arXiv Machine Learning August 4, 2026 By Vinayshekhar Bannihatti Kumar, Disha Makhija, Manoj Ghuhan Arivazhagan, Rashmi Gangadharaiah

Syntax Without Semantics: Teaching Large Language Models to Code in an Unseen Language

Read the original on arXiv Machine Learning →

arXiv:2605. 15607v2 Announce Type: replace-cross Abstract: Large language models (LLMs) achieve high pass rates on code generation benchmarks, yet whether they can transfer this ability to languages absent from pretraining remains poorly understood.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

arXiv Machine Learning

Jul 10

Selective Left-Shift: Turning Test-Time Compute and Difficulty-based Curation into Training Data for Low-Resource Code Generation

arXiv:2607. 07748v1 Announce Type: new Abstract: Large Language Models achieve strong code generation for high resource languages like Python and Java but suffer sharp performance drops on Low-Resource Programming Languages~(LRPLs) such as Julia.

By Didula Samaraweera, Anjana Supun, Srinath Perera

llms reinforcement-learning fine-tuning benchmarks

arXiv Machine Learning

Jun 25

Weave of Formal Thought

arXiv:2606. 25987v1 Announce Type: cross Abstract: Large language models (LLMs) attain remarkable surface fluency on code, yet they neither formally guarantee the syntactic validity of their output nor leverage the hierarchical structure defining the target language.

By Alexandre Bouayad

llms nlp fine-tuning

arXiv Computation and Language

Sep 22

LLM-Based FORM Code Generation with Verification-Driven Fine-Tuning

arXiv:2609.23367v1 Announce Type: cross Abstract: FORM is a domain-specific symbolic manipulation language widely used in particle physics for processing the very large algebraic expressions arising...

By Bakar Chargeishvili

llms robotics fine-tuning efficiency benchmarks

arXiv Machine Learning

Aug 6

From Brute Force to Semantic Insight: Performance-Guided Data Transformation Design with LLMs

arXiv:2601. 03808v2 Announce Type: replace-cross Abstract: Large language models (LLMs) have achieved notable performance in code synthesis; however, data-aware augmentation remains a limiting factor, handled via heuristic design or brute-force approaches.

By Usha Shrestha, Dmitry Ignatov, Radu Timofte

llms reinforcement-learning fine-tuning benchmarks safety

arXiv AI

Aug 26

Evaluating Language Models on Cross-Language Code Functional Equivalence

The paper introduces PolyHuman, a dataset of human-written programs in C++, Java, and Python, to test whether large language models can judge functional equivalence across languages. Using this dataset, the authors evaluate several open-weight and proprietary LLMs, finding that models struggle more with harder problems, show language-specific biases, and rely partly on superficial similarity cues. They also observe run‑to‑run instability in GPT‑o4‑mini, concluding that current LLMs do not reliably capture functional equivalence within or across programming languages.

By Hui Sun, Anderson Uch\^oa, Rohit Gheyi, Wesley K. G. Assun\c{c}\~ao

llms benchmarks

arXiv AI

Jul 24

Learn2Zinc: Fine-tuning Small Language Models for Text-to-Model Translation in MiniZinc

arXiv:2607. 20456v1 Announce Type: cross Abstract: Large language models excel at code generation for mainstream programming languages but struggle with rare, domain-specific languages such as MiniZinc, a constraint modeling language for combinatorial problems.

By Serdar Kadioglu, Karthik Uppuluri

llms fine-tuning

One email a morning, machine-written

Related stories

Selective Left-Shift: Turning Test-Time Compute and Difficulty-based Curation into Training Data for Low-Resource Code Generation

Weave of Formal Thought

LLM-Based FORM Code Generation with Verification-Driven Fine-Tuning

From Brute Force to Semantic Insight: Performance-Guided Data Transformation Design with LLMs

Evaluating Language Models on Cross-Language Code Functional Equivalence

Learn2Zinc: Fine-tuning Small Language Models for Text-to-Model Translation in MiniZinc