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

Oct 4, 2026cs.SE

Mind the Gaps: From Failure Attribution to Closed-Form Repair of Code Language Models

Code language models must be maintained like the software around them: when a library evolves, a model keeps writing the interface that it saw during training. Repairing the model itself lets one correction reach all downstream uses. Existing repair methods attribute a failure to neurons, select the highest-ranked ones, and apply a generic update. This pipeline assumes that the attributed neurons are the ones to patch and that a generic update fits every failure, and neither assumption has been examined. We examine both on executable API evolution tasks in Python and Rust with three code models and identify two gaps. The targeting gap separates the neurons that failure attribution targets from the neurons that can carry a patch: their top sets have a Jaccard overlap of only 0.15 to 0.20. The tailoring gap separates a generic update from a patch built for the failure: the patches that different carrier neurons need are nearly orthogonal. To address both gaps, we propose ASTRA. It targets neurons by contrastive semantics, an attribution that scores a neuron by its contribution to the logit contrast between the target token and the produced token. It then tailors the patch by solving one small linear system in closed form, which corrects all failing tokens of a sample jointly and needs neither an optimizer nor a backward pass. Contrastive semantics selects significantly better carrier neurons than gradient-based attributions in 3 of 6 settings and comparable ones in the others. On average, ASTRA reaches 66.7 percent Pass@1, against 48.4 percent for the best of AlphaEdit, STAR and low-rank adaptation, and repairs a sample in 2.7 seconds. It is the best method in all 6 settings and for every type of API change, and this advantage persists under an unseen phrasing of the test prompt. Its side effects on unrelated code are small on the large models and larger on the small one.

Jian Gu, Hongyu Zhang, Chunyang Chen +1

Monash University, Australia · Chongqing University, China · Technical University of Munich, Germany

Causal Interventions in Language Models Code Language Models

Oct 4, 2026cs.LG

Hidden in the Comments: A Context-Injection Attack Surface in Code LLMs

Code large language model (Code LLM) assistants generate code from heterogeneous development contexts, including open files, imported modules, pasted snippets, and comments, much of which may originate from untrusted sources. We investigate whether insecure instructions embedded in such contexts can steer Code LLMs toward vulnerable code without access to model weights or training data. We evaluate ten open-weight Code LLMs spanning 3B--13B parameters, including four base and six instruction-tuned models, across ten web-application weakness classes. We compare completion tasks containing insecure instructions embedded as code comments with benign tasks without malicious instructions. Attack-condition completions contained a medium-or-higher weakness in {\bf 77.4--92.3}% of cases, compared with {\bf 1.7--5.1}% in the benign condition. Base and instruction-tuned models averaged 86.5% and 84.5% vulnerable outputs, respectively; equivalence testing and three matched model pairs indicated reductions of at most 8.1% after instruction tuning. Susceptibility showed no clear association with model scale or specialization. Among vulnerable attack outputs, 86.2--91.0% were rated high or critical, and the effect persisted without the pattern-based detector. Post-generation screening reduced but did not eliminate the risk, the strongest screen leaving roughly one-third undetected. These findings identify inference-time context injection as a substantial attack surface and motivate provenance-aware training objectives.

Noor Munir, Francesco Quinzan, Stephen Roberts

Department of Engineering Science, University of Oxford, Oxford OX1 3PJ, UK

LLM Security Indirect Prompt Injection Prompt Injection Attacks Code Language Models LLM Code Generation

Sep 29, 2026cs.SE

Complexity-Aware Evaluation of LLM Comprehension

Large language models (LLMs) are increasingly used for software engineering tasks that require understanding existing source code, including behavior prediction, function explanation, debugging, and code review. However, aggregate benchmark accuracy can conceal how model reliability changes as source code becomes structurally more complex. This paper presents a complexity-aware framework for evaluating LLM code comprehension using cyclomatic complexity, nesting depth, branching factor, and Halstead volume. We evaluate DeepSeek-Coder-V2 and Llama through two complementary tasks: automatic input-output prediction over 300 Python functions and manually assessed semantic comprehension over a balanced subset of 60 functions. The functions are grouped into Low-, Medium-, and High-complexity bands. DeepSeek-Coder-V2 achieves an overall automatic accuracy of 78.33%, compared with 70.33% for Llama. However, accuracy decreases substantially from Low to High complexity, from 93.52% to 52.78% for DeepSeek-Coder-V2 and from 87.04% to 47.22% for Llama. Incorrect predictions are consistently associated with higher values of all four complexity metrics, and correlation and logistic-regression analyses confirm broadly comparable negative associations between structural complexity and correctness. Manual semantic comprehension shows the same degradation pattern, with accuracy decreasing from 100.00% to 75.00% for DeepSeek-Coder-V2 and from 90.00% to 60.00% for Llama. These findings demonstrate that complexity-aware evaluation provides a more diagnostic assessment of LLM code-comprehension reliability than aggregate accuracy alone.

