# AssumptionMiner: Extracting, Tracing, and Revising Implicit Assumptions in LLM Code Generation

arXiv: https://arxiv.org/abs/2607.22898 · HTML: https://mlsanity.com/paper/2607.22898/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 26 of its 57 references that are in the map.
- First posted on arXiv 24 Jul 2026.

## Builds on (most cited first, 26 of 26)

- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [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)
- [GPT-4o System Card](https://mlsanity.com/paper/2410.21276/) (2024)
- [Program Synthesis with Large Language Models](https://mlsanity.com/paper/2108.07732/) (2021)
- [Self-Refine: Iterative Refinement with Self-Feedback](https://mlsanity.com/paper/2303.17651/) (2023)
- [SWE-bench: Can Language Models Resolve Real-World GitHub Issues?](https://mlsanity.com/paper/2310.06770/) (2023)
- [Competition-Level Code Generation with AlphaCode](https://mlsanity.com/paper/2203.07814/) (2022)
- [A Prompt Pattern Catalog to Enhance Prompt Engineering with ChatGPT](https://mlsanity.com/paper/2302.11382/) (2023)
- [GraphCodeBERT: Pre-training Code Representations with Data Flow](https://mlsanity.com/paper/2009.08366/) (2020)
- [Self-collaboration Code Generation via ChatGPT](https://mlsanity.com/paper/2304.07590/) (2023)
- [Is Self-Repair a Silver Bullet for Code Generation?](https://mlsanity.com/paper/2306.09896/) (2023)
- [SequenceR: Sequence-to-Sequence Learning for End-to-End Program Repair](https://mlsanity.com/paper/1901.01808/) (2018)
- [Self-planning Code Generation with Large Language Models](https://mlsanity.com/paper/2303.06689/) (2023)
- [Productivity Assessment of Neural Code Completion](https://mlsanity.com/paper/2205.06537/) (2022)
- [Fuzz4All: Universal Fuzzing with Large Language Models](https://mlsanity.com/paper/2308.04748/) (2023)
- [Neural Program Repair with Execution-based Backpropagation](https://mlsanity.com/paper/2105.04123/) (2021)
- [Interactive Code Generation via Test-Driven User-Intent Formalization](https://mlsanity.com/paper/2208.05950/) (2022)
- [Conversational Automated Program Repair](https://mlsanity.com/paper/2301.13246/) (2023)
- [HumanEvalComm: Benchmarking the Communication Competence of Code Generation for LLMs and LLM Agent](https://mlsanity.com/paper/2406.00215/) (2024)
- [AVATAR : Fixing Semantic Bugs with Fix Patterns of Static Analysis Violations](https://mlsanity.com/paper/1812.07270/) (2018)
- [Traceability Transformed: Generating more Accurate Links with Pre-Trained BERT Models](https://mlsanity.com/paper/2102.04411/) (2021)
- [Specifications: The missing link to making the development of LLM systems an engineering discipline](https://mlsanity.com/paper/2412.05299/) (2024)
- [When Prompts Go Wrong: Evaluating Code Model Robustness to Ambiguous, Contradictory, and Incomplete Task Descriptions](https://mlsanity.com/paper/2507.20439/) (2025)
- [Defective Task Descriptions in LLM-Based Code Generation: Detection and Analysis](https://mlsanity.com/paper/2604.24703/) (2026)
- [Correctness, confidence, and context: Framing software assurance in the AI age](https://mlsanity.com/paper/2607.04667/) (2026)

## Abstract (arXiv)

Large language models (LLMs) generate code from natural-language prompts, yet real-world prompts rarely provide complete specifications. When prompts leave input formats, error handling, or design decisions unspecified, LLMs fill these gaps with implicit assumptions that shape the generated code's behavior and correctness. Because these assumptions remain hidden, generated code may satisfy tests while violating developer intent. We present AssumptionMiner, a framework that makes implicit assumptions a first-class artifact of LLM-based code generation. In addition to code, AssumptionMiner produces an explicit assumption layer, a structured representation of inferred constraints and design decisions that developers can inspect, confirm, or revise. An AST-based dependency graph enables targeted regeneration of only the code affected by a revised assumption. We also introduce a benchmark of 180 ambiguous programming tasks with 676 annotated assumptions, including a human-verified subset for evaluating code localization. We evaluate assumption extraction, code localization, and assumption-guided regeneration. Across open-source LLMs, a confidence-weighted ensemble achieves an F1 score of 0.816 for assumption extraction, improving on the strongest offline baseline by 3.6x. On the human-verified localization benchmark, AST-guided localization identifies more precise code regions than keyword-based and whole-file baselines. During assumption revision, targeted regeneration modifies less code than non-targeted alternatives while exposing challenges in handling cascading edits. These results demonstrate that making assumptions explicit improves the transparency and controllability of LLM-based code generation.