Reinforcement learning from human feedback (RLHF) has become a pivot technique in
aligning large language models (LLMs) with human preferences. In RLHF practice …

Finetuning large language models (LLMs) on instructions leads to vast performance
improvements on natural language tasks. We apply instruction tuning using code …

Large language models (LLMs) have demonstrated significant potential in the realm of
natural language understanding and programming code processing tasks. Their capacity to …

Recent LLMs have demonstrated remarkable performance in solving exam-like math word
problems. However, the degree to which these numerical reasoning skills are effective in …

We introduce KnowledgeFMath, a novel benchmark designed to evaluate LLMs' capabilities
in solving knowledge-intensive math reasoning problems. Compared to prior works, this …

Code LLMs are being rapidly deployed and there is evidence that they can make
professional programmers more productive. Current benchmarks for code generation …

Code cloning, the duplication of code fragments, is common in software development. While
some reuse aids productivity, excessive cloning hurts maintainability and introduces bugs …

Recent LLMs have demonstrated remarkable performance in solving exam-like math word
problems. However, the degree to which these numerical reasoning skills are effective in …

Code editing is an essential step towards reliable program synthesis to automatically correct
critical errors generated from code LLMs. Recent studies have demonstrated that closed …

Tabular data analysis is crucial in various fields, and large language models show promise
in this area. However, current research mostly focuses on rudimentary tasks like Text2SQL …