Ali Mohammadi Esfahani, Nafiseh Kahani, Samuel A. Ajila

Systems and computer Engineering Carleton University Ottawa, Canada

Software Engineering LLM Evaluation LLM Reliability Code Language Models

Sep 28, 2026cs.SE

UNBIND: UNlearning By INference-time Directional Steering for Code LLMs

Code large language models acquire programming capabilities from large code corpora, but can also memorize implementations that later require removal. Code unlearning is needed to control their continued reproduction when copyright or security concerns arise. However, targeted and retained code share computational patterns, creating a tension between forgetting specific implementations and preserving general programming ability. We propose \textbf{UNBIND}, a code unlearning framework that separately considers which hidden states correspond to the target code and how to suppress its reproduction. By constructing separate directions for these objectives, UNBIND achieves selective unlearning at inference time while keeping model weights fixed. Our evaluation covers fourteen baselines across two code models and two corpora. UNBIND achieves the highest joint forgetting and utility score in every setting. It reduces target code reproduction by 97.3% to 99.1% as measured by F-BLEU, with at most two fewer HumanEval+ and six fewer MBPP+ problems solved than the original models. In repeated extraction tests under a fixed budget, the number of targets yielding exact spans of at least 50 tokens falls from 188--262 to 0--2 out of 300 per setting. No extracted span reaches 100 tokens, and the mean best recovery ratio ranges from 0.43% to 6.45%. Multilingual and related-code evaluations further show effective forgetting with limited impact on useful programming capabilities, supporting UNBIND as a practical approach to selective code unlearning.

Zhengyang Shan, Jiayun Xin, Yanjun Lin +7

Department of Computer Science and Technology Shandong University Qingdao, China

Activation Steering LLM Unlearning Code Language Models

Sep 24, 2026cs.AI

Style, Not Self: Surface Cues Explain Zero-Shot Code Attribution by Large Language Models

If a language model can recognize code it wrote, it may favor that code as a judge, and instances of one model monitoring each other could collude. We test this zero-shot on current commercial models. Five LLMs generate solutions to MBPP, HumanEval, and DS-1000, seven more to MBPP, and models act as evaluators in four tasks: picking their own solution from a pair, judging whether a single solution is their own, identifying which of two solutions a named model wrote, and judging quality blind. In the single-solution task, balanced accuracy is 49-58% for all 15 model-benchmark combinations, while raw accuracy (38-67%) mostly reflects how readily a model claims authorship. In the pairwise task, accuracy across 14 evaluator-opponent combinations correlates at r=0.93 with how often the evaluator's solution is longer. Attribution to a named model succeeds on some pairs and is consistently inverted on others. A rule-based normalization that strips docstrings, comments, type hints, and local names preserves Pass@1 and leaves ten of twelve re-tested results at chance; the other two follow a length difference it leaves, although a trained classifier still separates most normalized pairs. Claude Haiku's self-preference also disappears. We recommend reporting balanced accuracy, heuristic baselines, and label consistency.

Ehsan Barkhordar, Surendrabikram Thapa

Koç University · Virginia Tech

LLM Evaluation Language Model Generation Evaluation Language Model Fingerprinting Language Model Self-Assessment Authorship Attribution Code Language Models

Sep 22, 2026cs.SE

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

Recent advances in large language models (LLMs) have made them widely used for code-related tasks. Identifier names are statistically informative in naturally occurring code, but their information is not always reliable. We investigate whether current LLMs assign disproportionate weight to lexical cues when renaming preserves program structure. We introduce Face/Off, a semantics-preserving identifier-renaming framework, and evaluate progressive naming conditions across multiple models and code-comprehension tasks. Within this framework, lexical overemphasis is pervasive across the evaluated models and primary tasks: performance generally decreases as identifier information is removed or made misleading, and outputs are often directed toward the meanings suggested by misleading names. The pattern persists under representative prompt- and fine-tuning-based interventions, suggesting that lexical overemphasis is an entrenched problem. A type-inference control confirms a boundary: naming effects are smaller when the answer is locally recoverable without the target name. These results do not imply that identifiers are unhelpful; rather, they reveal a systematic vulnerability in how current LLMs balance lexical cues against program structure. Our findings motivate evaluations and modeling methods that preserve the benefits of natural code regularities while keeping conclusions grounded in accurate, formalized code semantics.

Xin Shen, San-Zhuo Xi, Yali Du +1

Nanjing University, Nanjing, China

Language Model Robustness Code Language Models

Sep 16, 2026cs.SE

An Empirical Evaluation of Cost-Efficient Large Language Models on Algorithmic Programming Tasks

This study empirically evaluates whether cost-efficient Large Language Models (LLMs) can be trusted to generate enterprise code to a written specification. Three models (Gemini Flash 3, GPT-5.4 mini and Claude Haiku 4.5) were asked to solve 992 algorithmic problems as Java Spring Boot service methods conforming to a mandated signature and data-transfer-object specification, crossing four model and agentic coding tool combinations with two prompt variants to yield eight configurations, with iteration forbidden and hardcoded answers explicitly prohibited. Eight problem statements were withheld to probe how models respond to missing input. The 7,593 resulting methods were classified by an eight-class outcome taxonomy describing what each does about producing an answer, then deployed and executed, giving 7,936 measured requests joined to that classification. Structural conformance approached ceiling, yet 38.4% of methods do not compute the value they returned and only 12.9% of returned answers were correct. Conditioning on outcome class shows that response reliability and correctness are inversely related, whereas genuinely computing methods answered least often and were correct 19.3%. Limitations include single generation runs per configuration, partial harness coverage, single-pass timing, syntactic classification, and probable corpus contamination.

