# HiLDe: Intentional Code Generation via Human-in-the-Loop Decoding

arXiv: https://arxiv.org/abs/2505.22906 · HTML: https://mlsanity.com/paper/2505.22906/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 39 of its 52 references that are in the map.
- First posted on arXiv 28 May 2025.

## Builds on (most cited first, 30 of 39)

- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [Neural Machine Translation of Rare Words with Subword Units](https://mlsanity.com/paper/1508.07909/) (2015)
- [SentencePiece: A simple and language independent subword tokenizer and detokenizer for Neural Text Processing](https://mlsanity.com/paper/1808.06226/) (2018)
- [Qwen2.5-Coder Technical Report](https://mlsanity.com/paper/2409.12186/) (2024)
- [Asleep at the Keyboard? Assessing the Security of GitHub Copilot's Code Contributions](https://mlsanity.com/paper/2108.09293/) (2021)
- [Effect of Confidence and Explanation on Accuracy and Trust Calibration in AI-Assisted Decision Making](https://mlsanity.com/paper/2001.02114/) (2020)
- [The Impact of AI on Developer Productivity: Evidence from GitHub Copilot](https://mlsanity.com/paper/2302.06590/) (2023)
- [Grounded Copilot: How Programmers Interact with Code-Generating Models](https://mlsanity.com/paper/2206.15000/) (2022)
- [Do Users Write More Insecure Code with AI Assistants?](https://mlsanity.com/paper/2211.03622/) (2022)
- [Large Language Models for Code: Security Hardening and Adversarial Testing](https://mlsanity.com/paper/2302.05319/) (2023)
- [Examining Zero-Shot Vulnerability Repair with Large Language Models](https://mlsanity.com/paper/2112.02125/) (2021)
- [A Large-Scale Survey on the Usability of AI Programming Assistants: Successes and Challenges](https://mlsanity.com/paper/2303.17125/) (2023)
- ["I'm Not Sure, But...": Examining the Impact of Large Language Models' Uncertainty Expression on User Reliance and Trust](https://mlsanity.com/paper/2405.00623/) (2024)
- [Luminate: Structured Generation and Exploration of Design Space with Large Language Models for Human-AI Co-Creation](https://mlsanity.com/paper/2310.12953/) (2023)
- [Investigating Explainability of Generative AI for Code through Scenario-based Design](https://mlsanity.com/paper/2202.04903/) (2022)
- [Finetuning Large Language Models for Vulnerability Detection](https://mlsanity.com/paper/2401.17010/) (2024)
- [WaitGPT: Monitoring and Steering Conversational LLM Agent in Data Analysis with On-the-Fly Code Visualization](https://mlsanity.com/paper/2408.01703/) (2024)
- [DynaVis: Dynamically Synthesized UI Widgets for Visualization Editing](https://mlsanity.com/paper/2401.10880/) (2024)
- [Assistance or Disruption? Exploring and Evaluating the Design and Trade-offs of Proactive AI Programming Support](https://mlsanity.com/paper/2502.18658/) (2025)
- [Vulnerabilities in AI Code Generators: Exploring Targeted Data Poisoning Attacks](https://mlsanity.com/paper/2308.04451/) (2023)
- [Improving Steering and Verification in AI-Assisted Data Analysis with Interactive Task Decomposition](https://mlsanity.com/paper/2407.02651/) (2024)
- [On the Design of AI-powered Code Assistants for Notebooks](https://mlsanity.com/paper/2301.11178/) (2023)
- [Supporting Sensemaking of Large Language Model Outputs at Scale](https://mlsanity.com/paper/2401.13726/) (2024)
- [Beyond Code Generation: An Observational Study of ChatGPT Usage in Software Engineering Practice](https://mlsanity.com/paper/2404.14901/) (2024)
- [Generation Probabilities Are Not Enough: Uncertainty Highlighting in AI Code Completions](https://mlsanity.com/paper/2302.07248/) (2023)
- [Can We Trust Large Language Models Generated Code? A Framework for In-Context Learning, Security Patterns, and Code Evaluations Across Diverse LLMs](https://mlsanity.com/paper/2406.12513/) (2024)
- [Poisoned ChatGPT Finds Work for Idle Hands: Exploring Developers' Coding Practices with Insecure Suggestions from Poisoned AI Models](https://mlsanity.com/paper/2312.06227/) (2023)
- [Ivie: Lightweight Anchored Explanations of Just-Generated Code](https://mlsanity.com/paper/2403.02491/) (2024)
- [Beyond Code Generation: LLM-supported Exploration of the Program Design Space](https://mlsanity.com/paper/2503.06911/) (2025)

## Built on by (most cited first, 1 of 1)

- [Does In-IDE Calibration of Large Language Models work at Scale?](https://mlsanity.com/paper/2510.22614/) (2025)

## Abstract (arXiv)

While AI programming tools hold the promise of increasing programmers' capabilities and productivity to a remarkable degree, they often exclude users from essential decision-making processes, causing many to effectively "turn off their brains" and over-rely on solutions provided by these systems. These behaviors can have severe consequences in critical domains, like software security. We propose Human-in-the-loop Decoding, a novel interaction technique that allows users to observe and directly influence LLM decisions during code generation, in order to align the model's output with their personal requirements. We implement this technique in HiLDe, a code completion assistant that highlights critical decisions made by the LLM and provides local alternatives for the user to explore. In a within-subjects study (N=18) on security-related tasks, we found that HiLDe led participants to generate significantly fewer vulnerabilities and better align code generation with their goals compared to a traditional code completion assistant.