On the public citation graph

Efficient and Green Large Language Models for Software Engineering: Literature Review, Vision, and the Road Ahead

0 signed · 140 inferred · view as graph

Inferred edges come from two machine sources: sweeps of open repository metadata (mostly SSRN and Zenodo), and a bulk OpenAlex citation snapshot. Every row below is labelled with the one it came from. Neither is a complete citation index — absence here is not evidence of absence.

Is this your work? Sign in with ORCID and put your name on the claims that are yours.

Claim with ORCID

Reference health. See whether every reference in this work resolves to a known work and none has been retracted — and get a dated CiteStamped badge you can embed.

See reference health

What this work says

Outgoing claims: the papers this work cites, builds on, or argues with.

inferredcites →https://doi.org/10.1007/978-3-030-64437-6_16openalex-snapshot

REFINITY to Model and Prove Program Transformation Rules

inferredcites →https://doi.org/10.1007/978-3-031-46002-9openalex-snapshot

Bridging the Gap Between AI and Reality

inferredcites →https://doi.org/10.1007/978-3-031-46002-9_23openalex-snapshot

Large Language Model Assisted Software Engineering: Prospects, Challenges, and a Case Study

inferredcites →https://doi.org/10.1007/978-3-031-71139-8_5openalex-snapshot

Large Language Models for Software Engineering: A Systematic Mapping Study

inferredcites →https://doi.org/10.1007/s10515-024-00421-4openalex-snapshot

Distilled GPT for source code summarization

inferredcites →https://doi.org/10.1016/j.future.2024.01.033openalex-snapshot

Development and evaluation of a reference measurement model for assessing the resource and energy efficiency of software products and components—Green Software Measurement Model (GSMM)

inferredcites →https://doi.org/10.1016/j.jclepro.2017.12.239openalex-snapshot

Assessing ICT global emissions footprint: Trends to 2040 & recommendations

inferredcites →https://doi.org/10.1016/j.joule.2023.09.004openalex-snapshot

The growing energy footprint of artificial intelligence

inferredcites →https://doi.org/10.1016/j.xinn.2021.100180openalex-snapshot

Technologies and perspectives for achieving carbon neutrality

inferredcites →https://doi.org/10.1109/ase56229.2023.00125openalex-snapshot

An Empirical Study of Parameter-Efficient Fine-Tuning Methods for Pre-Trained Code Models

inferredcites →https://doi.org/10.1109/hpec58863.2023.10363447openalex-snapshot

From Words to Watts: Benchmarking the Energy Costs of Large Language Model Inference

inferredcites →https://doi.org/10.1109/icse-companion58688.2023.00089openalex-snapshot

Don't Complete It! Preventing Unhelpful Code Completion for Productive and Sustainable Neural Code Completion Systems

inferredcites →https://doi.org/10.1109/icse-fose59343.2023.00008openalex-snapshot

Large Language Models for Software Engineering: Survey and Open Problems

inferredcites →https://doi.org/10.1109/icse-fose59343.2023.00010openalex-snapshot

Trustworthy and Synergistic Artificial Intelligence for Software Engineering: Vision and Roadmaps

inferredcites →https://doi.org/10.1109/icse43902.2021.00110openalex-snapshot

Efficient Compiler Autotuning via Bayesian Optimization

inferredcites →https://doi.org/10.1109/icse48619.2023.00013openalex-snapshot

One Adapter for All Programming Languages? Adapter Tuning for Code Search and Summarization

inferredcites →https://doi.org/10.1109/icse48619.2023.00125openalex-snapshot

Impact of Code Language Models on Automated Program Repair

inferredcites →https://doi.org/10.1109/icse48619.2023.00129openalex-snapshot

Automated Program Repair in the Era of Large Pre-trained Language Models

inferredcites →https://doi.org/10.1109/icsme58846.2023.00028openalex-snapshot

CCBERT: Self-Supervised Code Change Representation Learning

inferredcites →https://doi.org/10.1109/ipccc59175.2023.10253886openalex-snapshot

Evaluating the Carbon Impact of Large Language Models at the Inference Stage

inferredcites →https://doi.org/10.1109/issre59848.2023.00026openalex-snapshot

LLaMA-Reviewer: Advancing Code Review Automation with Large Language Models through Parameter-Efficient Fine-Tuning

