Code Language Models

Follow this topic Ask about this topic

Momentum

10 papers in the last four weeks, up 150% on the four weeks before. 0.1% of all new papers.

Jul 13Week of Sep 28

Latest papers 85

All topics

Obey, Diverge, Collapse: Blind Obedience to Incorrect Instructions Drives Code LLMs to Irrecoverable Code Semantic Collapse
Jul 5, 2026Raj Jaiswal, Anany Singh Divy, Savar Bhasin +3LLM Self-Correction Automated Program Repair
IIIT Delhi · Microsoft Research India · IIT Kanpur
Teaching Code LLMs to Reason with Intermediate Formal Specifications
Jul 5, 2026Minh Le-Anh, Cuong Chi Le, Tien N. NguyenFormal Verification Code Language Models
FPT Software AI Center Hanoi Univ. of Science and Tech. Hanoi, Vietnam · University of Texas at Dallas Texas, USA
Benchmarking Large Language Models on Floating-Point Error Classification
Jun 30, 2026Lisa Taldir, Muhammad Ahmad Saeed, David Defour +2LLM Evaluation Static Code Analysis
LI-PaRAD · Université de Perpignan via Domitia, Perpignan, France · Université Paris-Saclay, UVSQ, France +1
SrDetection: A Self-Referential Framework for Data Leakage Detection in Code Large Language Models
Jun 29, 2026Shuaimin Li, Liyang Fan, Zeyang Li +9LLM Evaluation LLM Auditing
Shenzhen Key Laboratory for High Performance Data Mining, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences · Shenzhen University · Artificial Intelligence Research Institute, Shenzhen University of Advanced Technology +5
When AI Reviews Its Own Code: Recursive Self-Training Collapse in Code LLMs
Jun 26, 2026Xinyuan Song, Zekun Cai, Liang ZhaoSelf-Training Model Collapse
Emory University, Atlanta, GA, USA · The University of Tokyo, Tokyo, Japan · LocationMind, Tokyo, Japan
Weave of Formal Thought
Jun 24, 2026Alexandre BouayadCode Language Models LLM Code Generation
Recall Before Rerank: Benchmarking Deep Learning Models for Large-Scale Code-to-Code Retrieval
Jun 24, 2026Leonardo Venuta, Francesco Tosoni, Paolo FerraginaLLM Evaluation Semantic Search
Sant’Anna School of Advanced Studies, Pisa, Italy
Dream at SemEval-2026 Task 13: SALSA for Single-Pass Machine-Generated Code Detection
Jun 23, 2026Ruslan Berdichevsky, Shai Nahum-Gefen, Elad Ben-ZakenOOD Generalization Code Language Models
Dream Security Ltd. Tel Aviv, Israel
From Brewing to Resolution: Tracing the Internal Lifecycle of Code Reasoning in LLMs
Jun 16, 2026Siyue Chen, Yifu Guo, Yuquan Lu +9LLM Interpretability Code Language Models
1South China University of Technology · 2Sun Yat-sen University · 4Shanghai Jiao Tong University +5
Beyond Correctness: Enhancing Architectural Reasoning in Code LLMs via Scalable Labeling with Agentic Judgment
Jun 12, 2026Kirill Vasilevski, Ximing Dong, Benjamin Rombaut +8Software Engineering Agents LLM-as-a-Judge
Justina · Centre for Software Excellence, Huawei Canada · School of Computing, Queen’s University, Canada +1
Code Correctness Is Linearly Decodable from LLM Hidden States Before Generation
Jun 12, 2026Carlo Di CiccoCode Language Models LLM Code Generation
Independent researcher.
Detecting Functional Memorization in Code Language Models
Jun 11, 2026Matthieu Meeus, Anil Ramakrishna, Matthew Grange +2Memorization in Language Models LLM Auditing
Meta · Imperial College London
CODEBLOCK: Learning to Supervise Code at the Right Granularity
Jun 10, 2026Zhijie Deng, Ling Li, Jinlong Pang +5Supervised Fine-Tuning Code Language Models
Hong Kong University of Science and Technology (Guangzhou) · UC Santa Cruz · Ant Group +1
CodeAlchemy: Synthetic Code Rewriting at Scale
Jun 8, 2026Ankit Gupta, Aditya Prasad, Rameswar PandaSynthetic Data Pretraining Synthetic Data Generation
MIT-IBM Watson AI Lab, IBM Research
Code Is More Than Text: Uncertainty Estimation for Code Generation
Jun 8, 2026Yuling Shi, Caiqi Zhang, Yuexian Li +4Confidence Estimation in Language Models LLM Reliability
Shanghai Jiao Tong University · University of Cambridge
Beyond Pass Rate: A Multilingual, Execution-Grounded Evaluation of Open Code LLMs
Jun 7, 2026Sayed Erfan ArefinCode Generation Evaluation Code Language Models
Department of Computer Science University of Dayton Dayton, OH 45469, USA
Lost in the Flow with Code Talkers: Unveiling the Instruction-Tuning Tax of Large Language Models in Code Tasks
Jun 7, 2026Shi Ying Chang, Chiok Yew Ho, Yichen Li +1Instruction Tuning Code Generation Evaluation
The Chinese University of Hong Kong, China
Code2LoRA: Hypernetwork-Generated Adapters for Code Language Models under Software Evolution
Jun 4, 2026Liliana Hotsko, Yinxi Li, Yuntian Deng +1Software Engineering LLM Fine-Tuning
University of Waterloo
NovelAPIBench: Diagnosing How A Code LLM Learns to Use Novel APIs
Jun 2, 2026Jinnuo Liu, Yue Peng, Jinhan Niu +1Knowledge Augmentation for Language Models LLM Fine-Tuning
NYU Shanghai
Code as a Weapon: A Consensus-Labeled Prompt Bank for Measuring Coding-Model Compliance with Malicious-Code Requests
May 27, 2026Richard J. Young, Gregory D. MoodyClassification LLM Safety Evaluation
University of Nevada Las Vegas · Department of Information Systems · Las Vegas, NV, USA
Poison with Style: A Practical Poisoning Attack on Code Large Language Models
May 26, 2026Khang Tran, Yazan Boshmaf, Issa Khalil +3LLM Backdoor Attacks Data Poisoning Attacks
Department of Data Science, New Jersey Institute of Technology, New Jersey, U.S.A. · Qatar Computing Research Institute, HBKU, Doha, Qatar · Mohamed Bin Zayed University of Artificial Intelligence, Abu Dhabi, United Arab Emirates
Merge-Bench: Resolve Merge Conflicts with Large Language Models
May 25, 2026Benedikt Schesch, Michael D. ErnstSoftware Engineering Code Language Models
Amazon · University of Washington, USA
CSP-Atlas: Concept-Specific Neural Circuits in a Sparse Python Transformer
May 23, 2026Piotr WilamTransformer Interpretability Circuit Discovery
University College London
TRACER: A Semantic-Aware Framework for Fine-Grained Contamination Detection in Code LLMs
May 22, 2026Yifeng Di, Xuliang Huang, Tianyi ZhangLLM Auditing Data Contamination in Language Models
Purdue University West Lafayette, IN · University of Illinois Urbana-Champaign Champaign, IL
Echo: Learning from Experience Data via User-Driven Refinement
May 21, 2026Hande Dong, Xiaoyun Liang, Jiarui Yu +15Continual Learning for LLM Agents LLM Agent Self-Improvement
Tencent, CodeBuddy
The Range Shrinks, the Threat Remains: Re-evaluating LLM Package Hallucinations on the 2026 Frontier-Model Cohort
May 16, 2026Aleksandr ChurilovLLM Evaluation Hallucination in Language Models
Independent Researcher
Syntax Without Semantics: Teaching Large Language Models to Code in an Unseen Language
May 15, 2026Vinayshekhar Bannihatti Kumar, Disha Makhija, Manoj Ghuhan Arivazhagan +1LLM Fine-Tuning Code Language Models
AWS AI Labs
Correctness-Aware Repository Filtering Under Maximum Effective Context Window Constraints
May 14, 2026Shweta MishraLLM Context Management Code Language Models
Independent Researcher
Code-Centric Detection of Vulnerability-Fixing Commits: A Unified Benchmark and Empirical Study
May 13, 2026Nils Loose, Joseph Bienhüls, Kristoffer Hempel +2Software Vulnerability Detection Software Engineering Benchmarks
University of Lübeck Institute for IT Security Lübeck, Germany
SemChunk-C: Semantic Segmentation for C Code
May 12, 2026Boris Nazarov, Darya Frolova, Shaked Leibzirer +1Small Language Models Code Language Models

