arXiv AI

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.

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.

By Lara Marinov, Aditya Thimmaiah, Jayanth Srinivasa, Junyi Jessy Li, Milos Gligoric

llms

arXiv Machine Learning

5d ago

LLMs are Brittle to Simple Code Transformations: Introducing CETBench - A Benchmark for Code-Equivalence Checking

The paper introduces CETBench, a benchmark for assessing large language models (LLMs) on code-equivalence checking by generating program pairs through random code transformations. It demonstrates that even simple transformations significantly degrade LLM performance, especially in cross-lingual scenarios, and proposes a fine-tuning approach to improve results. The study provides detailed ablations on program difficulty and transformation types, offering insights into LLMs’ limited semantic understanding of code.

By Neeva Oza, Ishaan Govil, Parul Gupta, Dinesh Khandelwal, Dinesh Garg, Parag Singla

llms fine-tuning benchmarks

arXiv AI

Aug 13

Program Semantic Inequivalence Game with Large Language Models

arXiv:2505. 03818v3 Announce Type: replace-cross Abstract: Large Language Models (LLMs) can achieve strong performance on everyday coding tasks, but they can fail on complex tasks that require non-trivial reasoning about program semantics.

By Antonio Valerio Miceli-Barone, Vaishak Belle, Ali Payani

llms agents fine-tuning benchmarks

arXiv Machine Learning

Jul 22

Spaghetti Architect: A Contamination-Resistant, By-Construction-Labelled, Multi-Language Code Dataset Generator

arXiv:2607. 18642v1 Announce Type: new Abstract: Mined code corpora are abundant but uncontrolled: a snippet's semantics, surface "messiness," and difficulty are whatever the wild contained; there is no known-optimal reference to grade against; and any public sample may already sit in a model's training set.

By Yuxiang Ji

arXiv AI

Jun 8

SWE-IF: Aligning Code Evaluation with Human Preference

arXiv:2510. 07315v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) have catalyzed vibe coding, where users leverage LLMs to generate and iteratively refine code through natural language interactions until it passes their vibe check.

By Ming Zhong, Xiang Zhou, Ting-Yun Chang, Qingze Wang, Nan Xu, Xiance Si, Dan Garrette, Shyam Upadhyay, Jeremiah Liu, Jiawei Han, Benoit Schillings, Jiao Sun

llms

arXiv AI

Jun 9

Beyond Pass Rate: A Multilingual, Execution-Grounded Evaluation of Open Code LLMs

arXiv:2606. 08840v1 Announce Type: new Abstract: Code generation models are typically compared using compact execution benchmarks and aggregate pass rates, but such summaries obscure how performance varies across programming languages, problem families, and failure modes.

By Sayed Erfan Arefin

llms benchmarks

arXiv AI

Oct 5

Are you Synthesizing or Recalling? Evaluating LLMs on Algorithmic Code Retrieval

arXiv:2610.02438v1 Announce Type: cross Abstract: Large language models (LLMs) have demonstrated strong performance in code generation, where success depends on both recalling relevant algorithmic kn...

By Nickil Maveli, Antonio Vergari, Shay B. Cohen

llms fine-tuning benchmarks

arXiv AI

Aug 11

Contamination Means Overestimation? A Fine-Grained Empirical Study in Code Intelligence

arXiv:2506. 02791v4 Announce Type: replace-cross Abstract: In recent years, code intelligence has gained increasing importance in the field of automated software engineering.

By Zhen Yang, Hongyi Lin, Yifan He, Junqi Wang, Zeyu Sun, Shuo Liu, Jie Xu, Pengpeng Wang, Zhongxing Yu, Qingyuan Liang

llms nlp fine-tuning

arXiv AI

Jul 15

Code-MUE: Measuring Code LLMs' Uncertainty through Execution-based Semantic Interaction Graphs

arXiv:2607. 12273v1 Announce Type: cross Abstract: As Code Large Language Models (LLMs) become central to modern software engineering, their inherent stochasticity poses significant real-world risks, where even minor errors can lead to severe functional, security, or safety consequences.

By Xiaoning Ren, Yinxing Xue, Lei Ma, Yuheng Huang

llms rag benchmarks safety

arXiv AI

Jun 19

Multi-LCB: Extending LiveCodeBench to Multiple Programming Languages

arXiv:2606. 20517v1 Announce Type: new Abstract: LiveCodeBench (LCB) has recently become a widely adopted benchmark for evaluating large language models (LLMs) on code-generation tasks.

By Maria Ivanova, Pavel Zadorozhny, Rodion Levichev, Ivan Petrov, Adamenko Pavel, Ivan Lopatin, Alexey Kutalev, Dmitrii Babaev

llms benchmarks

arXiv AI

Jun 10

Frontier Coding Agents Use Metaprogramming to Adapt to Unfamiliar Programming Languages

arXiv:2606. 10933v1 Announce Type: new Abstract: LLM-based coding agents are usually evaluated in familiar software settings: mainstream languages, common libraries, and public repositories.

By Aman Sharma, Sushrut Thorat, Paras Chopra

llms agents benchmarks

arXiv AI

Sep 24

Can LLMs Reason About Runtime Behavior? A Repository-Level Dynamic Benchmark

The paper introduces SWE-Flux, a repository‑level benchmark designed to test large language models’ ability to reason about runtime behavior. It contains 480 execution‑grounded instances from 12 real Python repositories, with gold answers automatically harvested from instrumented test executions. Evaluation of five LLMs shows the task remains difficult, with the best model achieving only 37% accuracy, and the benchmark can generate challenging variants through input perturbation.

By Hamed Taherkhani, Mohammad Abdollahi, Melika Sepidband, Hridya Dhulipala, Tien N. Nguyen, Hadi Hemmati

llms benchmarks

Related stories