Papers mbpp
“mbpp” 태그가 달린 논문 129편 · 필터 해제
any4: Learned 4-bit Numeric Representation for LLMs
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+2EvoAgentX: An Automated Framework for Evolving Agentic Workflows
Multi-agent systems (MAS) have emerged as a powerful paradigm for orchestrating large language models (LLMs) and specialized tools to collaboratively address complex tasks. However, existing MAS frameworks often require …
Code GenerationMathMathematical Problem-SolvingmbppSACL: Understanding and Combating Textual Bias in Code Retrieval with Semantic-Augmented Reranking and Localization
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+1Plan for Speed -- Dilated Scheduling for Masked Diffusion Language Models
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+3Enhancing Reasoning Capabilities of Small Language Models with Blueprints and Prompt Template Search
Small language models (SLMs) offer promising and efficient alternatives to large language models (LLMs). However, SLMs' limited capacity restricts their reasoning capabilities and makes them sensitive to prompt variation…
GSM8KMathmbppGuideline Forest: Experience-Induced Multi-Guideline Reasoning with Stepwise Aggregation
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 …
GSM8KHumanEvalMathmbppSelf-Correcting Code Generation Using Small Language Models
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 GenerationHumanEvalmbppEnhancing LLM-Based Code Generation with Complexity Metrics: A Feedback-Driven Approach
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 GenerationHumanEvalmbppLLaDA 1.5: Variance-Reduced Preference Optimization for Large Language Diffusion Models
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+1Invisible Entropy: Towards Safe and Efficient Low-Entropy LLM Watermarking
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, …
HumanEvalmbppRethinking Repetition Problems of LLMs in Code Generation
With the advent of neural language models, the performance of code generation has been significantly boosted. However, the problem of repetitions during the generation process continues to linger. Previous work has prima…
Code GenerationHumanEvalmbppReinforcing the Diffusion Chain of Lateral Thought with Diffusion Language Models
We introduce the Diffusion Chain of Lateral Thought (DCoLT), a reasoning framework for diffusion language models. DCoLT treats each intermediate step in the reverse diffusion process as a latent "thinking" action and opt…
Code GenerationGSM8KHumanEvalMath+2Web-Bench: A LLM Code Benchmark Based on Web Standards and Frameworks
The application of large language models (LLMs) in the field of coding is evolving rapidly: from code assistants, to autonomous coding agents, and then to generating complete projects through natural language. Early LLM …
Code GenerationHumanEvalmbppCodeMixBench: Evaluating Large Language Models on Code Generation with Code-Mixed Prompts
Large Language Models (LLMs) have achieved remarkable success in code generation tasks, powering various applications like code completion, debugging, and programming assistance. However, existing benchmarks such as Huma…
Code CompletionCode GenerationHumanEvalmbppDataDecide: How to Predict Best Pretraining Data with Small Experiments
Because large language models are expensive to pretrain on different datasets, using smaller-scale experiments to decide on data is crucial for reducing costs. Which benchmarks and methods of making decisions from observ…
ARCHellaSwagHumanEvalmbpp+1Two Heads are Better Than One: Test-time Scaling of Multi-agent Collaborative Reasoning
Multi-agent systems (MAS) built on large language models (LLMs) offer a promising path toward solving complex, real-world tasks that single-agent systems often struggle to manage. While recent advancements in test-time s…
Mathematical ReasoningmbppType-Constrained Code Generation with Language Models
Large language models (LLMs) have achieved notable success in code generation. However, they still frequently produce uncompilable output because their next-token inference procedure does not model formal aspects of code…
Code GenerationHumanEvalmbppOpenCodeInstruct: A Large-scale Instruction Tuning Dataset for Code LLMs
Large Language Models (LLMs) have transformed software development by enabling code generation, automated debugging, and complex reasoning. However, their continued advancement is constrained by the scarcity of high-qual…
Code GenerationHumanEvalmbppDynaCode: A Dynamic Complexity-Aware Code Benchmark for Evaluating Large Language Models in Code Generation
The rapid advancement of large language models (LLMs) has significantly improved their performance in code generation tasks. However, existing code benchmarks remain static, consisting of fixed datasets with predefined p…
Code GenerationmbppMemorizationGrammar-Based Code Representation: Is It a Worthy Pursuit for LLMs?
Grammar serves as a cornerstone in programming languages and software engineering, providing frameworks to define the syntactic space and program structure. Existing research demonstrates the effectiveness of grammar-bas…
Code GenerationHumanEvalmbpp