Multicalibration for LLM-based Code Generation

• URL: http://arxiv.org/abs/2512.08810v1
• Date: Tue, 09 Dec 2025 17:04:01 GMT
• Title: Multicalibration for LLM-based Code Generation
• Authors: Viola Campos, Robin Kuschnereit, Adrian Ulges,
• Abstract summary: Multicalibration can yield distinct improvements over both uncalibrated token likelihoods and baseline calibrations.<n>We make our dataset (consisting of code generations, likelihoods, and correctness labels) available for future research on code LLM calibration.
• Score: 0.3568466510804538
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: As AI-based code generation becomes widespread, researchers are investigating the calibration of code LLMs - ensuring their confidence scores faithfully represent the true likelihood of code correctness. To do so, we investigate multicalibration, which can capture additional factors about a coding problem, such as complexity, code length, or programming language used. We study four multicalibration approaches on three function synthesis benchmarks, using latest-generation code LLMs (Qwen3 Coder, GPT-OSS, DeepSeek-R1-Distill). Our results demonstrate that multicalibration can yield distinct improvements over both uncalibrated token likelihoods (+1.03 in skill score) and baseline calibrations (+0.37 in skill score). We study the influence of the aforementioned factors in ablations, and make our dataset (consisting of code generations, likelihoods, and correctness labels) available for future research on code LLM calibration.

Related papers

• Evaluating and Achieving Controllable Code Completion in Code LLM [89.64782747840225]
  We present the first instruction-guided code completion benchmark, Controllable Code Completion Benchmark (C3-Bench)<n>We reveal substantial gaps in instruction-following capabilities between open-source and advanced proprietary models during code completion tasks.<n>The resulting model, Qwen2.5-Coder-C3, achieves state-of-the-art performance on C3-Bench.
  arXiv  Detail & Related papers  (2026-01-22T11:40:04Z)
• An Empirical Study of LLM-Based Code Clone Detection [4.393136571408381]
  We show that large language models (LLMs) can achieve comparable performance across different datasets.<n>Most models achieved a high response consistency, with over 90% of judgments remaining consistent across all five submissions.
  arXiv  Detail & Related papers  (2025-11-03T03:00:42Z)
• Ensembling Large Language Models for Code Vulnerability Detection: An Empirical Evaluation [69.8237598448941]
  This study investigates the potential of ensemble learning to enhance the performance of Large Language Models (LLMs) in source code vulnerability detection.<n>We propose Dynamic Gated Stacking (DGS), a Stacking variant tailored for vulnerability detection.
  arXiv  Detail & Related papers  (2025-09-16T03:48:22Z)
• 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)
• Detecting LLM-generated Code with Subtle Modification by Adversarial Training [4.814313782484443]
  We propose an enhanced version of CodeGPTSensor, which employs adversarial training to improve robustness against input perturbations.<n> Experimental results on the HMCorp dataset demonstrate that CodeGPTSensor+ significantly improves detection accuracy on the adversarial test set.
  arXiv  Detail & Related papers  (2025-07-17T13:38:16Z)
• Enhancing LLM-Based Code Generation with Complexity Metrics: A Feedback-Driven Approach [6.289275189295223]
  We investigate the relationship between code complexity and the success of Large Language Models generated code.<n>We propose an iterative feedback method, where LLMs are prompted to generate correct code based on complexity metrics from previous failed outputs.<n>Experiment results show that our approach makes notable improvements, particularly with a smaller LLM.
  arXiv  Detail & Related papers  (2025-05-29T19:06:14Z)
• Quantizing Large Language Models for Code Generation: A Differentiated Replication [51.85505914274633]
  Large Language Models (LLMs) have shown an impressive capability in code generation and, specifically, to automatically implement requirements described in natural language.<n>LLMs pose significant challenges related to their memory (and, consequently, carbon) footprint.<n>New frontier for LLM quantization is 4-bit precision, resulting in an average memory footprint reduction of 70%.
  arXiv  Detail & Related papers  (2025-03-10T09:26:08Z)
• Precision or Peril: Evaluating Code Quality from Quantized Large Language Models [0.5249805590164902]
  Quantization has emerged as a way to mitigate the memory overhead of Large Language Models. This study aims to evaluate the current code generation capabilities of smaller LLMs using various metrics.
  arXiv  Detail & Related papers  (2024-11-16T01:31:29Z)
• Fixing Function-Level Code Generation Errors for Foundation Large Language Models [6.137340149146578]
  We conduct an empirical study on the generation errors and conduct an analysis of their causes, leading to 19 categories of error causes.<n>Our empirical analysis indicated that three of these causes can be directly fixed.<n>We propose a fixing method called LlmFix, which addresses these three types of errors through a three-step process.
  arXiv  Detail & Related papers  (2024-09-01T09:40:15Z)
• What's Wrong with Your Code Generated by Large Language Models? An Extensive Study [92.62952504133926]
  This study evaluated the performance of three leading closed-source LLMs and six popular open-source LLMs on three commonly used benchmarks.<n>We developed a taxonomy of bugs for incorrect codes and analyzed the root cause for common bug types.<n>We propose a novel training-free iterative method that introduces self-critique, enabling LLMs to critique and correct their generated code.
  arXiv  Detail & Related papers  (2024-07-08T17:27:17Z)
• 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)
• StepCoder: Improve Code Generation with Reinforcement Learning from Compiler Feedback [58.20547418182074]
  We introduce StepCoder, a novel framework for code generation, consisting of two main components. CCCS addresses the exploration challenge by breaking the long sequences code generation task into a Curriculum of Code Completion Subtasks. FGO only optimize the model by masking the unexecuted code segments to provide Fine-Grained Optimization. Our method improves the ability to explore the output space and outperforms state-of-the-art approaches in corresponding benchmarks.
  arXiv  Detail & Related papers  (2024-02-02T13:14:31Z)

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.