Chandimal Adikari, Nandika Herath

Faculty of Engineering and Information Sciences University of Wollongong Wollongong, Australia · Faculty of Engineering, Computing and Science Western Sydney University Parramatta, Australia

Code Generation LLM Reliability Code Generation Evaluation Code Language Models

Sep 14, 2026cs.SE

Retrieval-Augmented Generation for Scientific Code Understanding

Large language models have become central to modern coding assistants, but state-of-the-art systems such as Claude Code or Codex rely on very large, cloud-hosted models with significant computational cost and data-privacy implications. This work investigates whether a useful, fully local coding agent can be built around small open-source models by shifting the computational burden away from inference. We develop a Retrieval-Augmented Generation (RAG) system for scientific code understanding that strictly separates an expensive offline ingestion stage parsing, structural graph construction, LLM-generated entity explanations, and embedding from a lightweight online answering stage. The system is evaluated on a 100-question benchmark spanning eleven categories over the IPPL scientific codebase written in C++, with answers scored by an independent frontier model as the judge. Across seven answering models, we find that model family and retrieval quality matter more than parameter count, i.e. a 9B model achieves the highest average score (0.795), outperforming both larger models within our pipeline and the same models embedded in the Claude Code retrieval architecture. The results indicate that front-loading code understanding into a reusable, codebase-specialised vector store enables small local models to deliver grounded and repository-specific answers, making the agent well suited as a privacy-preserving development tool for in-house scientific codebases.

Aaron Nobile, Andreas Adelmann, Mohsen Sadr

Department of Physics, ETH Zürich, 8093 Zürich, Switzerland · Paul Scherrer Institute, 5232 Villigen PSI, Switzerland · Massachusetts Institute of Technology, Cambridge, MA 02139, USA

Retrieval-Augmented Generation LLM Grounding Code Language Models

Sep 10, 2026cs.SE

The Vibe Shift in Software Engineering: Evaluating AI-Led Conversational Programming for Performance, Cognition, and Responsible Adoption

This study evaluates Vibe Coding, an emerging AI-led conversational programming paradigm that enables developers to generate software through natural-language interaction with large language models. Using a mixed-methods design, the study assessed performance efficiency, cognitive implications, and responsible adoption in comparison with traditional and AI-assisted coding environments. Thirty participants, including professional developers and advanced computing students, completed equivalent programming tasks under three experimental conditions. Quantitative data were analyzed using descriptive statistics and repeated-measures ANOVA, while qualitative data were examined through thematic analysis. Results show that vibe coding significantly improved development efficiency, reducing task completion time by 27% compared with traditional coding and 12% compared with AI-assisted coding. However, these gains were accompanied by lower maintainability indices and higher security vulnerabilities, indicating trade-offs in software quality. Usability results yielded a good rating (SUS = 71.4), while cognitive workload remained moderate (NASA-TLX = 55.5), reflecting reduced syntactic effort but increased linguistic reasoning. Thematic analysis identified trust calibration, loss of control, cognitive adaptation, and prompt-engineering strategy as key constructs. Notably, perceived loss of control was associated with increased security risks due to reduced transparency and validation of AI-generated outputs. Based on these findings, the study proposes a three-pillar framework for responsible adoption: hybrid integration of human and AI capabilities, human oversight and transparent accountability, and context-aware deployment. Overall, vibe coding enhances productivity but requires critical oversight, reinforcing its role as a transformative yet transitional paradigm in software development.

Sales G. Aribe Jr., Louie Jay S. Labastida

Information Technology Department, Bukidnon State University, Malaybalay City, Philippines

Code Generation Evaluation Human-AI Collaboration Code Language Models Responsible AI AI-Assisted Software Development

Sep 7, 2026cs.SE

CodeTD: Topology of Attention Detects Hallucinations in Code LLMs

As AI-code assistant tools become widespread, automatic assessment of the correctness of generated code becomes a significant challenge. Code LLMs are prone to hallucinations, which may lead to code that does not solve the required problem, or even to code with severe security vulnerabilities. In this paper, we introduce CodeTD -- the first approach to pre-execution assessment of code correctness based on topological data analysis (TDA) of Code LLMs' attention maps. Our method quantifies prompt-generation mismatch using topological patterns of attention maps. We carry out experiments with common benchmarks (HumanEval, MBPP, BigCodeBench, MultiPL-E), 5 programming languages and 10 Code LLMs of size up to 34B parameters. The experimental results show that the proposed method outperforms recent baselines. Moreover, CodeTD is transferable between coding benchmarks.

Daria Voronkova, Ilya Trofimov, Anton Dmitriev +3

Applied AI Institute · AXXX · IMJ CNRS

LLM Hallucination Detection Code Generation Evaluation Code Language Models

Sep 3, 2026cs.CL

CROCODIL: Cross-Model Code Editing with LLMs

Large language models (LLMs) have become ubiquitous tools for code generation and editing. However, development teams often use multiple LLM assistants. Different developers may prefer different models, and individual developers may switch between models across different coding sessions. Because of this, the edits any one model makes are frequently applied to foreign code originally generated by another model. These LLMs are often trained on different datasets, and as a result have different stylistic preferences. Do LLMs behave differently when they edit foreign code originally written by a different LLM with a different coding style? We find that models tend to make more, and often excessive, edits on foreign code. We introduce CROCODIL (Cross-model Code Editing with LLMs), a post-training framework for reducing excessive edits while preserving functional correctness. CROCODIL's similarity reward penalizes large changes, while its execution reward scores build and test success. We use the product of these two rewards to encourage the policy to decrease the edit size without decreasing the edit task success rate. CROCODIL is available at https://github.com/EngineeringSoftware/Crocodil.

