Mhpp: Exploring the capabilities and limitations of language models beyond basic code generation
Recent advancements in large language models (LLMs) have greatly improved code
generation, specifically at the function level. For instance, GPT-4o has achieved a 91.0 …
generation, specifically at the function level. For instance, GPT-4o has achieved a 91.0 …
Autopsv: Automated process-supervised verifier
In this work, we propose a novel method named\textbf {Auto} mated\textbf {P} rocess-\textbf
{S} upervised\textbf {V} erifier (\textbf {\textsc {AutoPSV}}) to enhance the reasoning …
{S} upervised\textbf {V} erifier (\textbf {\textsc {AutoPSV}}) to enhance the reasoning …
ACECode: A Reinforcement Learning Framework for Aligning Code Efficiency and Correctness in Code Language Models
CodeLLMs have demonstrated remarkable advancements in software engineering tasks.
However, while these models can generate functionally correct code, they often produce …
However, while these models can generate functionally correct code, they often produce …
Learning From Correctness Without Prompting Makes LLM Efficient Reasoner
Large language models (LLMs) have demonstrated outstanding performance across various
tasks, yet they still exhibit limitations such as hallucination, unfaithful reasoning, and toxic …
tasks, yet they still exhibit limitations such as hallucination, unfaithful reasoning, and toxic …