SOTAVerified

Code Completion

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 51–100 of 212 papers

TitleStatusHype
RAMBO: Enhancing RAG-based Repository-Level Method Body CompletionCode1
DataSculpt: Crafting Data Landscapes for Long-Context LLMs through Multi-Objective PartitioningCode1
MarsCode Agent: AI-native Automated Bug Fixing—0
Statically Contextualizing Large Language Models with Typed Holes—0
Security Attacks on LLM-based Code Completion ToolsCode1
Revisiting VerilogEval: A Year of Improvements in Large-Language Models for Hardware Code GenerationCode3
Retrieval-augmented code completion for local projects using large language models—0
RepoMasterEval: Evaluating Code Completion via Real-World Repositories—0
Black-Box Adversarial Attacks on LLM-Based Code Completion—0
TaskEval: Assessing Difficulty of Code Generation Tasks for Large Language Models—0
Evaluating Long Range Dependency Handling in Code Generation Models using Multi-Step Key Retrieval—0
Scaling Granite Code Models to 128K ContextCode4
Curriculum Learning for Small Code Language Models—0
TPIA: Towards Target-specific Prompt Injection Attack against Code-oriented Large Language Models—0
Jailbreak Attacks and Defenses Against Large Language Models: A Survey—0
On the Workflows and Smells of Leaderboard Operations (LBOps): An Exploratory Study of Foundation Model LeaderboardsCode3
Hierarchical Context Pruning: Optimizing Real-World Code Completion with Repository-Level Pretrained Code LLMsCode1
Measuring memorization in RLHF for code completion—0
Long Code Arena: a Set of Benchmarks for Long-Context Code ModelsCode1
CodeGemma: Open Code Models Based on Gemma—0
VersiCode: Towards Version-controllable Code GenerationCode1
An LLM-Assisted Easy-to-Trigger Backdoor Attack on Code Completion Models: Injecting Disguised Vulnerabilities against Strong DetectionCode2
Chain of Agents: Large Language Models Collaborating on Long-Context Tasks—0
R2C2-Coder: Enhancing and Benchmarking Real-world Repository-level Code Completion Abilities of Code Large Language Models—0
SemCoder: Training Code Language Models with Comprehensive Semantics ReasoningCode1
Dataflow-Guided Retrieval Augmentation for Repository-Level Code CompletionCode1
Superposed Decoding: Multiple Generations from a Single Autoregressive Inference PassCode1
Model Cascading for Code: A Cascaded Black-Box Multi-Model Framework for Cost-Efficient Code Completion with Self-Testing—0
Optimizing Large Language Models for OpenAPI Code CompletionCode2
AutoCoder: Enhancing Code Large Language Model with AIEV-InstructCode4
A Transformer-Based Approach for Smart Invocation of Automatic Code CompletionCode0
Full Line Code Completion: Bringing AI to Desktop—0
Does Your Neural Code Completion Model Use My Code? A Membership Inference ApproachCode0
Rethinking Software Engineering in the Foundation Model Era: From Task-Driven AI Copilots to Goal-Driven AI Pair Programmers—0
Is Next Token Prediction Sufficient for GPT? Exploration on Code Logic Comprehension—0
Stable Code Technical Report—0
PCToolkit: A Unified Plug-and-Play Prompt Compression Toolkit of Large Language ModelsCode3
Investigating the Performance of Language Models for Completing Code in Functional Programming Languages: a Haskell Case StudyCode0
Repoformer: Selective Retrieval for Repository-Level Code Completion—0
Token Alignment via Character Matching for Subword Completion—0
CodeAttack: Revealing Safety Generalization Challenges of Large Language Models via Code CompletionCode2
RepoHyper: Search-Expand-Refine on Semantic Graphs for Repository-Level Code CompletionCode2
Evaluation of LLMs on Syntax-Aware Code Fill-in-the-Middle TasksCode1
IRCoder: Intermediate Representations Make Language Models Robust Multilingual Code GeneratorsCode1
StarCoder 2 and The Stack v2: The Next GenerationCode7
Insights from the Usage of the Ansible Lightspeed Code Completion Service—0
CodeChameleon: Personalized Encryption Framework for Jailbreaking Large Language ModelsCode1
Language Models for Code Completion: A Practical EvaluationCode1
REPOFUSE: Repository-Level Code Completion with Fused Dual Context—0
Context Composing for Full Line Code Completion—0
Show:102550
← PrevPage 2 of 5Next →
All datasetsSAFIMCodeXGLUE - Github Java CorpusCodeXGLUE - PY150DotPromptsDefects4JRambo Benchmark

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1deepseek-coder-33b-baseAverage69.01—Unverified
2deepseek-coder-6.7b-baseAverage63.4—Unverified
3starcoderbaseAverage55.54—Unverified
4gpt-4-1106-previewAverage53.28—Unverified
5CodeLlama-13b-hfAverage52.78—Unverified
6deepseek-coder-1.3b-baseAverage52.63—Unverified
7CodeLlama-34b-hfAverage49.66—Unverified
8CodeLlama-7b-hfAverage45—Unverified
9gpt-3.5-turbo-0301Average40.86—Unverified
10incoder-6BAverage33.79—Unverified
#ModelMetricClaimedVerifiedStatus
1CodeGPT-adaptedAccuracy (token-level)77.13—Unverified
2CodeT5+ 770MEM (line-level)37.9—Unverified
3CodeT5+ 220MEM (line-level)35.17—Unverified
#ModelMetricClaimedVerifiedStatus
1CodeGPT-adaptedAccuracy (token-level)75.11—Unverified
2CodeT5+ 770MEM (line-level)44.86—Unverified
3CodeT5+ 220MEM (line-level)43.42—Unverified
#ModelMetricClaimedVerifiedStatus
1SantaCoder-MGDCompilation Rate73.03—Unverified
2SantaCoderCompilation Rate59.97—Unverified
3SantaCoderCompilation Rate59.79—Unverified
#ModelMetricClaimedVerifiedStatus
1RamboCompilation Rate76.47—Unverified
2RepoCoderCompilation Rate74.02—Unverified
#ModelMetricClaimedVerifiedStatus
1RamboCompilation Rate61.7—Unverified
2RepoCoderCompilation Rate58.09—Unverified