Linghan Zhong, Aditya Thimmaiah, Jayanth Srinivasa +2

1The University of Texas at Austin · 2Cisco Research

Reinforcement Learning LLM Post-Training Code Language Models

Sep 1, 2026cs.SE

Hints Help But Do They Teach? Evaluating Skills Transfer in Code Generation

When a hint turns a failing generated program into a passing one, does it provide missing information or merely steer the model toward a solution it could already produce? We test these hypotheses on HumanEval+ and MBPP+ using executable evaluation. For Qwen2.5-3B-Instruct, adaptive relevant hints rescue 36 of 79 selected failures; an unrelated hint rescues 19, while eight unhinted samples solve 46 and recover 31 of the 36 relevant-hint rescues. Phi-3.5-mini shows the same pattern: relevant hints rescue 42 of 101 failures, an unrelated hint rescues 17, and unhinted sampling solves 57, including 36 of the 42 relevant-hint rescues. Because the hint conditions use different attempt budgets, these comparisons do not isolate a purely semantic effect. Mechanistic tests on Qwen identify a stable activation direction shared by relevant and unrelated hints. Persistently adding this direction yields 14 rescues and 18 regressions, with no detectable net accuracy gain; learned low-rank interventions have a positive but imprecise estimated effect. Full textual specifications solve 22 of 24 context-defined problems, versus 5-11 for tested virtual-KV prefixes. Post-generation hidden-state probes transfer across benchmarks, with pooled AUROC 0.806 and 0.780, but their top-one selection advantage over token confidence is statistically unresolved. Overall, relevant hints can rescue failures, but most rescued solutions are already reachable through ordinary sampling, and the internal interventions tested here do not establish task-general capability transfer.

Will Badr

Language Model Generation Evaluation LLM Prompting Code Generation Evaluation Causal Interventions in Language Models Code Language Models

Sep 1, 2026cs.PL

Predicting Program Exit Code with LLMs and Programming Language Semantics

Large language models (LLMs) have shown proficiency in various software engineering tasks, such as code generation and translation. However, a key limitation in their performance may be their (lack of) understanding of programming-language semantics. Even when explicit semantics are given, it remains unclear whether LLMs apply those rules or lean on priors learned during pre-training instead. We study if LLMs lean on priors or given semantics with a novel task--Program Executability Prediction (PrEx)--that asks models to predict whether a program is semantically valid or invalid (and, if invalid, which formal rule it violates) given the program's syntax and operational semantics. Because PrEx requires both valid and invalid programs, we build a dataset with systematically generated invalid transformations derived from valid programs. We evaluate open-source coding LLMs under two semantic formalisms and two semantic shifts across Human-Written, LLM-Translated, and Fuzzer-Generated program splits. Our findings show that LLMs lean on pre-training priors rather than systematically applying the given rules, performing especially poorly on modified semantics and degrading further as program complexity increases. PrEx is available at https://github.com/EngineeringSoftware/prex.

Lara Marinov, Aditya Thimmaiah, Jayanth Srinivasa +2

The University of Texas at Austin · Cisco Research

LLM Evaluation Code Language Models

Aug 13, 2026cs.SE

Memorization Diagnostics for Code LLMs Should be Scale-Aware

The extent to which large language models for code rely on memorization over genuine understanding remains highly debated. While current literature frequently reports widespread memorization, evaluating the underlying probing techniques across dense architectures reveals a severe breakdown in their utility at scale. Traditional encoder-style probes using perturbations such as synonym fuzzing or dead-code insertion struggle to expose memorization in scaled models, even on known-contaminated benchmarks, and decoder-style probes that rely on log probabilities show similar performance degradation. The specific mode of failure for these probes, particularly why such techniques disrupt smaller models but fail to impact larger ones, motivates us to untangle representation load from memorization rather than treating them as a single phenomenon. By applying invertible mathematical transforms to numeric problems, we isolate these two factors and reveal that scaled encoders successfully absorb substantial representation load while still converging on the correct family of solutions. In practical software engineering, this ability to adapt to varying surface forms is what truly matters for usability and generalizability in LLM and agentic applications. Whether a specific solution was seen during training becomes a much less pressing question because although memorization inflates scores on contaminated benchmarks, factoring out representation load makes it debatable how much we should truly care if a functional answer was originally memorized. Future evaluations must therefore be built around separating these phenomena rather than relying on methodologies that quietly entangle them.

Prateek Kumar Rajput, Abdoul Aziz Bonkoungou, Alberick Euraste Djiré +6

University of Luxembourg, Esch-sur-Alzette, Luxembourg.

Memorization in Language Models Code Language Models Language Model Probing

Aug 8, 2026cs.SE

On the Robustness of LLMs' Internal Representation of Code Correctness

Code generated by modern language models often reads naturally. Yet, it also often fails to implement what was asked. This should be no surprise, as research shows the models' own confidence signals are poorly calibrated with actual correctness. A promising way to assess correctness looks inside the model: by contrasting the hidden states of correct and incorrect programs, recent work captured an internal signal of code correctness that is able to judge candidate solutions better than the model's token-level or stated confidence, with no test execution. However, this signal was captured under one particular way, leaving open an important question: whether it reflects a robust property of the model or an artifact of that choice. We study this question systematically, varying how the signal is extracted from the model internals. Besides this, we also ask if the signal's quality is limited by the data used to extract it, by constructing program pairs that differ only in the fault that makes them incorrect. Our results show that no single configuration is best, and that isolating the fault does not help.

