z Yao - arxiv preprint arxiv:2406.12288, 2024 - arxiv.org
Large language models (LLMs) have shown strong arithmetic reasoning capabilities when
prompted with Chain-of-Thought (CoT) prompts. However, we have only a limited …

[PDF][PDF] IntelliExplain: Enhancing Interactive Code Generation through Natural Language Explanations for Non-Professional Programmers

H Yan, TD Latoza, Z Yao - arxiv preprint arxiv:2405.10250, 2024 - openreview.net
arxiv:2405.10250v1 [cs.HC] 16 May 2024 Page 1 IntelliExplain: Enhancing Interactive Code
Generation through Natural Language Explanations for Non-Professional Programmers Hao …

Can large language models understand uncommon meanings of common words?

J Wu, F Che, X Zheng, S Zhang, R **, S Nie… - arxiv preprint arxiv …, 2024 - arxiv.org
Large language models (LLMs) like ChatGPT have shown significant advancements across
diverse natural language understanding (NLU) tasks, including intelligent dialogue and …

Understanding the Effect of Algorithm Transparency of Model Explanations in Text-to-SQL Semantic Parsing

D Rai, RR Weiland, KMG Herrera, TH Shaw… - arxiv preprint arxiv …, 2024 - arxiv.org
Explaining the decisions of AI has become vital for fostering appropriate user trust in these
systems. This paper investigates explanations for a structured prediction task called``text-to …