inferredcites →https://doi.org/10.1109/issrew60843.2023.00058openalex-snapshot

Software Vulnerability Detection using Large Language Models

inferredcites →https://doi.org/10.1109/msr52588.2021.00045openalex-snapshot

Fast and Memory-Efficient Neural Code Completion

inferredcites →https://doi.org/10.1109/saner53432.2022.00130openalex-snapshot

Can Identifier Splitting Improve Open-Vocabulary Language Model of Code?

inferredcites →https://doi.org/10.1109/saner60148.2024.00055openalex-snapshot

Delving into Parameter-Efficient Fine-Tuning in Code Change Learning: An Empirical Study

inferredcites →https://doi.org/10.1109/sp54263.2024.00152openalex-snapshot

"Len or index or count, anything but v1": Predicting Variable Names in Decompilation Output with Transfer Learning

inferredcites →https://doi.org/10.1109/tse.2023.3334955openalex-snapshot

An Empirical Evaluation of Using Large Language Models for Automated Unit Test Generation

inferredcites →https://doi.org/10.1109/tse.2024.3368208openalex-snapshot

Software Testing With Large Language Models: Survey, Landscape, and Vision

inferredcites →https://doi.org/10.1109/tse.2024.3376964openalex-snapshot

Active Code Learning: Benchmarking Sample-Efficient Training of Code Models

inferredcites →https://doi.org/10.1126/science.abq1158openalex-snapshot

Competition-level code generation with AlphaCode

inferredcites →https://doi.org/10.1145/3365438.3410949openalex-snapshot

Certifying a rule-based model transformation engine for proof preservation

inferredcites →https://doi.org/10.1145/3368089.3417058openalex-snapshot

IntelliCode compose: code generation using transformer

inferredcites →https://doi.org/10.1145/3503222.3507764openalex-snapshot

Finding missed optimizations through the lens of dead code elimination

inferredcites →https://doi.org/10.1145/3510003.3510062openalex-snapshot

Bridging pre-trained models and downstream tasks for source code understanding

inferredcites →https://doi.org/10.1145/3510003.3510096openalex-snapshot

SPT-code

inferredcites →https://doi.org/10.1145/3520312.3534862openalex-snapshot

A systematic evaluation of large language models of code

inferredcites →https://doi.org/10.1145/3539618.3591687openalex-snapshot

FiD-Light: Efficient and Effective Retrieval-Augmented Text Generation

inferredcites →https://doi.org/10.1145/3540250.3549094openalex-snapshot

Diet code is healthy: simplifying programs for pre-trained models of code

inferredcites →https://doi.org/10.1145/3540250.3549162openalex-snapshot

NatGen: generative pre-training by “naturalizing” source code

inferredcites →https://doi.org/10.1145/3540250.3558959openalex-snapshot

Exploring and evaluating personalized models for code generation

inferredcites →https://doi.org/10.1145/3551349.3556955openalex-snapshot

CoditT5: Pretraining for Source Code and Natural Language Editing

inferredcites →https://doi.org/10.1145/3551349.3556964openalex-snapshot

Compressing Pre-trained Models of Code into 3 MB

inferredcites →https://doi.org/10.1145/3551349.3559555openalex-snapshot

Few-shot training LLMs for project-specific code-summarization

inferredcites →https://doi.org/10.1145/3564625.3567985openalex-snapshot

Transformer-Based Language Models for Software Vulnerability Detection

inferredcites →https://doi.org/10.1145/3597503.3608136openalex-snapshot

FAIR: Flow Type-Aware Pre-Training of Compiler Intermediate Representations

inferredcites →https://doi.org/10.1145/3597503.3608137openalex-snapshot

Prompting Is All You Need: Automated Android Bug Replay with Large Language Models

inferredcites →https://doi.org/10.1145/3597503.3623316openalex-snapshot

CoderEval: A Benchmark of Pragmatic Code Generation with Generative Pre-trained Models