Francisco Ribeiro, Sohaila Abdulsattar, Renata Gonzalez +2

New York University Abu Dhabi Abu Dhabi, United Arab Emirates

LLM Reliability Language Model Robustness Code Language Models Language Model Probing

Aug 6, 2026cs.SE

LangChoiceBench: Measuring and Explaining Programming-Language Choice in LLMs

Large language models (LLMs) have been shown to exhibit strong Python preferences when generating project-level code, but there is currently no systematic way to measure this behaviour across new models. To bridge this gap, we introduce LangChoiceBench, a project-level code-generation benchmark for measuring Python preference, recommendation-implementation consistency, and language diversity. LangChoiceBench covers 28 projects across seven software areas where Python is often a poor default. We evaluate 25 diverse LLMs and find that Python remains heavily over-selected, recommendation-implementation consistency is low, and smaller open-weight models generally show stronger Python preference and lower language diversity. We further analyse 9,826 reasoning traces and find that most Python choices are automatic or driven primarily by ease, rather than explicit consideration of project requirements. In a smaller but important set of cases, models fabricate contextual support for choosing Python - a failure mode we call phantom evidence - or produce code that contradicts the language selected in their own reasoning.

Lukas Twist, Twm Stone, Helen Yannakoudakis +1

King’s College London, London, UK · MATS Research

LLM Evaluation Language Model Bias Evaluation Code Language Models LLM Code Generation

Aug 5, 2026cs.AI

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. In this work, we introduce OctoLong, a context engineering pipeline that instruments an AST parser, a language server backend, and a package manager to facilitate the recursive retrieval of code references, enabling the curation of dependency-rich code contexts of millions of tokens in length. We then train OctoLong-Instruct, a suite of capable long-context open LMs, derived from base models ranging in size from 600M to 14B parameters, via context-extension mid-training on a ~50B-token mixture containing ~6.2B tokens of OctoLong code contexts, followed by ~10B tokens of instruction tuning. Our training ablations and experimental evaluations against 18 state-of-the-art open-weight long-context LMs show that supplanting just 12% of traditional context-extension corpora with OctoLong data yields substantial gains in long-range retrieval, long-term state tracking, repository-level code understanding, and downstream agentic tasks, while also enhancing API usage in short-context coding scenarios.

Indraneil Paul, Falko Helm, Goran Glavaš +1

UKP Lab & Center for Applied Cybersecurity ATHENE, TU Darmstadt · CAIDAS, University of Würzburg

Software Engineering Long-Context Language Modeling Continued Pretraining Code Language Models LLM Training

Jul 30, 2026cs.SE

To Add Is Machine, To Delete Is Human: Measuring and Mitigating Deletion Avoidance in LLM Code Editing

Large language models increasingly write and repair production code, yet evidence is mounting that their test-passing patches leave codebases harder to maintain. We identify one concrete source: deletion avoidance, the systematic tendency to retain code that an intended edit requires removing. Across the five leading models on the official SWE-bench Verified leaderboard, deletion recall against the developer patch reaches at most 71.7% even on tasks all five solve, and models reach the right file for over 92% of required deletions but cut the exact line in under 52% of cases. Instead, 29.0% of passing patches wrap the targeted code in a guard or fallback, a pattern we call Guard-and-Go. Such patches pass because the original tests rarely check removal: when we retrofit 34 Verified tasks with tests that fail if the targeted code remains, four frontier models spanning closed and open weights fall from 63.2% to 41.9%. Because real repairs mix removal with addition, we curate CanItDelete, a benchmark of 200 tasks mined from real commits whose entire required edit is deletion. Even with the addition work gone, the best model still fails one task in five, and smaller open models fall to 18.0%. We then ablate GPT-5.6 Sol under four cumulative prompts; success moves little until we supply the exact lines, which nearly eliminate incomplete deletion yet raise success only to 80.5% because the model then deletes beyond the spans or adds code instead. Finally, through a pilot study we show one potential fix: teaching deletion during post-training reduces deletion avoidance and improves broader code-editing performance, suggesting the behavior is undertrained rather than beyond reach.

Amir M. Ebrahimi, Mohammed Mehedi Hasan, Aaditya Bhatia +2

School of Computing, Queen’s University, Kingston, Ontario, Canada

LLM Reliability Language Model Editing Code Language Models

Jul 27, 2026cs.SE

Learning from 53.6K Real-World Developer Edits of AI-Generated Code

Imperfections in AI-generated code require that software developers modify the generated code manually, or by re-prompting an AI programming assistant. Manual code edits provide more realistic and granular information on editing behavior than Git commits, which only contain final successful code snippets. Yet, due to a lack of high-quality, realistic code editing data, LLMs are mostly trained on publicly available Git data (e.g., commits). To address this gap, we introduce DECODE (Developer Edits of Code Dataset), a dataset of 53.6K real-world in-IDE code edits of AI-generated code in Python, TypeScript, and JavaScript, sourced from 1K+ developers. First, we demonstrate the utility of DECODE for data analysis, obtaining insights on when, why, and how AI-generated code is edited. We find that most edits occur within the first 15 minutes after accepting an AI completion, resulting in the removal of AI completions in 31% of edit trajectories. Second, we use DECODE to benchmark the ability of LLMs to predict code edits. We find that finetuning on DECODE enables open-source 3B models to perform code edit prediction tasks significantly better than frontier LLMs. We then discuss implications of this work, emphasizing the necessity of developer-centric machine learning approaches for future AI programming assistants.

