# Uncertainty-Guided Chain-of-Thought for Code Generation with LLMs

arXiv: https://arxiv.org/abs/2503.15341 · HTML: https://mlsanity.com/paper/2503.15341/

## Key facts

- Cited by 32 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning for agents, planning and code, one of 17 directions in LLM reasoning.
- Builds on 20 of its 26 references that are in the map.
- First posted on arXiv 19 Mar 2025.

## Placed in

- LLM reasoning / [Reasoning for agents, planning and code](https://mlsanity.com/lr/reasoning-for-agents-planning-and-code/)

## Builds on (most cited first, 20 of 20)

- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [Large Language Models are Zero-Shot Reasoners](https://mlsanity.com/paper/2205.11916/) (2022)
- [Code Llama: Open Foundation Models for Code](https://mlsanity.com/paper/2308.12950/) (2023)
- [Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Them](https://mlsanity.com/paper/2210.09261/) (2022)
- [Qwen2.5-Coder Technical Report](https://mlsanity.com/paper/2409.12186/) (2024)
- [DeepSeek-Coder: When the Large Language Model Meets Programming -- The Rise of Code Intelligence](https://mlsanity.com/paper/2401.14196/) (2024)
- [Large Language Models Are Human-Level Prompt Engineers](https://mlsanity.com/paper/2211.01910/) (2022)
- [Teaching Large Language Models to Self-Debug](https://mlsanity.com/paper/2304.05128/) (2023)
- [Do NOT Think That Much for 2+3=? On the Overthinking of o1-Like LLMs](https://mlsanity.com/paper/2412.21187/) (2024)
- [Chain-of-Thought Reasoning Without Prompting](https://mlsanity.com/paper/2402.10200/) (2024)
- [Planning with Large Language Models for Code Generation](https://mlsanity.com/paper/2303.05510/) (2023)
- [Structured Chain-of-Thought Prompting for Code Generation](https://mlsanity.com/paper/2305.06599/) (2023)
- [Natural Language to Code Translation with Execution](https://mlsanity.com/paper/2204.11454/) (2022)
- [Repository-Level Prompt Generation for Large Language Models of Code](https://mlsanity.com/paper/2206.12839/) (2022)
- [Calibration and Correctness of Language Models for Code](https://mlsanity.com/paper/2402.02047/) (2024)
- [Teaching Code LLMs to Use Autocompletion Tools in Repository-Level Code Generation](https://mlsanity.com/paper/2401.06391/) (2024)
- [MHPP: Exploring the Capabilities and Limitations of Language Models Beyond Basic Code Generation](https://mlsanity.com/paper/2405.11430/) (2024)
- [Large Language Models for Code Generation: A Comprehensive Survey of Challenges, Techniques, Evaluation, and Applications](https://mlsanity.com/paper/2503.01245/) (2025)
- [Guiding Language Models of Code with Global Context using Monitors](https://mlsanity.com/paper/2306.10763/) (2023)
- [Exploring Data-Efficient Adaptation of Large Language Models for Code Generation](https://mlsanity.com/paper/2403.00046/) (2024)

