# mathbbUSCD: Improving Code Generation of LLMs by Uncertainty-Aware Selective Contrastive Decoding

arXiv: https://arxiv.org/abs/2409.05923 · HTML: https://mlsanity.com/paper/2409.05923/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 32 of its 44 references that are in the map.
- First posted on arXiv 9 Sep 2024.

## Builds on (most cited first, 30 of 32)

- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [Program Synthesis with Large Language Models](https://mlsanity.com/paper/2108.07732/) (2021)
- [Code Llama: Open Foundation Models for Code](https://mlsanity.com/paper/2308.12950/) (2023)
- [WizardLM: Empowering large pre-trained language models to follow complex instructions](https://mlsanity.com/paper/2304.12244/) (2023)
- [GLM: General Language Model Pretraining with Autoregressive Blank Infilling](https://mlsanity.com/paper/2103.10360/) (2021)
- [Large Language Models Cannot Self-Correct Reasoning Yet](https://mlsanity.com/paper/2310.01798/) (2023)
- [Teaching Large Language Models to Self-Debug](https://mlsanity.com/paper/2304.05128/) (2023)
- [WizardCoder: Empowering Code Large Language Models with Evol-Instruct](https://mlsanity.com/paper/2306.08568/) (2023)
- [Mitigating Object Hallucinations in Large Vision-Language Models through Visual Contrastive Decoding](https://mlsanity.com/paper/2311.16922/) (2023)
- [Contrastive Decoding: Open-ended Text Generation as Optimization](https://mlsanity.com/paper/2210.15097/) (2022)
- [InCoder: A Generative Model for Code Infilling and Synthesis](https://mlsanity.com/paper/2204.05999/) (2022)
- [Trusting Your Evidence: Hallucinate Less with Context-aware Decoding](https://mlsanity.com/paper/2305.14739/) (2023)
- [Mitigating Hallucinations in Large Vision-Language Models with Instruction Contrastive Decoding](https://mlsanity.com/paper/2403.18715/) (2024)
- [Is Self-Repair a Silver Bullet for Code Generation?](https://mlsanity.com/paper/2306.09896/) (2023)
- [Can ChatGPT Understand Too? A Comparative Study on ChatGPT and Fine-tuned BERT](https://mlsanity.com/paper/2302.10198/) (2023)
- [Towards Making the Most of ChatGPT for Machine Translation](https://mlsanity.com/paper/2303.13780/) (2023)
- [Structured Chain-of-Thought Prompting for Code Generation](https://mlsanity.com/paper/2305.06599/) (2023)
- [Can Large Language Models Really Improve by Self-critiquing Their Own Plans?](https://mlsanity.com/paper/2310.08118/) (2023)
- [Jigsaw: Large Language Models meet Program Synthesis](https://mlsanity.com/paper/2112.02969/) (2021)
- [Abstract Syntax Networks for Code Generation and Semantic Parsing](https://mlsanity.com/paper/1704.07535/) (2017)
- [Latent Predictor Networks for Code Generation](https://mlsanity.com/paper/1603.06744/) (2016)
- [A Retrieve-and-Edit Framework for Predicting Structured Outputs](https://mlsanity.com/paper/1812.01194/) (2018)
- [Automatic Semantic Augmentation of Language Model Prompts (for Code Summarization)](https://mlsanity.com/paper/2304.06815/) (2023)
- [Break-It-Fix-It: Unsupervised Learning for Program Repair](https://mlsanity.com/paper/2106.06600/) (2021)
- [Compilable Neural Code Generation with Compiler Feedback](https://mlsanity.com/paper/2203.05132/) (2022)
- [Mitigating Hallucinations and Off-target Machine Translation with Source-Contrastive and Language-Contrastive Decoding](https://mlsanity.com/paper/2309.07098/) (2023)
- [Retrieval-Based Neural Code Generation](https://mlsanity.com/paper/1808.10025/) (2018)
- [ROSE Doesn't Do That: Boosting the Safety of Instruction-Tuned Large Language Models with Reverse Prompt Contrastive Decoding](https://mlsanity.com/paper/2402.11889/) (2024)
- [Beyond Code Generation: An Observational Study of ChatGPT Usage in Software Engineering Practice](https://mlsanity.com/paper/2404.14901/) (2024)

## Built on by (most cited first, 6 of 6)

- [DynamicKV: Task-Aware Adaptive KV Cache Compression for Long Context LLMs](https://mlsanity.com/paper/2412.14838/) (2024)
- [Loki's Dance of Illusions: A Comprehensive Survey of Hallucination in Large Language Models](https://mlsanity.com/paper/2507.02870/) (2025)
- [Enhancing Input-Label Mapping in In-Context Learning with Contrastive Decoding](https://mlsanity.com/paper/2502.13738/) (2025)
- [Temporal Guidance for Large Language Models](https://mlsanity.com/paper/2601.21744/) (2026)
- [Gradient-Guided Reward Optimization for Inference-time Alignment](https://mlsanity.com/paper/2606.09635/) (2026)
- [Beyond Tokens: A Survey on Decoding Methods for Large Language and Vision-Language Models](https://mlsanity.com/paper/2608.14797/) (2026)

## Abstract (arXiv)

Large language models (LLMs) have shown remarkable capabilities in code generation. However, the effects of hallucinations (e.g., output noise) make it particularly challenging for LLMs to generate high-quality code in one pass. In this work, we propose a simple and effective uncertainty-aware selective contrastive decoding (mathbbUSCD) mechanism to improve the quality of one-pass code generation in LLMs and reduce the impact of output noise. To be specific, we first elaborately designed a negative prompt (namely lame prompt) to output noise by removing input-output examples from the standard few-shot prompt. Our preliminary study shows that the Jensen-Shannon divergence (JS divergence) between token distribution uncertainty and the output noise is relatively low (approximately 0.25), indicating their high relevance. Then, we selectively eliminate output noise induced by lame prompts based on the uncertainty of the prediction distribution from the standard prompt. Notably, our proposed plug-and-play mechanism is an inference-only method, enjoying appealing flexibility. Extensive experiments on widely used benchmarks, e.g., HumanEval, MBPP, and MultiPL-E, upon several LLMs (i.e., Inocder-6b, CodeLlama-7b, WizardCoder-15b, StarCoder, and Llama2-7b), demonstrate that our proposed USCD significantly improves one-pass code generation, with an average textitpass@1 scores increase of 16.59%. We will release code and data on GitHub.