The Fools are Certain; the Wise are Doubtful: Exploring LLM Confidence in Code Completion

• URL: http://arxiv.org/abs/2508.16131v1
• Date: Fri, 22 Aug 2025 06:51:13 GMT
• Title: The Fools are Certain; the Wise are Doubtful: Exploring LLM Confidence in Code Completion
• Authors: Zoe Kotti, Konstantina Dritsa, Diomidis Spinellis, Panos Louridas,
• Abstract summary: We evaluate the confidence of Large Language Models (LLMs) when generating code by measuring code perplexity.<n>We find that strongly-typed languages exhibit lower perplexity than dynamically typed languages.<n> Perl appears universally high in perplexity, whereas Java appears low.
• Score: 4.215010577170175
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Code completion entails the task of providing missing tokens given a surrounding context. It can boost developer productivity while providing a powerful code discovery tool. Following the Large Language Model (LLM) wave, code completion has been approached with diverse LLMs fine-tuned on code (code LLMs). The performance of code LLMs can be assessed with downstream and intrinsic metrics. Downstream metrics are usually employed to evaluate the practical utility of a model, but can be unreliable and require complex calculations and domain-specific knowledge. In contrast, intrinsic metrics such as perplexity, entropy, and mutual information, which measure model confidence or uncertainty, are simple, versatile, and universal across LLMs and tasks, and can serve as proxies for functional correctness and hallucination risk in LLM-generated code. Motivated by this, we evaluate the confidence of LLMs when generating code by measuring code perplexity across programming languages, models, and datasets using various LLMs, and a sample of 1008 files from 657 GitHub projects. We find that strongly-typed languages exhibit lower perplexity than dynamically typed languages. Scripting languages also demonstrate higher perplexity. Perl appears universally high in perplexity, whereas Java appears low. Code perplexity depends on the employed LLM, but not on the code dataset. Although code comments often increase perplexity, the language ranking based on perplexity is barely affected by their presence. LLM researchers, developers, and users can employ our findings to assess the benefits and suitability of LLM-based code completion in specific software projects based on how language, model choice, and code characteristics impact model confidence.

Related papers

• IFEvalCode: Controlled Code Generation [69.28317223249358]
  The paper introduces forward and backward constraints generation to improve the instruction-following capabilities of Code LLMs.<n>The authors present IFEvalCode, a multilingual benchmark comprising 1.6K test samples across seven programming languages.
  arXiv  Detail & Related papers  (2025-07-30T08:08:48Z)
• On the Effectiveness of LLM-as-a-judge for Code Generation and Summarization [54.965787768076254]
  Large Language Models have been recently exploited as judges for complex natural language processing tasks, such as Q&A.<n>We study the effectiveness of LLMs-as-a-judge for two code-related tasks, namely code generation and code summarization.
  arXiv  Detail & Related papers  (2025-07-22T13:40:26Z)
• Can LLMs Replace Humans During Code Chunking? [2.4056836012742]
  Large language models (LLMs) have become essential tools in computer science, especially for tasks involving code understanding and generation.<n>This paper examines the application of LLMs in the modernization of legacy government code written in ALC and MUMPS.
  arXiv  Detail & Related papers  (2025-06-24T13:02:35Z)
• How Accurately Do Large Language Models Understand Code? [4.817546726074033]
  Large Language Models (LLMs) are increasingly used in post-development tasks such as code repair and testing.<n> Quantifying code comprehension is challenging due to its abstract nature and the lack of a standardized metric.<n>This paper presents the first large-scale empirical investigation into LLMs' ability to understand code.
  arXiv  Detail & Related papers  (2025-04-06T05:59:29Z)
• Crystal: Illuminating LLM Abilities on Language and Code [58.5467653736537]
  We propose a pretraining strategy to enhance the integration of natural language and coding capabilities. The resulting model, Crystal, demonstrates remarkable capabilities in both domains.
  arXiv  Detail & Related papers  (2024-11-06T10:28:46Z)
• Perplexed: Understanding When Large Language Models are Confused [3.4208414448496027]
  This paper introduces perplexed, a library for exploring where a language model is perplexed. We conducted a case study focused on Large Language Models (LLMs) for code generation using an additional tool we built to help with the analysis of code models called codetokenizer. We found that our studied code LLMs had their worst performance on coding structures where the code was not syntactically correct.
  arXiv  Detail & Related papers  (2024-04-09T22:03:39Z)
• InfiBench: Evaluating the Question-Answering Capabilities of Code Large Language Models [56.723509505549536]
  InfiBench is the first large-scale freeform question-answering (QA) benchmark for code to our knowledge. It comprises 234 carefully selected high-quality Stack Overflow questions that span across 15 programming languages. We conduct a systematic evaluation for over 100 latest code LLMs on InfiBench, leading to a series of novel and insightful findings.
  arXiv  Detail & Related papers  (2024-03-11T02:06:30Z)
• If LLM Is the Wizard, Then Code Is the Wand: A Survey on How Code Empowers Large Language Models to Serve as Intelligent Agents [81.60906807941188]
  Large language models (LLMs) are trained on a combination of natural language and formal language (code) Code translates high-level goals into executable steps, featuring standard syntax, logical consistency, abstraction, and modularity.
  arXiv  Detail & Related papers  (2024-01-01T16:51:20Z)
• ML-Bench: Evaluating Large Language Models and Agents for Machine Learning Tasks on Repository-Level Code [76.84199699772903]
  ML-Bench is a benchmark rooted in real-world programming applications that leverage existing code repositories to perform tasks. To evaluate both Large Language Models (LLMs) and AI agents, two setups are employed: ML-LLM-Bench for assessing LLMs' text-to-code conversion within a predefined deployment environment, and ML-Agent-Bench for testing autonomous agents in an end-to-end task execution within a Linux sandbox environment.
  arXiv  Detail & Related papers  (2023-11-16T12:03:21Z)
• CodeApex: A Bilingual Programming Evaluation Benchmark for Large Language Models [43.655927559990616]
  We propose CodeApex, a benchmark dataset focusing on the programming comprehension, code generation, and code correction abilities of LLMs. We evaluate 12 widely used LLMs, including both general-purpose and specialized models. GPT-4 exhibits the best programming capabilities, achieving approximate accuracy of 69%, 54%, and 66% on the three tasks, respectively.
  arXiv  Detail & Related papers  (2023-09-05T04:12:01Z)
• LEVER: Learning to Verify Language-to-Code Generation with Execution [64.36459105535]
  We propose LEVER, a simple approach to improve language-to-code generation by learning to verify the generated programs with their execution results. Specifically, we train verifiers to determine whether a program sampled from the LLMs is correct or not based on the natural language input, the program itself and its execution results. LEVER consistently improves over the base code LLMs(4.6% to 10.9% with code-davinci) and achieves new state-of-the-art results on all of them.
  arXiv  Detail & Related papers  (2023-02-16T18:23:22Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.