arXiv Machine Learning July 14, 2026 By Adam \v{S}torek, Mukur Gupta, Samira Hajizadeh, Prashast Srivastava, Suman Jana

Sense and Sensitivity: Examining the Influence of Semantic Recall on Long Context Code Understanding

Read the original on arXiv Machine Learning →

arXiv:2505. 13353v5 Announce Type: replace-cross Abstract: Large language models (LLMs) are increasingly deployed for understanding large codebases, but whether they understand operational semantics of long code context or rely on pattern matching shortcuts remains unclear.

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

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...

By Matthieu Meeus, Anil Ramakrishna, Shengyuan Hu, Matthew Grange, Zheng Xu, Luca Melis

llms agents

arXiv Machine Learning

Sep 23

On the Lexical Superstition of Large Language Models for Code Comprehension: Re-evaluation on Code of Low Lexical Quality

arXiv:2609.26388v1 Announce Type: cross Abstract: Recent advances in large language models (LLMs) have made them widely used for code-related tasks. Identifier names are statistically informative in...

By Xin Shen (Nanjing University, Nanjing, China), San-Zhuo Xi (Nanjing University, Nanjing, China), Yali Du (Nanjing University, Nanjing, China), Ming Li (Nanjing University, Nanjing, China)

llms fine-tuning

arXiv AI

Sep 2

Adaptive Critical Token-Aware Retrieval for Repository-Level Code Generation

arXiv:2609.01601v1 Announce Type: cross Abstract: The repository-level code generation task requires synthesizing code that satisfies task requirements while remaining consistent with the target repo...

By Kefeng Duan, Dewu Zheng, Yanlin Wang, Terry Yue Zhuo, Mingwei Liu, Jianxing Yu, Jiachi Chen, Ensheng Shi, Xilin Liu, Yuchi Ma, Zibin Zheng

llms rag benchmarks

Hugging Face Trending Papers

Aug 5

OctoLong: Mid-Training On Cross-Repository Code Contexts Enhances Long-Context Modeling

Context lengths of language models (LMs) have dramatically increased, driven by the demands for in-context learning, self-improvement, and long-horizon agentic workflows. Existing long-context corpora, however, are dominated by books, academic articles, and code repositories, which are finite resources and often scarce in long-distance dependencies.

llms agents fine-tuning benchmarks

arXiv AI

Aug 6

OctoLong: Mid-Training On Cross-Repository Code Contexts Enhances Long-Context Modeling

arXiv:2608. 05141v1 Announce Type: new Abstract: Context lengths of language models (LMs) have dramatically increased, driven by the demands for in-context learning, self-improvement, and long-horizon agentic workflows.

By Indraneil Paul, Falko Helm, Goran Glava\v{s}, Iryna Gurevych

llms agents fine-tuning benchmarks

arXiv Machine Learning

Aug 31

Beyond Output Correctness: Benchmarking and Evaluating Large Language Model Reasoning in Coding Tasks

The paper introduces CodeRQ-Bench, the first benchmark for assessing large language model reasoning quality across coding tasks such as generation, summarization, and classification. It analyzes over a thousand mismatches from existing evaluators, identifies recurring limitations, and derives design insights that lead to a new two‑stage evaluator, VERA. Experiments show VERA outperforms strong baselines, improving AUCROC by up to 0.26 and AUPRC by up to 0.21 on four datasets.

By Yuangang Li, Justin Tian Jin Chen, Ethan Yu, David Hong, Iftekhar Ahmed

llms nlp benchmarks

One email a morning, machine-written

Related stories

Detecting Functional Memorization in Code Language Models

On the Lexical Superstition of Large Language Models for Code Comprehension: Re-evaluation on Code of Low Lexical Quality

Adaptive Critical Token-Aware Retrieval for Repository-Level Code Generation

OctoLong: Mid-Training On Cross-Repository Code Contexts Enhances Long-Context Modeling

OctoLong: Mid-Training On Cross-Repository Code Contexts Enhances Long-Context Modeling

Beyond Output Correctness: Benchmarking and Evaluating Large Language Model Reasoning in Coding Tasks