# Position: Intelligent Coding Systems Should Write Programs with Justifications

arXiv: https://arxiv.org/abs/2508.06017 · HTML: https://mlsanity.com/paper/2508.06017/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 34 of its 72 references that are in the map.
- First posted on arXiv 8 Aug 2025.

## Builds on (most cited first, 30 of 34)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Code Llama: Open Foundation Models for Code](https://mlsanity.com/paper/2308.12950/) (2023)
- [OpenHands: An Open Platform for AI Software Developers as Generalist Agents](https://mlsanity.com/paper/2407.16741/) (2024)
- [Agentless: Demystifying LLM-based Software Engineering Agents](https://mlsanity.com/paper/2407.01489/) (2024)
- [Monitoring Reasoning Models for Misbehavior and the Risks of Promoting Obfuscation](https://mlsanity.com/paper/2503.11926/) (2025)
- [Explainability for Large Language Models: A Survey](https://mlsanity.com/paper/2309.01029/) (2023)
- [Magicoder: Empowering Code Generation with OSS-Instruct](https://mlsanity.com/paper/2312.02120/) (2023)
- [Chain-of-Thought Reasoning In The Wild Is Not Always Faithful](https://mlsanity.com/paper/2503.08679/) (2025)
- [ProSA: Assessing and Understanding the Prompt Sensitivity of LLMs](https://mlsanity.com/paper/2410.12405/) (2024)
- [An Empirical Study of the Non-determinism of ChatGPT in Code Generation](https://mlsanity.com/paper/2308.02828/) (2023)
- [The Good, The Bad, and The Greedy: Evaluation of LLMs Should Not Ignore Non-Determinism](https://mlsanity.com/paper/2407.10457/) (2024)
- [What Did I Do Wrong? Quantifying LLMs' Sensitivity and Consistency to Prompt Engineering](https://mlsanity.com/paper/2406.12334/) (2024)
- [Lingma SWE-GPT: An Open Development-Process-Centric Language Model for Automated Software Improvement](https://mlsanity.com/paper/2411.00622/) (2024)
- [QED: A Framework and Dataset for Explanations in Question Answering](https://mlsanity.com/paper/2009.06354/) (2020)
- [RepoAudit: An Autonomous LLM-Agent for Repository-Level Code Auditing](https://mlsanity.com/paper/2501.18160/) (2025)
- [A Perspective on Explainable Artificial Intelligence Methods: SHAP and LIME](https://mlsanity.com/paper/2305.02012/) (2023)
- [Do Explanations Reflect Decisions? A Machine-centric Strategy to Quantify the Performance of Explainability Algorithms](https://mlsanity.com/paper/1910.07387/) (2019)
- [What Prompts Don't Say: Understanding and Managing Underspecification in LLM Prompts](https://mlsanity.com/paper/2505.13360/) (2025)
- [ProSec: Fortifying Code LLMs with Proactive Security Alignment](https://mlsanity.com/paper/2411.12882/) (2024)
- [Rationalization for Explainable NLP: A Survey](https://mlsanity.com/paper/2301.08912/) (2023)
- [Passport: Improving Automated Formal Verification Using Identifiers](https://mlsanity.com/paper/2204.10370/) (2022)
- [Learning Code Preference via Synthetic Evolution](https://mlsanity.com/paper/2410.03837/) (2024)
- [SecCoder: Towards Generalizable and Robust Secure Code Generation](https://mlsanity.com/paper/2410.01488/) (2024)
- [CoqPilot, a plugin for LLM-based generation of proofs](https://mlsanity.com/paper/2410.19605/) (2024)
- [Interpretable Question Answering on Knowledge Bases and Text](https://mlsanity.com/paper/1906.10924/) (2019)
- [SAFE-RL: Saliency-Aware Counterfactual Explainer for Deep Reinforcement Learning Policies](https://mlsanity.com/paper/2404.18326/) (2024)
- [Validating Network Protocol Parsers with Traceable RFC Document Interpretation](https://mlsanity.com/paper/2504.18050/) (2025)
- [Skeletal Program Enumeration for Rigorous Compiler Testing](https://mlsanity.com/paper/1610.03148/) (2016)
- [3DGen: AI-Assisted Generation of Provably Correct Binary Format Parsers](https://mlsanity.com/paper/2404.10362/) (2024)

## Abstract (arXiv)

Intelligent coding systems are transforming software development by enabling users to specify code behavior in natural language. However, the opaque decision-making of AI-driven coders raises trust and usability concerns, particularly for non-expert users who cannot inspect low-level implementations. We argue that these systems should not only generate code but also produce clear, consistent justifications that bridge model reasoning and user understanding. To this end, we identify two critical justification properties-cognitive alignment and semantic faithfulness-and highlight the limitations of existing methods, including formal verification, static analysis, and post-hoc explainability. We advocate exploring neuro-symbolic approaches for justification generation, where symbolic constraints guide model behavior during training and program semantics are enriched through neural representations, enabling automated consistency checks at inference time.