inferredcites →https://doi.org/10.1145/3597503.3639074openalex-snapshot

Unveiling Memorization in Code Models

inferredcites →https://doi.org/10.1145/3597503.3639085openalex-snapshot

Code Search is All You Need? Improving Code Suggestions with Code Search

inferredcites →https://doi.org/10.1145/3597503.3639120openalex-snapshot

When Neural Code Completion Models Size up the Situation: Attaining Cheaper and Faster Completion through Dynamic Model Inference

inferredcites →https://doi.org/10.1145/3597503.3639125openalex-snapshot

GrammarT5: Grammar-Integrated Pretrained Encoder-Decoder Neural Model for Code

inferredcites →https://doi.org/10.1145/3597503.3639183openalex-snapshot

Automatic Semantic Augmentation of Language Model Prompts (for Code Summarization)

inferredcites →https://doi.org/10.1145/3597926.3598036openalex-snapshot

Towards Efficient Fine-Tuning of Pre-trained Code Models: An Experimental Study and Beyond

inferredcites →https://doi.org/10.1145/3609437.3609438openalex-snapshot

Structural-semantics Guided Program Simplification for Understanding Neural Code Intelligence Models

inferredcites →https://doi.org/10.1145/3611643.3613892openalex-snapshot

InferFix: End-to-End Program Repair with LLMs

inferredcites →https://doi.org/10.1145/3611643.3616271openalex-snapshot

Copiloting the Copilots: Fusing Large Language Models with Completion Engines for Automated Program Repair

inferredcites →https://doi.org/10.1145/3611643.3616302openalex-snapshot

Towards Greener Yet Powerful Code Generation via Quantization: An Empirical Study

inferredcites →https://doi.org/10.1145/3611643.3616304openalex-snapshot

The EarlyBIRD Catches the Bug: On Exploiting Early Layers of Encoder Models for More Efficient Code Classification

inferredcites →https://doi.org/10.1145/3611643.3616369openalex-snapshot

Efficient Text-to-Code Retrieval with Cascaded Fast and Slow Transformer Models

inferredcites →https://doi.org/10.1145/3635711openalex-snapshot

Representation Learning for Stack Overflow Posts: How Far Are We?

inferredcites →https://doi.org/10.1145/3637528.3671470openalex-snapshot

A Survey on RAG Meeting LLMs: Towards Retrieval-Augmented Large Language Models

inferredcites →https://doi.org/10.1145/3639475.3640097openalex-snapshot

Greening Large Language Models of Code

inferredcites →https://doi.org/10.1145/3639475.3640111openalex-snapshot

A Synthesis of Green Architectural Tactics for ML-Enabled Systems

inferredcites →https://doi.org/10.1145/3639476.3639762openalex-snapshot

Large Language Model for Vulnerability Detection: Emerging Results and Future Directions

inferredcites →https://doi.org/10.1145/3643674openalex-snapshot

Refining ChatGPT-Generated Code: Characterizing and Mitigating Code Quality Issues

inferredcites →https://doi.org/10.1145/3643753openalex-snapshot

Natural Is the Best: Model-Agnostic Code Simplification for Pre-trained Large Language Models

inferredcites →https://doi.org/10.1145/3643762openalex-snapshot

CORE: Resolving Code Quality Issues using LLMs

inferredcites →https://doi.org/10.1145/3643795.3648394openalex-snapshot

Learn to Code Sustainably: An Empirical Study on Green Code Generation

inferredcites →https://doi.org/10.1145/3643916.3644434openalex-snapshot

Do Machines and Humans Focus on Similar Code? Exploring Explainability of Large Language Models in Code Summarization

inferredcites →https://doi.org/10.1145/3644815.3644942openalex-snapshot

Green Runner: A Tool for Efficient Deep Learning Component Selection

inferredcites →https://doi.org/10.1145/3644815.3644943openalex-snapshot

Engineering Carbon Emission-aware Machine Learning Pipelines

inferredcites →https://doi.org/10.1145/3644815.3644962openalex-snapshot

Identifying Architectural Design Decisions for Achieving Green ML Serving

inferredcites →https://doi.org/10.1145/3644815.3644966openalex-snapshot

The Impact of Knowledge Distillation on the Energy Consumption and Runtime Efficiency of NLP Models

