arXiv Machine Learning
LLMs program using Reusable and Composable Abstract Representations
Read the original on arXiv Machine Learning →The Flow has not summarised this story yet — read it at arXiv Machine Learning.
Related stories
Hugging Face Trending Papers
Oct 13
LLMs program using Reusable and Composable Abstract Representations
When writing code, the same computation can be expressed in different programming languages and through different implementation strategies. We show that the activations of LLMs capture this shared st...
arXiv Computation and Language
Oct 21
From Abstraction to Action: DSLs for Natural Language Abstraction Interpretation and Execution
The paper introduces domain-specific languages (DSLs) as an explicit representation layer to bridge the gap between high-level natural-language abstractions and concrete actions. Experiments on the visually-grounded “Hexagons” task and the “Text2CAD” benchmark show that code generation using a human-curated DSL yields dramatic performance gains, especially at higher abstraction levels, while automatically induced DSLs only partially recover these gains. The study highlights that the right representation can close much of the performance gap caused by abstraction, but that automatically learning such representations remains a challenge.
arXiv AI
Sep 2
Predicting Program Exit Code with LLMs and Programming Language Semantics
The paper introduces Program Executability Prediction (PrEx), a task that asks large language models (LLMs) to determine whether a program is semantically valid or invalid and, if invalid, to identify the violated formal rule. To evaluate this, the authors create a dataset of systematically generated invalid programs derived from valid ones and test open‑source coding LLMs across different semantic formalisms, semantic shifts, and program splits (human‑written, LLM‑translated, fuzzer‑generated). Results show that LLMs rely more on pre‑training priors than on the provided semantics, performing poorly on modified semantics and with increasing program complexity.
arXiv AI
Jul 16
Generative Compilation: On-the-Fly Compiler Feedback as AI Generates Code
arXiv:2607. 13921v1 Announce Type: cross Abstract: Languages with rich static semantics, such as Rust, provide stronger guarantees for AI-generated code, but their strictness makes generation more difficult.
arXiv AI
Jun 8
Discovering Interpretable Algorithms by Decompiling Transformers to RASP
arXiv:2602. 08857v2 Announce Type: replace-cross Abstract: Recent work has shown that the computations of Transformers can be simulated in the RASP family of programming languages.
arXiv Machine Learning
Aug 24
Detecting Functional Memorization in Code Language Models
arXiv:2606.12764v2 Announce Type: replace Abstract: Large language models (LLMs) are increasingly used to generate code at scale. Meanwhile, prior work has investigated whether training data may be r...