Jenny T. Liang, Mihika Bairathi, Wayne Chi +3

Carnegie Mellon University

Code Generation Evaluation Code Language Models AI-Assisted Software Development

Jul 25, 2026cs.LG

Wrong Design Intent Is Worse Than Never Conditioning: A Derangement-Control Diagnosis of Header Conditioning in CAD Program Completion

Fine-tuned code LLMs are routinely conditioned on a design-intent specification, but the correctness axis of such a signal -- a wrong intent rather than an absent one -- has not been tested, and the benefit of conditioning is usually scored with the same detector that defines the signal. We study CADCON, a five-feature design-intent header prepended to CadQuery-style programs during LoRA fine-tuning of Qwen2.5-Coder-1.5B, scoring adherence with executable geometric assertions that share no code with the header-defining extractor. On a pre-registered sample of 400 deduplicated held-out programs stratified over eleven intent profiles, at 40% prefix and three seeds, a semantically wrong header degrades adherence below the never-header-trained baseline on 3/3 seeds under both tokenizations at the program level, and on 3/3 token and 2/3 text seeds at the 298 distinct model inputs they present. Wrong-header executability is not depressed relative to that baseline. A derangement control, retrained so every program receives another program's header -- holding the header marginal fixed while destroying its correlation with the program -- saw the same programs, indices and wrong headers. Its correct-to-wrong change is -0.006/+0.016/-0.003 against 0.124/0.241/0.230 for the standard model, and the interaction is significant on 3/3 seeds (p <= 5.9e-7), so the model's sensitivity to whether the header is right or wrong requires the learned mapping. The control sits below the baseline by the same margin under a correct as under a wrong header, so we claim that sensitivity and not the below-baseline level. On features the true intent lacks, the standard model realizes a feature far more often when the wrong header names it; the control does not. Ground truth itself scores only 0.567 here, the scale on which arm levels should be read. Wrong design intent is not inert: it actively misdirects generation.

Yang Xiao

Sichuan University

Code Generation LLM-Based Program Synthesis Causal Interventions in Language Models Code Language Models

Jul 23, 2026cs.CL

What, Where, and How: Disentangling the Roles of Task, Language, and Model in Code Model Representations

Do independently trained language models come to represent the same thing in the same way? We answer for code, extending a recently introduced concept-circuit extraction method to a 2x2 design -- Python and Rust crossed with Qwen2.5-Coder-7B and DeepSeek-Coder-V1-6.7B -- and measuring a complete inventory of grammatical concepts (58 Python, 57 Rust) identically in all four cells: the smallest design that separates what depends on the task, the language, and the model. The answer splits into three parts. What earns dedicated circuitry is set by the task: the models agree on which concepts receive circuits (Spearman

ρ

= 0.638 for Python, 0.673 for Rust, both p <

10^{-7}

). Where those circuits sit is set by the model: Qwen processes concepts in a late band (~L17-19), DeepSeek at L6-7, for both languages. How circuits grow across layers is also set by the model: Qwen gives its atomic concepts an early spike that DeepSeek does not. "Are circuits universal?" thus has no single answer: yes for What, no for Where and How -- universality is a property of representational content, not of computational organisation. None of this structure was fixed in advance. The agreement could have landed anywhere between independence and identity; it lands at

ρ\approx 0.65

. Rust constructs receive 2-3x more concept-specific circuitry than their Python equivalents, in both models. Both models share neurons between the languages (6/7 and 7/7 paired constructs), DeepSeek 1.94x more than Qwen -- a direction no prior result predicts. And Qwen binds nine keywords of Rust's type-and-trait machinery into one tight neuron cluster (Jaccard 0.535 vs null 0.112, p < 0.001), a semantic dimension invisible in surface syntax. Ablation and linear probes confirm the circuits are functional. All claims are scoped to this 2x2; whether the per-model profile predicts a third model is the designed next test.

Piotr Wilam

University College London

Circuit Discovery Language Model Introspection Circuits in Language Models Representation Geometry in Language Models Code Language Models

Jul 23, 2026cs.SE

Transformer-Assisted LLM-Based Source Code Summarisation: to Enable More Secure Software Development

Neural Source Code Summarisation (NSCS) aims to generate natural language summaries of source code to improve developers' and maintainers' understanding of code. Source code summaries are vital during the maintenance phase of the Secure Software Development Lifecycle (SSDLC), as they improve maintainers' understanding of code and help reduce the number of bugs and vulnerabilities in a software system. However, summaries are often missing, incomplete, or outdated in many software systems. Solutions to this problem use small, task-specific Transformer models or code-aware Large Language Models (LLMs). Task-specific Transformer-generated summaries often score well across many natural language generation (NLG) metrics, but these metrics reward lexical overlap rather than summary quality. Conversely, the ability of LLMs to capture semantics and produce high-quality summaries presents an exciting solution to this problem. This is especially relevant given the increased availability of LLMs and improvements in workstation hardware in recent years, which mean that some LLMs can now be run on developers' workstations. However, because of their abstractive nature, LLM-generated code summaries often differ greatly from developer-written summaries in the words and phrases they use, resulting in low scores across NLG metrics. We show how combining these two methods, by using Transformer-generated summaries in prompt engineering, may enable LLMs to create better source code summaries and help software practitioners maintain secure systems. We prompt four LLMs using four different prompts, with a task-specific Transformer used to assist the LLMs within the prompts. We present "Transformer-Assisted LLM-Based Source Code Summarisation", a method through which we observe an improvement of 7.8% in BLEU-4 and 5%.

