paper-with-me

Papers HumanEval

“HumanEval” 태그가 달린 논문 264편 · 필터 해제

Turning the Tide: Repository-based Code Reflection

2025-07-14 · Wei zhang, Jian Yang, Jiaxi Yang, Ya Wang 외

Code large language models (LLMs) enhance programming by understanding and generating code across languages, offering intelligent feedback, bug detection, and code updates through reflection, improving development effici…

Code GenerationDiversityHumanEval

Rethinking Verification for LLM Code Generation: From Generation to Testing

2025-07-09 · Zihan Ma, Taolin Zhang, Maosong Cao, Junnan Liu 외

Large language models (LLMs) have recently achieved notable success in code-generation benchmarks such as HumanEval and LiveCodeBench. However, a detailed examination reveals that these evaluation suites often comprise o…

Code GenerationHumanEval

any4: Learned 4-bit Numeric Representation for LLMs

2025-07-07 · Mostafa Elhoushi, Jeff Johnson

We present any4, a learned 4-bit weight quantization solution for large language models (LLMs) providing arbitrary numeric representations without requiring pre-processing of weights or activations. any4 yields higher ac…

GPUGSM8KHumanEvalmbpp+2

SACL: Understanding and Combating Textual Bias in Code Retrieval with Semantic-Augmented Reranking and Localization

2025-06-25 · Dhruv Gupta, Gayathri Ganesh Lakshmy, Yiqing Xie

Retrieval-Augmented Code Generation (RACG) is a critical technique for enhancing code generation by retrieving relevant information. In this work, we conduct an in-depth analysis of code retrieval by systematically maski…

Code GenerationHumanEvalmbppReranking+1

Plan for Speed -- Dilated Scheduling for Masked Diffusion Language Models

2025-06-23 · Omer Luxembourg, Haim Permuter, Eliya Nachmani

Masked diffusion language models (MDLM) have shown strong promise for non-autoregressive text generation, yet existing samplers act as implicit planners, selecting tokens to unmask via denoiser confidence or entropy scor…

Code CompletionGSM8KHumanEvalMath+3

AgentGroupChat-V2: Divide-and-Conquer Is What LLM-Based Multi-Agent System Need

2025-06-18 · Zhouhong Gu, Xiaoxuan Zhu, Yin Cai, Hao Shen 외

Large language model based multi-agent systems have demonstrated significant potential in social simulation and complex task resolution domains. However, current frameworks face critical challenges in system architecture…

GSM8KHumanEvalLarge Language ModelMath+1

Guaranteed Guess: A Language Modeling Approach for CISC-to-RISC Transpilation with Testing Guarantees

2025-06-17 · Ahmed Heakl, Sarim Hashmi, Chaimaa Abi, Celine Lee 외

The hardware ecosystem is rapidly evolving, with increasing interest in translating low-level programs across different instruction set architectures (ISAs) in a quick, flexible, and correct way to enhance the portabilit…

Code TranslationHumanEvalLanguage ModelingLanguage Modelling+2

LoRA-Mixer: Coordinate Modular LoRA Experts Through Serial Attention Routing

2025-06-17 · Wenbing Li, Zikai Song, Hang Zhou, Yunyao Zhang 외

Recent efforts to combine low-rank adaptation (LoRA) with mixture-of-experts (MoE) for adapting large language models (LLMs) to multiple tasks still exhibit prevailing limitations: they either swap entire attention/feed-…

ARCCoLAGSM8KHumanEval+4

Guideline Forest: Experience-Induced Multi-Guideline Reasoning with Stepwise Aggregation

2025-06-09 · Jiaxiang Chen, Zhuo Wang, Mingxi Zou, Qifan Wang 외

Human reasoning is flexible, adaptive, and grounded in prior experience-qualities that large language models (LLMs) still struggle to emulate. Existing methods either explore diverse reasoning paths at inference time or …

GSM8KHumanEvalMathmbpp

SwiftEval: Developing a Language-Specific Benchmark for LLM-generated Code Evaluation

2025-05-30 · Ivan Petrukha, Yana Kurliak, Nataliia Stulova

In recent years, large language models (LLMs) have showcased significant advancements in code generation. However, most evaluation benchmarks are primarily oriented towards Python, making it difficult to evaluate other p…