inferredcites →https://doi.org/10.1145/3644815.3644967openalex-snapshot

Green AI: a Preliminary Empirical Study on Energy Consumption in DL Models Across Different Runtime Infrastructures

inferredcites →https://doi.org/10.1145/3649506openalex-snapshot

Harnessing the Power of LLMs in Practice: A Survey on ChatGPT and Beyond

inferredcites →https://doi.org/10.1145/3650212.3680343openalex-snapshot

When to Stop? Towards Efficient Code Generation in LLMs with Excess Token Prevention

inferredcites →https://doi.org/10.1145/3650212.3680347openalex-snapshot

AI Coders Are among Us: Rethinking Programming Language Grammar towards Efficient Code Generation

inferredcites →https://doi.org/10.1145/3660818openalex-snapshot

Your Code Secret Belongs to Me: Neural Code Completion Tools Can Memorize Hard-Coded Credentials

inferredcites →https://doi.org/10.1145/3664646.3664773openalex-snapshot

The Role of Generative AI in Software Development Productivity: A Pilot Case Study

inferredcites →https://doi.org/10.1145/3688831openalex-snapshot

Don’t Complete It! Preventing Unhelpful Code Completion for Productive and Sustainable Neural Code Completion Systems

inferredcites →https://doi.org/10.1145/3691620.3695066openalex-snapshot

Exploring Parameter-Efficient Fine-Tuning of Large Language Model on Automated Program Repair

inferredcites →https://doi.org/10.1145/3695988openalex-snapshot

Large Language Models for Software Engineering: A Systematic Literature Review

inferredcites →https://doi.org/10.1145/3712007openalex-snapshot

Innovating for Tomorrow: The Convergence of Software Engineering and Green AI

inferredcites →https://doi.org/10.1145/3714461openalex-snapshot

Exploring Parameter-Efficient Fine-Tuning Techniques for Code Generation with Large Language Models

inferredcites →https://doi.org/10.1145/3731753openalex-snapshot

Ecosystem of Large Language Models for Code

inferredcites →https://doi.org/10.18653/v1/2020.acl-main.443openalex-snapshot

Code and Named Entity Recognition in StackOverflow

inferredcites →https://doi.org/10.18653/v1/2020.findings-emnlp.139openalex-snapshot

CodeBERT: A Pre-Trained Model for Programming and Natural Languages

inferredcites →https://doi.org/10.18653/v1/2021.eacl-main.74openalex-snapshot

Leveraging Passage Retrieval with Generative Models for Open Domain Question Answering

inferredcites →https://doi.org/10.18653/v1/2021.emnlp-main.685openalex-snapshot

CodeT5: Identifier-aware Unified Pre-trained Encoder-Decoder Models for Code Understanding and Generation

inferredcites →https://doi.org/10.18653/v1/2021.findings-emnlp.232openalex-snapshot

Retrieval Augmented Code Generation and Summarization

inferredcites →https://doi.org/10.18653/v1/2021.naacl-main.211openalex-snapshot

Unified Pre-training for Program Understanding and Generation

inferredcites →https://doi.org/10.18653/v1/2021.nlp4prog-1.5openalex-snapshot

CoTexT: Multi-task Learning with Code-Text Transformer

inferredcites →https://doi.org/10.18653/v1/2022.acl-long.181openalex-snapshot

Accelerating Code Search with Deep Hashing and Code Classification

inferredcites →https://doi.org/10.18653/v1/2022.acl-long.499openalex-snapshot

UniXcoder: Unified Cross-Modal Pre-training for Code Representation

inferredcites →https://doi.org/10.18653/v1/2022.emnlp-main.187openalex-snapshot

CodeRetriever: A Large Scale Contrastive Pre-Training Method for Code Search

inferredcites →https://doi.org/10.18653/v1/d19-1633openalex-snapshot

Mask-Predict: Parallel Decoding of Conditional Masked Language Models

inferredcites →https://doi.org/10.18653/v1/n19-1423openalex-snapshot

BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding

inferredcites →https://doi.org/10.48550/arxiv.2211.02001openalex-snapshot

Estimating the Carbon Footprint of BLOOM, a 176B Parameter Language Model

What points at this work

Incoming claims: where this work appears in other papers’ reference lists and arguments.