Jesse Phillips, Tracy Hall, Paul Rayson +1

School of Computing and Communications, Lancaster University, UK · School of Computing · College of Engineering & Computer Science, VinUniversity, Vietnam

Code Language Models

Jul 14, 2026cs.SE

Form, Not Content? A Preregistered, Placebo-Controlled Evaluation of Learned Error-Conditioned Self-Repair Through Prompts and Weights in Frozen Small Code Models

Frozen small code LLMs are deployed locally, yet the information guiding a retry after a failed attempt is still measured without placebo controls in the self-repair literature. We treat a failed program as a conjecture and an execution counterexample as an oracle-relative refutation, and introduce PoPE (Popperian Placebo-controlled Evaluation): a methodology for measuring whether evidence that falsifies LLM-generated code can be used operationally by that same model. In PoPE, error content is paired with channel-specific placebos that keep the predeclared scaffold while ablating task-relevant content or deranging the task-error assignment. Frozen small code models (0.5-1.5B) are evaluated under preregistered rules through a prompt channel and a weight channel (small-data adapter training), with four generations per arm-unit pair. In the prompt channel, public-tier screening unlocked 12 units under the content-ablated form placebo versus 10 under the live error-pattern arm on a 40-unit resistant band; the result was recorded as mechanism-null. In the weight channel, an 8-8 tie was observed between the error-content adapter and the intervention-free baseline (p=1.0), while the SHA-deranged placebo adapter stayed ahead with 10 unlocks; content-attributable superiority was not confirmed. These results do not constitute evidence of equivalence or non-inferiority. Equivalence was not tested separately. Findings are restricted to the public-tier screening endpoint; hidden-tier confirmation was deferred by design. We read this not as compiled criticism disappearing as information, but as the loss of its external role in testing a new conjecture: when a representation learned from the oracle is written back into the generation state, testing is replaced by conditioning. No working JEPA-RL controller is claimed. PoPE is presented as a placebo-controlled, retestable measurement standard.

Mehmet Iscan

PythaLab, Yıldız Technical University, Istanbul, Turkey

LLM Self-Correction Automated Program Repair Code Generation Evaluation Code Language Models

Jul 14, 2026cs.SE

Line-Anchored Feedback Cuts Token Costs and Improves Correctness in AI Code Editing

Generated tokens are a direct driver of the cost, latency, and energy of generative AI (GAI) code editing. We show the format of feedback is a lever on all three. We compare two deliveries of the same requested changes: a holistic prompt (control) versus the structured, line-anchored export of FileMark (treatment). FileMark is a VSCodium extension for inline comments on any file. In a paired experiment line anchoring cut generated tokens by 22% (Claude Opus) and 58% (Claude Sonnet), reaching 24%-80% on files of 100 lines or more, with four of seven models generating significantly fewer tokens after multiple-testing correction. Correctness rose where models had headroom: +2.0 points pooled and +5 to +7 points for three of five local models. An exploratory experiment in which the harness, not the GAI model, applies function-level patches shows the correctness benefit grows further when the edit-application burden is lifted: local-model correctness on 100+ line files roughly triples under anchoring. Line-anchored feedback reduces what stronger models spend and improves what weaker models get right.

William Franz Lamberti

Computational and Data Sciences College of Science George Mason University Fairfax, VA, United States

Code Generation Evaluation Code Language Models LLM Code Generation

Jul 14, 2026cs.AI

Function-Aware Fill-in-the-Middle as Mid-Training for Coding Agent Foundation Models

Coding agents must integrate external tool returns into ongoing reasoning - a capability that standard left-to-right pretraining on code exposes only in its forward direction. We observe that the action-observation-continuation loop of a coding agent is structurally isomorphic to a function call site, where a caller binds arguments, a callee returns a value computed elsewhere, and downstream code consumes that value. This conditioning structure exists at internet scale in ordinary code. We exploit it through function-aware fill-in-the-middle (FIM) mid-training: a self-supervised objective that masks functions selected via program dependency graph analysis and a complexity-inferability double criterion. We mid-train Qwen2.5-Coder-Instruct (7B/14B) and Qwen3-8B on a 2.6B-token decontaminated corpus drawn from 968 GitHub repositories, then apply existing agentic post-training pipelines. Mid-training improves SWE-Bench-Verified by +2.8/+3.0 at 7B/14B and by +3.2 on Qwen3-8B; SWE-Bench-Lite gains are +3.7/+4.0/+5.4 on the same models. The improvement holds across two post-training pipelines (R2E-Gym, SWE-Smith) and on a non-Qwen2.5 base (Qwen3-8B with SWE-Lego). Beyond in-domain gains, mid-training also mitigates the capability erosion that agentic post-training otherwise inflicts on non-agent coding (e.g., LiveCodeBench) and non-coding tool-use benchmarks (tau-bench, BFCL): although the mid-training corpus contains Python code only, the function-call inductive bias survives post-training and yields consistent gains.

Yubo Wang, Jiarong Liang, Yuxuan Zhang +5

University of Waterloo · 5Vector Institute · University of British Columbia +2

Masked Language Modeling Coding Agents Code Language Models LLM Training

Jul 14, 2026cs.SE

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

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. Reliable automation, therefore, demands the ability to distinguish between confident, well-supported predictions and stochastic guessing. However, existing uncertainty estimation methods face a critical gap: white and grey-box techniques are often inapplicable to closed-source models, while standard "black-box" text metrics fail to capture the unique fragility of code, where syntactic variation does not always imply semantic divergence. To bridge this syntax-semantics gap, we introduce Code-MUE, a purely black-box framework that measures uncertainty through execution-based Semantic Interaction Graphs. Unlike prior approaches that rely on superficial textual similarity, Code-MUE grounds uncertainty in observable runtime behavior, calculating the Von Neumann entropy of the solution space to quantify global semantic diversity. A large-scale empirical study across eight state-of-the-art LLMs demonstrates that Code-MUE achieves a strong negative correlation with functional correctness (Spearman's correlation up to -0.98), significantly outperforming lexical and embedding-based baselines while enabling robust risk detection and selective prediction in practical workflows.

