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.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.

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 AI

Jun 3

Diagnosing Knowledge Gaps in LLM Tool Use: An Agentic Benchmark for Novel API Acquisition

arXiv:2606. 03657v1 Announce Type: new Abstract: Large language models for code generation often need to use APIs that are absent from their pretraining data.

By Jinnuo Liu, Yue Peng, Jinhan Niu, Hongyi Wen

llms agents 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 3

TokenScope: Token-Level Explainability and Interpretability for Code-Oriented Tasks in Large Language Models

arXiv:2607. 01235v1 Announce Type: cross Abstract: Understanding how Large Language Models (LLMs) make token-level decisions during code generation remains a major challenge for both researchers and practitioners.

By Amirreza Esmaeili, Fatemeh Fard

llms safety

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

Related stories

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

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

Diagnosing Knowledge Gaps in LLM Tool Use: An Agentic Benchmark for Novel API Acquisition

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

TokenScope: Token-Level Explainability and Interpretability for Code-Oriented Tasks in Large Language Models

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