inferred← citeshttps://doi.org/10.1007/s10664-025-10776-1openalex-snapshot

Performance analysis of AI-generated code: A case study of Copilot, Copilot Chat, CodeLlaMa, and DeepSeek-Coder models

inferred← citeshttps://doi.org/10.1016/j.csi.2026.104170openalex-snapshot

Estimating Deep Learning energy consumption based on model architecture and training environment

inferred← citeshttps://doi.org/10.1016/j.infsof.2026.108207openalex-snapshot

Quality attributes, challenges, and solutions for designing GenAI-enabled systems

inferred← citeshttps://doi.org/10.1016/j.procs.2025.10.038openalex-snapshot

Creating Green Jobs in ICT: Opportunities and Challenges

inferred← citeshttps://doi.org/10.1016/j.scs.2025.106444openalex-snapshot

A novel domain knowledge augmented large language model based medical conversation system for sustainable smart city development

inferred← citeshttps://doi.org/10.1109/access.2026.3658813openalex-snapshot

GreenAI: A Comparative Analysis of Environmental Efficiency in LLM-Generated Code

inferred← citeshttps://doi.org/10.1109/acp66871.2025.11350985openalex-snapshot

Carbon-Aware LLM Inference Instance Deployment and Workload Assignment Across Geo-distributed Data Centers

inferred← citeshttps://doi.org/10.1109/aibthings63359.2024.10863356openalex-snapshot

Risks, Causes, and Mitigations of Widespread Deployments of Large Language Models (LLMs): A Survey

inferred← citeshttps://doi.org/10.1109/ase63991.2025.00021openalex-snapshot

Code-DiTing: Automatic Evaluation of Code Generation without References or Test Cases

inferred← citeshttps://doi.org/10.1109/ase63991.2025.00024openalex-snapshot

"My productivity is boosted, but …" Demystifying Users’ Perception on AI Coding Assistants

inferred← citeshttps://doi.org/10.1109/ase63991.2025.00157openalex-snapshot

Coding-Fuse: Efficient Fusion of Code Pre-Trained Models for Classification Tasks

inferred← citeshttps://doi.org/10.1109/cai64502.2025.00067openalex-snapshot

Optimizing Large Language Models: Metrics, Energy Efficiency, and Case Study Insights

inferred← citeshttps://doi.org/10.1109/esem64174.2025.00047openalex-snapshot

How Small is Enough? Empirical Evidence of Quantized Small Language Models for Automated Program Repair

inferred← citeshttps://doi.org/10.1109/icscsa69367.2026.11708136openalex-snapshot

Drivers of Sustainable ‘Green Cloud’ Computing Adoption in IT Service Firms: An ESG-Based Content Analysis Using the Technology–Organization–Environment Perspective

inferred← citeshttps://doi.org/10.1109/icsme64153.2025.00049openalex-snapshot

Is Quantization a Deal-Breaker? Empirical Insights From Large Code Models

inferred← citeshttps://doi.org/10.1109/saner67736.2026.00094openalex-snapshot

Assessing Large Language Models in Verifying Concurrent Programs

inferred← citeshttps://doi.org/10.1109/sbac-padw69789.2025.00028openalex-snapshot