## Built on by (most cited first, 30 of 32)

- [TokUR: Token-Level Uncertainty Estimation for Large Language Model Reasoning](https://mlsanity.com/paper/2505.11737/) (2025)
- [Think Just Enough: Sequence-Level Entropy as a Confidence Signal for LLM Reasoning](https://mlsanity.com/paper/2510.08146/) (2025)
- [Uncertainty Quantification in LLM Agents: Foundations, Emerging Challenges, and Opportunities](https://mlsanity.com/paper/2602.05073/) (2026)
- [Semantic Energy: Detecting LLM Hallucination Beyond Entropy](https://mlsanity.com/paper/2508.14496/) (2025)
- [Temporalizing Confidence: Evaluation of Chain-of-Thought Reasoning with Signal Temporal Logic](https://mlsanity.com/paper/2506.08243/) (2025)
- [TreeDiff: AST-Guided Code Generation with Diffusion LLMs](https://mlsanity.com/paper/2508.01473/) (2025)
- [Reasoning Efficiently Through Adaptive Chain-of-Thought Compression: A Self-Optimizing Framework](https://mlsanity.com/paper/2509.14093/) (2025)
- [From Reasoning Traces to Reusable Modules: Understanding Compositional Generalization in Language Model Reasoning](https://mlsanity.com/paper/2606.18089/) (2026)
- [Chain-of-Code Collapse: Reasoning Failures in LLMs via Adversarial Prompting in Code Generation](https://mlsanity.com/paper/2506.06971/) (2025)
- [Self-Reflective Generation at Test Time](https://mlsanity.com/paper/2510.02919/) (2025)
- [Lil: Less is Less When Applying Post-Training Sparse-Attention Algorithms in Long-Decode Stage](https://mlsanity.com/paper/2601.03043/) (2026)
- [Uncertainty Propagation in LLM-Based Systems](https://mlsanity.com/paper/2604.23505/) (2026)
- [Functional Entropy: Predicting Functional Correctness in LLM-Generated Code with Uncertainty Quantification](https://mlsanity.com/paper/2605.28500/) (2026)
- [Fast, Slow, and Tool-augmented Thinking for LLMs: A Review](https://mlsanity.com/paper/2508.12265/) (2025)
- [Can Confidence Estimates Decide When Chain-of-Thought Is Necessary for LLMs?](https://mlsanity.com/paper/2510.21007/) (2025)
- [Reinforcement Learning-Guided Chain-of-Draft for Token-Efficient Code Generation](https://mlsanity.com/paper/2509.25243/) (2025)
- [Benchmarking Text-to-Python against Text-to-SQL: The Impact of Explicit Logic and Ambiguity](https://mlsanity.com/paper/2601.15728/) (2026)
- [Uncertainty and Fairness Awareness in LLM-Based Recommendation Systems](https://mlsanity.com/paper/2602.02582/) (2026)
- [Enhancing LLM Reasoning via Non-Human-Like Reasoning Path Preference Optimization](https://mlsanity.com/paper/2510.11104/) (2025)
- [Lifecycle-Aware code generation: Leveraging Software Engineering Phases in LLMs](https://mlsanity.com/paper/2510.24019/) (2025)
- [Synthesizing File-Level Data for Unit Test Generation with Chain-of-Thoughts via Self-Debugging](https://mlsanity.com/paper/2602.03181/) (2026)
- [Structural Anchors and Reasoning Fragility:Understanding CoT Robustness in LLM4Code](https://mlsanity.com/paper/2604.12214/) (2026)
- [Improving LLM Code Generation via Requirement-Aware Curriculum Reinforcement Learning](https://mlsanity.com/paper/2605.00433/) (2026)
- [OracleTSC: Oracle-Informed Reward Hurdle and Uncertainty Regularization for Traffic Signal Control](https://mlsanity.com/paper/2605.08516/) (2026)
- [ThinkBooster: A Unified Framework for Seamless Test-Time Scaling of LLM Reasoning](https://mlsanity.com/paper/2606.06915/) (2026)
- [Code-MUE: Measuring Code LLMs' Uncertainty through Execution-based Semantic Interaction Graphs](https://mlsanity.com/paper/2607.12273/) (2026)
- [How Reasoning Shapes Social Bias in LLM-Generated Code?](https://mlsanity.com/paper/2608.06829/) (2026)
- [When Uncertainty Isn't Enough: An Empirical Study of Self-Correction in Code Generation](https://mlsanity.com/paper/2608.14659/) (2026)
- [GUT: Quantifying and Optimizing the Reasoning Uncertainty of LLMs via Graph Complexity](https://mlsanity.com/paper/2609.05284/) (2026)
- [Uncertainty Quantification for LLM Agents: A Taxonomy, an Evaluation Protocol, and an Empirical Study](https://mlsanity.com/paper/2609.07395/) (2026)

## Abstract (arXiv)

Chain-of-Thought (CoT) reasoning has been demonstrated as an effective technique for improving the problem-solving capabilities of large language models (LLMs) in the context of code generation. However, existing CoT methods often exhibit a tendency toward "overthinking", where the LLM consistently applies reasoning strategies without adequately considering the task's underlying complexity. This results in the LLMs allocating excessive computational resources, in terms of tokens, to relatively simple tasks or problems where the correct answer is already evident. Additionally, this overthinking may lead LLMs down incorrect reasoning paths, resulting in incorrect code generation. In this paper, we introduce UnCertainty-Aware Chain-of-Thought (UnCert-CoT), an LLM-based approach designed to enhance code generation by incorporating an uncertainty-aware CoT reasoning mechanism, which focuses computational resources on targeting points where LLMs are more prone to error. We propose two confidence-based uncertainty measures: Entropy-based and Probability Differential-based methods. When uncertainty is high, UnCert-CoT activates CoT-decoding to generate multiple reasoning paths and selects the final code that exhibits the highest likelihood of correctness. In contrast, LLM directly generates the code when uncertainty is low. This uncertainty judgment mechanism allows LLMs to prioritize complex tasks and avoid unnecessary steps in simpler cases, thereby improving overall efficiency and accuracy in code generation. Our experimental results demonstrate that UnCert-CoT significantly enhances code generation accuracy on challenging benchmark MHPP(Mostly Hard Python Problems), it achieves improvements up to 6.1% on PassRate accuracy, particularly in situations where traditional LLMs are prone to errors.