Code GenerationHumanEval

Self-Correcting Code Generation Using Small Language Models

2025-05-29 · Jeonghun Cho, Deokhyung Kang, Hyounghun Kim, Gary Geunbae Lee

Self-correction has demonstrated potential in code generation by allowing language models to revise and improve their outputs through successive refinement. Recent studies have explored prompting-based strategies that in…

Code GenerationHumanEvalmbpp

Enhancing LLM-Based Code Generation with Complexity Metrics: A Feedback-Driven Approach

2025-05-29 · Melika Sepidband, Hamed Taherkhani, Song Wang, Hadi Hemmati

Automatic code generation has gained significant momentum with the advent of Large Language Models (LLMs) such as GPT-4. Although many studies focus on improving the effectiveness of LLMs for code generation, very limite…

Code GenerationHumanEvalmbpp

Actor-Critic based Online Data Mixing For Language Model Pre-Training

2025-05-29 · Jing Ma, Chenhao Dang, Mingjie Liao

The coverage and composition of pretraining data significantly impacts the generalization ability of Large Language Models (LLMs). To reduce the carbon footprint and financial costs of training, some data mixing methods,…

HumanEvalLanguage ModelingLanguage ModellingMMLU

An LLM-as-Judge Metric for Bridging the Gap with Human Evaluation in SE Tasks

2025-05-27 · Xin Zhou, Kisub Kim, Ting Zhang, Martin Weyssow 외

Large Language Models (LLMs) and other automated techniques have been increasingly used to support software developers by generating software artifacts such as code snippets, patches, and comments. However, accurately as…

Code GenerationCode SummarizationHumanEvalProgram Repair

Evaluating Large Language Models for Code Review

2025-05-26 · Umut Cihan, Arda İçöz, Vahid Haratian, Eray Tüzün

Context: Code reviews are crucial for software quality. Recent AI advances have allowed large language models (LLMs) to review and fix code; now, there are tools that perform these reviews. However, their reliability and…

HumanEval

LLaDA 1.5: Variance-Reduced Preference Optimization for Large Language Diffusion Models

2025-05-25 · Fengqi Zhu, Rongzhen Wang, Shen Nie, Xiaolu Zhang 외

While Masked Diffusion Models (MDMs), such as LLaDA, present a promising paradigm for language modeling, there has been relatively little effort in aligning these models with human preferences via reinforcement learning.…

GSM8KHumanEvalLanguage ModelingLanguage Modelling+1

From Output to Evaluation: Does Raw Instruction-Tuned Code LLMs Output Suffice for Fill-in-the-Middle Code Generation?

2025-05-24 · Wasi Uddin Ahmad, Somshubra Majumdar, Boris Ginsburg

Post-processing is crucial for the automatic evaluation of LLMs in fill-in-the-middle (FIM) code generation due to the frequent presence of extraneous code in raw outputs. This extraneous generation suggests a lack of aw…

Code GenerationHumanEval

Invisible Entropy: Towards Safe and Efficient Low-Entropy LLM Watermarking

2025-05-20 · Tianle Gu, Zongqi Wang, Kexin Huang, Yuanqi Yao 외

Logit-based LLM watermarking traces and verifies AI-generated content by maintaining green and red token lists and increasing the likelihood of green tokens during generation. However, it fails in low-entropy scenarios, …

HumanEvalmbpp

Prior Prompt Engineering for Reinforcement Fine-Tuning

2025-05-20 · Pittawat Taveekitworachai, Potsawee Manakul, Sarana Nutanong, Kunat Pipatanakul

This paper investigates prior prompt engineering (pPE) in the context of reinforcement fine-tuning (RFT), where language models (LMs) are incentivized to exhibit behaviors that maximize performance through reward signals…

HumanEvalPrompt Engineering

Warm Up Before You Train: Unlocking General Reasoning in Resource-Constrained Settings

2025-05-19 · Safal Shrestha, Minwu Kim, Aadim Nepal, Anubhav Shrestha 외

Designing effective reasoning-capable LLMs typically requires training using Reinforcement Learning with Verifiable Rewards (RLVR) or distillation with carefully curated Long Chain of Thoughts (CoT), both of which depend…

HumanEvalMathMMLU
1–20 / 264 다음 →