# When to Show a Suggestion? Integrating Human Feedback in AI-Assisted Programming

arXiv: https://arxiv.org/abs/2306.04930 · HTML: https://mlsanity.com/paper/2306.04930/

## Key facts

- Cited by 25 papers in the map (data through 14 Oct 2026).
- Placed in Process reward models for reasoning, one of 10 directions in LLM alignment / RLHF / preference optimisation.
- Builds on 28 of its 54 references that are in the map.
- First posted on arXiv 8 Jun 2023.

## Placed in

- LLM alignment / RLHF / preference optimisation / [Process reward models for reasoning](https://mlsanity.com/alignment/process-reward-models-for-reasoning/)

## Builds on (most cited first, 28 of 28)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [XGBoost: A Scalable Tree Boosting System](https://mlsanity.com/paper/1603.02754/) (2016)
- [Deep reinforcement learning from human preferences](https://mlsanity.com/paper/1706.03741/) (2017)
- [Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback](https://mlsanity.com/paper/2204.05862/) (2022)
- [Fine-Tuning Language Models from Human Preferences](https://mlsanity.com/paper/1909.08593/) (2019)
- [Competition-Level Code Generation with AlphaCode](https://mlsanity.com/paper/2203.07814/) (2022)
- [CodeBERT: A Pre-Trained Model for Programming and Natural Languages](https://mlsanity.com/paper/2002.08155/) (2020)
- [Measuring Coding Challenge Competence With APPS](https://mlsanity.com/paper/2105.09938/) (2021)
- [Consistent Estimators for Learning to Defer to an Expert](https://mlsanity.com/paper/2006.01862/) (2020)
- [Predict Responsibly: Improving Fairness and Accuracy by Learning to Defer](https://mlsanity.com/paper/1711.06664/) (2017)
- [Grounded Copilot: How Programmers Interact with Code-Generating Models](https://mlsanity.com/paper/2206.15000/) (2022)
- [Interactive Learning from Policy-Dependent Human Feedback](https://mlsanity.com/paper/1701.06049/) (2017)
- [GitHub Copilot AI pair programmer: Asset or Liability?](https://mlsanity.com/paper/2206.15331/) (2022)
- [The Algorithmic Automation Problem: Prediction, Triage, and Human Effort](https://mlsanity.com/paper/1903.12220/) (2019)
- [Productivity Assessment of Neural Code Completion](https://mlsanity.com/paper/2205.06537/) (2022)
- [Reading Between the Lines: Modeling User Behavior and Costs in AI-Assisted Programming](https://mlsanity.com/paper/2210.14306/) (2022)
- [Differentiable Learning Under Triage](https://mlsanity.com/paper/2103.08902/) (2021)
- [Who Should Predict? Exact Algorithms For Learning to Defer to Humans](https://mlsanity.com/paper/2301.06197/) (2023)
- [Out of the BLEU: how should we assess quality of the Code Generation models?](https://mlsanity.com/paper/2208.03133/) (2022)
- [Sample Efficient Learning of Predictors that Complement Humans](https://mlsanity.com/paper/2207.09584/) (2022)
- [Perfection Not Required? Human-AI Partnerships in Code Translation](https://mlsanity.com/paper/2104.03820/) (2021)
- [What is it like to program with artificial intelligence?](https://mlsanity.com/paper/2208.06213/) (2022)
- [Teaching Humans When To Defer to a Classifier via Exemplars](https://mlsanity.com/paper/2111.11297/) (2021)
- [Learning Personalized Decision Support Policies](https://mlsanity.com/paper/2304.06701/) (2023)
- [Attention-Sensitive Alerting](https://mlsanity.com/paper/1301.6707/) (2013)

