SOTAVerified

HumanEval

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 151–200 of 264 papers

TitleStatusHype
AttentionInfluence: Adopting Attention Head Influence for Weak-to-Strong Pretraining Data Selection—0
AutoTest: Evolutionary Code Solution Selection with Test Cases—0
BASS: Batched Attention-optimized Speculative Sampling—0
Benchmarking AI Models in Software Engineering: A Review, Search Tool, and Enhancement Protocol—0
PythonSaga: Redefining the Benchmark to Evaluate Code Generating LLMs—0
Brevity is the soul of wit: Pruning long files for code generation—0
Bridging Code Semantic and LLMs: Semantic Chain-of-Thought Prompting for Code Generation—0
Can LLMs Enable Verification in Mainstream Programming?—0
CELI: Controller-Embedded Language Model Interactions—0
CodeCoT: Tackling Code Syntax Errors in CoT Reasoning for Code Generation—0
CodeFuse-13B: A Pretrained Multi-lingual Code Large Language Model—0
CodeMirage: Hallucinations in Code Generated by Large Language Models—0
CodeMixBench: Evaluating Large Language Models on Code Generation with Code-Mixed Prompts—0
Code-Optimise: Self-Generated Preference Data for Correctness and Efficiency—0
CodeShell Technical Report—0
CodeTree: Agent-guided Tree Search for Code Generation with Large Language Models—0
Concept Distillation from Strong to Weak Models via Hypotheses-to-Theories Prompting—0
Context-Augmented Code Generation Using Programming Knowledge Graphs—0
CPL: Critical Plan Step Learning Boosts LLM Generalization in Reasoning Tasks—0
CREST: Effectively Compacting a Datastore For Retrieval-Based Speculative Decoding—0
CRUXEval-X: A Benchmark for Multilingual Code Reasoning, Understanding and Execution—0
Dafny as Verification-Aware Intermediate Language for Code Generation—0
Decoding Data Quality via Synthetic Corruptions: Embedding-guided Pruning of Code Data—0
Demo-Craft: Using In-Context Learning to Improve Code Generation in Large Language Models—0
Discrete Flow Matching—0
Divide-and-Conquer Meets Consensus: Unleashing the Power of Functions in Code Generation—0
Does Few-Shot Learning Help LLM Performance in Code Synthesis?—0
Does your data spark joy? Performance gains from domain upsampling at the end of training—0
DOMAINEVAL: An Auto-Constructed Benchmark for Multi-Domain Code Generation—0
Dovetail: A CPU/GPU Heterogeneous Speculative Decoding for LLM inference—0
DSTC: Direct Preference Learning with Only Self-Generated Tests and Code to Improve Code LMs—0
Dynamic Scaling of Unit Tests for Code Reward Modeling—0
Structured Chain-of-Thought Prompting for Code Generation—0
Enhancing LLM-Based Code Generation with Complexity Metrics: A Feedback-Driven Approach—0
Evaluating Large Language Models for Code Review—0
Reasoning Runtime Behavior of a Program with LLM: How Far Are We?—0
Exploring and Evaluating Hallucinations in LLM-Powered Code Generation—0
Falcon: Faster and Parallel Inference of Large Language Models through Enhanced Semi-Autoregressive Drafting and Custom-Designed Decoding Tree—0
From Output to Evaluation: Does Raw Instruction-Tuned Code LLMs Output Suffice for Fill-in-the-Middle Code Generation?—0
Fully Autonomous Programming using Iterative Multi-Agent Debugging with Large Language Models—0
G-Designer: Architecting Multi-agent Communication Topologies via Graph Neural Networks—0
Grammar-Based Code Representation: Is It a Worthy Pursuit for LLMs?—0
GRIN: GRadient-INformed MoE—0
Guaranteed Guess: A Language Modeling Approach for CISC-to-RISC Transpilation with Testing Guarantees—0
Guided Code Generation with LLMs: A Multi-Agent Framework for Complex Code Tasks—0
Guideline Forest: Experience-Induced Multi-Guideline Reasoning with Stepwise Aggregation—0
Importing Phantoms: Measuring LLM Package Hallucination Vulnerabilities—0
Inference-Aware Fine-Tuning for Best-of-N Sampling in Large Language Models—0
InfiFusion: A Unified Framework for Enhanced Cross-Model Reasoning via LLM Fusion—0
Interactive Code Generation via Test-Driven User-Intent Formalization—0
Show:102550
← PrevPage 4 of 6Next →

No leaderboard results yet.