One-Class Lightweight Interpretable Filtering For Academic Profiles and Strategic Themes Affinity

inferred← citeshttps://doi.org/10.1145/3708523openalex-snapshot

The Impact of Generative AI on Creativity in Software Development: A Research Agenda

inferred← citeshttps://doi.org/10.1145/3708531openalex-snapshot

Large Language Model Supply Chain: A Research Agenda

inferred← citeshttps://doi.org/10.1145/3715105openalex-snapshot

Finding Safety Violations of AI-Enabled Control Systems through the Lens of Synthesized Proxy Programs

inferred← citeshttps://doi.org/10.1145/3715106openalex-snapshot

Testing and Debugging Quantum Programs: The Road to 2030

inferred← citeshttps://doi.org/10.1145/3731753openalex-snapshot

Ecosystem of Large Language Models for Code

inferred← citeshttps://doi.org/10.1145/3744900openalex-snapshot

The Sustainability Face of Automated Program Repair Tools

inferred← citeshttps://doi.org/10.1145/3773034openalex-snapshot

Synthesizing Efficient and Permissive Programmatic Runtime Shields for Neural Policies

inferred← citeshttps://doi.org/10.1145/3774748.3787638openalex-snapshot

Reinforcement Learning from Testing Targets for Effective SLM Test Generation

inferred← citeshttps://doi.org/10.1145/3783995openalex-snapshot

AutoTestForge: A Multidimensional Automated Testing Framework for Natural Language Processing Models

inferred← citeshttps://doi.org/10.1145/3786148.3788622openalex-snapshot

The Impacts of Artificial Intelligence throughout the Software Development Life-cycle on Sustainability: A Mixed-method Study

inferred← citeshttps://doi.org/10.1145/3786148.3788630openalex-snapshot

Not All Local LLMs Are Equal: A Benchmark of Energy and Performance

inferred← citeshttps://doi.org/10.1145/3786582.3786814openalex-snapshot

PenForge: On-the-Fly Expert Agent Construction for Automated Penetration Testing

inferred← citeshttps://doi.org/10.1145/3797145openalex-snapshot

Small Is Beautiful: A Practical and Efficient Log Parsing Framework

inferred← citeshttps://doi.org/10.1145/3797276openalex-snapshot

LLM-as-a-Judge for Software Engineering: Literature Review, Vision, and the Road Ahead

inferred← citeshttps://doi.org/10.1145/3800580openalex-snapshot

Novice Developers’ Perspectives on Adopting LLMs for Software Development: A Systematic Literature Review

inferred← citeshttps://doi.org/10.1145/3801980openalex-snapshot

Ethical Prompt Engineering for AI-driven SE: Evidence-informed Interaction-time Governance Roadmap to 2030

inferred← citeshttps://doi.org/10.1145/3808196openalex-snapshot

Compiling Code LLMs into Lightweight Executables

inferred← citeshttps://doi.org/10.1145/3808198openalex-snapshot

One Size Does Fit All: Exploring Model Fusion for Software Engineering Tasks

inferred← citeshttps://doi.org/10.1145/3813822.3814148openalex-snapshot

LLM-EMM: A Large Language Model--Driven Efficiency Measurement and Modeling Framework for Software Development in Digitally Transforming Enterprises

inferred← citeshttps://doi.org/10.1145/3832175openalex-snapshot

Hidden Licensing Risks in the PTMware Ecosystem

inferred← citeshttps://doi.org/10.1145/3832783.3837454openalex-snapshot

It Takes Two to Tango: Accelerating Code Generation via Cache-Inspired Hierarchical Speculative Decoding

inferred← citeshttps://doi.org/10.2139/ssrn.6332149openalex-snapshot

LLM-Based Multi-Agent Systems for Code Generation: A Multi-Vocal Literature Review ⋆

inferred← citeshttps://doi.org/10.25136/2409-8647.2026.1.78545openalex-snapshot

Mathematical Methods in Data Economics: An Analytical Proof of Coincidence for Symmetric and Asymmetric AI Agents

inferred← citeshttps://doi.org/10.3390/a18080499openalex-snapshot

A Research Landscape of Agentic AI and Large Language Models: Applications, Challenges and Future Directions

inferred← citeshttps://doi.org/10.3390/w18101132openalex-snapshot

Large Language Models for Coagulant Dosage Prediction: A Systematic Investigation of Generalization, Rationale Patterns and Hallucination

Editorial review for independent work. ICSAC — the Institute for Complexity Science and Advanced Computing — runs a structured editorial panel for researchers publishing outside journals, and publishes on CiteStamp rails. Submission is free and goes through ORCID: icsacinstitute.org/submit.