Jul 5, 2026, cs.SEJ/K move · Enter open · S save

Obey, Diverge, Collapse: Blind Obedience to Incorrect Instructions Drives Code LLMs to Irrecoverable Code Semantic Collapse

Raj Jaiswal, Anany Singh Divy, Savar Bhasin, Adi Bajpai+2

IIIT Delhi · Microsoft Research India · IIT Kanpur

LLM Self-Correction Automated Program Repair Language Model Robustness Code Language Models

Open paper AskPDF arXiv

Code language models are now trusted collaborators in production workflows for debugging, refactoring, and iterative repair, and every benchmark that evaluates them assumes the instructions they act on are correct. We study what happens when that assumption breaks. We evaluate code language models across four experiments designed to assess whether models resist or obey incorrect instructions in single-pass and iterative repair settings, using the RunBugRun dataset of algorithmic Python problems with deterministic test cases. Our findings reveal a striking behavioral pattern: models correctly identify an incorrect instruction as wrong, then follow it anyway. This compliance unknowingly introduces errors beyond the original bug, and the corrupted code state cannot be recovered through subsequent self-guided iterative repair, which fails to converge across passes. We term this Blind Obedience, characterize the Ghost (Unknown) Errors it introduces, quantify the proportion of cases where semantic corruption proves irrecoverable, and show that extended reasoning cannot reverse it. These findings surface behavioral properties invisible to pass-rate evaluation, with direct consequences for code language models deployed in production settings.

Momentum

Related topics

Latest papers 85