Xiaoning Ren, Yinxing Xue, Lei Ma +1

Xi’an Jiaotong University, China · Institute of AI for Industries, Chinese Academy of Sciences, China · The University of Tokyo, Japan +1

Uncertainty Quantification LLM Uncertainty Estimation Code Language Models

Jul 13, 2026cs.SE

Fail-Aware and Explainable Test Oracle Prediction

Despite their central role in fault detection, test oracles remain challenging to construct effectively. Recent learning based methods address this challenge by automatically generating test assertions, yet even if syntactically correct, they are often ineffective in revealing bugs. Rather than generating assertions, this study explores a different approach by training a model to directly predict whether a given test prefix passes or fails. We present FOCAL, an emerging code LLM-based discriminative oracle predictor. It learns from labeled pairs of test prefixes and methods under test, employs losses that emphasize failing cases during training, and grounds its predictions in statement level behavioral evidence. Compared with the baseline method SEER, we substantially improve performance on failing cases for unseen projects and provide richer explanations. A preliminary evaluation on fault-detection benchmarks and automated test-generation artifacts shows that our approach is highly accurate within its training distribution and substantially improves failure detection on previously unseen projects where prior discriminative oracles collapse. Moreover, the highlighted statements are supported by behavioral explanation checks. These early results suggest that fail-aware discriminative oracle prediction can complement existing approaches such as fuzzing, search-based testing, and LLM-based test generation. These techniques produce test prefixes at scale but often lack fault oriented oracles. In future work, FOCAL could take generated test prefixes and attach fault-aware predicted oracles to them, turning high-volume input generation into executable tests that are more likely to expose semantic failures.

Yue Zhao, Binish Tanveer, Jelena Zdravkovic

Department of Computer and Systems Sciences, Stockholm University, Stockholm, Sweden

Automated Software Testing Fault Detection Code Language Models

Jul 9, 2026cs.CL

TypeProbe: Recovering Type Representations from Hidden States of Pre-trained Code Models

State-of-the-art code models achieve impressive performance, yet the extent to which they internally encode type information remains poorly understood. We probe the residual streams of pretrained code models for internal type representations using a parallel dataset of Java and Python code examples. Our results show that cross-lingual type representations emerge even from untyped code. Moreover, we test whether hidden states linearly encode the result type implied by typed function application by training probes on one language to infer argument and result types in the other. Finally, we find that this structure is partly robust to lexical perturbations and cross-language syntactic variations. To the best of our knowledge, prior work on interpretability of code models has not directly targeted formal type semantics or cross-lingual type representations. We release our code and datasets.

Giuliano Gorgone, Fausto Carcassi

ILLC, University of Amsterdam, Amsterdam, The Netherlands

LLM Interpretability Representation Geometry in Language Models Code Language Models Language Model Probing

Jul 9, 2026cs.CR

Beware What You Autocomplete: Forensic Attribution of Backdoored Code Completions

Large language models have enabled powerful code completion systems that assist developers by predicting subsequent lines of code. However, these models remain vulnerable to backdoor attacks, where malicious fine-tuning data covertly implants unsafe behaviors. Despite advances in defensive techniques, adaptive and sophisticated backdoor attacks still evade detection and mitigation. We present CodeTracer, a forensic framework that traces malicious code completions back to the backdoor fine-tuning data responsible for them. Operating under realistic post-deployment constraints, CodeTracer relies solely on the fine-tuning corpus and the reported miscompletion event. It extracts a structured behavioral fingerprint from the compromised output, narrows the search to semantically relevant code samples, and employs LLM-based reasoning to attribute unsafe logic to specific backdoor data. Extensive evaluations across three representative vulnerability cases and ten backdoor attacks, along with sixteen competitive baselines, demonstrate that CodeTracer consistently achieves high forensic accuracy, low false identification rates, and strong robustness against adaptive attacks.

Anjun Gao, Yueyang Quan, Zhuqing Liu +1

University of Louisville · University of North Texas

LLM Backdoor Attacks Backdoor Detection Code Language Models

Jul 8, 2026cs.SE

Functional and Secure Code Generation with Task Vectors

Large language models (LLMs) are increasingly used for code generation, but they struggle to generate functional code free of security vulnerabilities. Prior work to improve the secure code generation abilities of such coding LLMs has largely focused on evaluating code functionality and security separately using different datasets, or focused on finding vulnerabilities post-generation. At the same time, the text-generation domain has seen significant work on alignment techniques, where models are tuned such that their outputs exhibit certain qualities (e.g., helpfulness, harmlessness). Of particular interest is task-vector arithmetic, where linear operations on LLM weights can be used to arbitrarily enhance alignment while incurring only minimal computational overhead. We develop a novel method, SecVecCoder, leveraging task vectors to produce trustworthy code that is simultaneously functional and secure without the need for post-generation adjustment. Across six coding LLMs from three families on the CodeGuard+ benchmark, SecVecCoder improves the rate of trustworthy code completions by 2.1-36.0 percentage points over the base model, with improvements on unseen CWE types reaching up to 39.1 percentage points. Since the effectiveness of the coding LLM relies only on changing the model weights, SecVecCoder requires no method-specific decoding and hence achieves a decoding latency within 0.6% of the base model's, on average.

Felix Wang, Anudeep Das, Mei Nagappan +1

University of Waterloo, Waterloo, ON, Canada · KTH Royal Institute of Technology, Stockholm, Sweden

Code Generation LLM Safety Alignment Secure Code Generation Code Language Models