paper-with-me

Papers

Showing LLM-Generated Code Selectively Based on Confidence of LLMs

2024-10-04 · Jia Li, Yuqi Zhu, Yongmin Li, Ge Li, Zhi Jin

Large Language Models (LLMs) have shown impressive abilities in code generation, but they may generate erroneous programs. Reading a program takes ten times longer than writing it. Showing these erroneous programs to developers will waste developers' energies and introduce security risks to software. To address the above limitations, we propose HonestCoder, a novel LLM-based code generation approach. HonestCoder selectively shows the generated programs to developers based on LLMs' confidence. The confidence provides valuable insights into the correctness of generated programs. To achieve this goal, we propose a novel approach to estimate LLMs' confidence in code generation. It estimates confidence by measuring the multi-modal similarity between LLMs-generated programs. We collect and release a multilingual benchmark named TruthCodeBench, which consists of 2,265 samples and covers two popular programming languages (i.e., Python and Java). We apply HonestCoder to four popular LLMs (e.g., DeepSeek-Coder and Code Llama) and evaluate it on TruthCodeBench. Based on the experiments, we obtain the following insights. (1) HonestCoder can effectively estimate LLMs' confidence and accurately determine the correctness of generated programs. For example, HonestCoder outperforms the state-of-the-art baseline by 27.79% in AUROC and 63.74% in AUCPR. (2) HonestCoder can decrease the number of erroneous programs shown to developers. Compared to eight baselines, it can show more correct programs and fewer erroneous programs to developers. (3) Compared to showing code indiscriminately, HonestCoder only adds slight time overhead (approximately 0.4 seconds per requirement). (4) We discuss future directions to facilitate the application of LLMs in software development. We hope this work can motivate broad discussions about measuring the reliability of LLMs' outputs in performing code-related tasks.

📄 PDF Abstract BibTeX arXiv:2410.03234

Code (0)

등록된 구현이 없습니다.

Tasks

Code Generation

Similar Papers 제목 키워드 기반

Large Language Models Should Ask Clarifying Questions to Increase Confidence in Generated Code

2023-08-25 · Jie JW Wu

Large language models (LLMs) have significantly improved the ability to perform tasks in the field of code generation. However, there is still a gap between LLMs being capable coders and being top-tier software engineers…

Code Generation

POOL: Propagated Uncertainty Over Lookalikes

2026-08-24 · Rounak Sharma, Ananya B. Sai, Soumyabrata Pal arxiv

Black-box large language models need confidence scores that can separate likely-correct from likely-incorrect outputs, enabling systems to prioritize human review, route uncertain cases to stronger models, or choose abst…

Verifying LLM-Generated Code in the Context of Software Verification with Ada/SPARK

2025-02-11 · Marcos Cramer, Lucian McIntyre

Large language models (LLMs) have demonstrated remarkable code generation capabilities, but the correctness of the generated code cannot be inherently trusted. This paper explores the feasibility of using formal software…

Code Generation

CER: Confidence Enhanced Reasoning in LLMs

2025-02-20 · Ali Razghandi, Seyed Mohammad Hadi Hosseini, Mahdieh Soleymani Baghshah

Ensuring the reliability of Large Language Models (LLMs) in complex reasoning tasks remains a formidable challenge, particularly in scenarios that demand precise mathematical calculations and knowledge-intensive open-dom…

MathMathematical Reasoning

Can Confidence Estimates Decide When Chain-of-Thought Is Necessary for LLMs?

2025-10-23 · Samuel Lewis-Lim, Xingwei Tan, Zhixue Zhao, Nikolaos Aletras arxiv

Chain-of-thought (CoT) prompting is a common technique for improving the reasoning abilities of large language models (LLMs). However, extended reasoning is often unnecessary and substantially increases token usage. As s…