## Built on by (most cited first, 25 of 25)

- ["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)
- [Using AI-Based Coding Assistants in Practice: State of Affairs, Perceptions, and Ways Forward](https://mlsanity.com/paper/2406.07765/) (2024)
- [Navigating Rifts in Human-LLM Grounding: Study and Benchmark](https://mlsanity.com/paper/2503.13975/) (2025)
- [Flows: Building Blocks of Reasoning and Collaborating AI](https://mlsanity.com/paper/2308.01285/) (2023)
- [The Rise of the AI Co-Pilot: Lessons for Design from Aviation and Beyond](https://mlsanity.com/paper/2311.14713/) (2023)
- [When Neural Code Completion Models Size up the Situation: Attaining Cheaper and Faster Completion through Dynamic Model Inference](https://mlsanity.com/paper/2401.09964/) (2024)
- [Utilizing Human Behavior Modeling to Manipulate Explanations in AI-Assisted Decision Making: The Good, the Bad, and the Scary](https://mlsanity.com/paper/2411.10461/) (2024)
- [Pitfalls in Language Models for Code Intelligence: A Taxonomy and Survey](https://mlsanity.com/paper/2310.17903/) (2023)
- [Explaining and Improving Information Complementarities in Multi-Agent Decision-making](https://mlsanity.com/paper/2502.06152/) (2025)
- [Human-AI Experience in Integrated Development Environments: A Systematic Literature Review](https://mlsanity.com/paper/2503.06195/) (2025)
- [When Are Two Lists Better than One?: Benefits and Harms in Joint Decision-making](https://mlsanity.com/paper/2308.11721/) (2023)
- ["My productivity is boosted, but ..." Demystifying Users' Perception on AI Coding Assistants](https://mlsanity.com/paper/2508.12285/) (2025)
- [Modeling and Optimizing User Preferences in AI Copilots: A Comprehensive Survey and Taxonomy](https://mlsanity.com/paper/2505.21907/) (2025)
- [Multi-Round Human-AI Collaboration with User-Specified Requirements](https://mlsanity.com/paper/2602.17646/) (2026)
- [Agentic Coding Needs Proactivity, Not Just Autonomy](https://mlsanity.com/paper/2605.06717/) (2026)
- [A Dynamic Model of Performative Human-ML Collaboration: Theory and Empirical Evidence](https://mlsanity.com/paper/2405.13753/) (2024)
- [CCCI: Code Completion with Contextual Information for Complex Data Transfer Tasks Using Large Language Models](https://mlsanity.com/paper/2503.23231/) (2025)
- [Optimizing LLM Code Suggestions: Feedback-Driven Timing with Lightweight State Bounds](https://mlsanity.com/paper/2511.18842/) (2025)
- [Pre-Filtering Code Suggestions using Developer Behavioral Telemetry to Optimize LLM-Assisted Programming](https://mlsanity.com/paper/2511.18849/) (2025)
- [ComplLLM: Fine-tuning LLMs to Discover Complementary Signals for Decision-making](https://mlsanity.com/paper/2602.19458/) (2026)
- [The Role of GitHub Copilot on Software Development: A Perspective on Productivity, Security, Best Practices and Future Directions](https://mlsanity.com/paper/2502.13199/) (2025)
- [Toolsuite for Implementing Multiagent Systems Based on Communication Protocols](https://mlsanity.com/paper/2507.10324/) (2025)
- [A Benchmark and Framework for Evaluating Next Action Predictions in Spreadsheets](https://mlsanity.com/paper/2606.13802/) (2026)
- [Propose to Learn, Learn to Propose: Evaluability-Aware Assistance under Bounded Rationality](https://mlsanity.com/paper/2609.02242/) (2026)
- [ParallelPilot: Supporting Coordination and Monitoring in Parallel AI Coding](https://mlsanity.com/paper/2609.33113/) (2026)

## Abstract (arXiv)

AI powered code-recommendation systems, such as Copilot and CodeWhisperer, provide code suggestions inside a programmer's environment (e.g., an IDE) with the aim of improving productivity. We pursue mechanisms for leveraging signals about programmers' acceptance and rejection of code suggestions to guide recommendations. We harness data drawn from interactions with GitHub Copilot, a system used by millions of programmers, to develop interventions that can save time for programmers. We introduce a utility-theoretic framework to drive decisions about suggestions to display versus withhold. The approach, conditional suggestion display from human feedback (CDHF), relies on a cascade of models that provide the likelihood that recommended code will be accepted. These likelihoods are used to selectively hide suggestions, reducing both latency and programmer verification time. Using data from 535 programmers, we perform a retrospective evaluation of CDHF and show that we can avoid displaying a significant fraction of suggestions that would have been rejected. We further demonstrate the importance of incorporating the programmer's latent unobserved state in decisions about when to display suggestions through an ablation study. Finally, we showcase how using suggestion acceptance as a reward signal for guiding the display of suggestions can lead to suggestions of reduced quality, indicating an unexpected pitfall.