Copertina

Multi-task Code LLMs: Data Mix or Model Merge?

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Zhu, Mingzhi, Sobolev, Boris, Krishna, Rahul, Pavuluri, Raju, Patterson, Stacy, Merler, Michele
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Computation and Language Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

CRANE: Constrained Reasoning Injection for Code Agents via Nullspace Editing
di: Zhu, Mingzhi, et al.
Pubblicazione: (2026)

Merge to Mix: Mixing Datasets via Model Merging
di: Tao, Zhixu Silvia, et al.
Pubblicazione: (2025)

Mix Data or Merge Models? Balancing the Helpfulness, Honesty, and Harmlessness of Large Language Model via Model Merging
di: Yang, Jinluan, et al.
Pubblicazione: (2025)

Training-free LLM Merging for Multi-task Learning
di: Fu, Zichuan, et al.
Pubblicazione: (2025)

When MOE Meets LLMs: Parameter Efficient Fine-tuning for Multi-task Medical Applications
di: Liu, Qidong, et al.
Pubblicazione: (2023)

From Human Judgements to Predictive Models: Unravelling Acceptability in Code-Mixed Sentences
di: Kodali, Prashant, et al.
Pubblicazione: (2024)

REAM: Merging Improves Pruning of Experts in LLMs
di: Jha, Saurav, et al.
Pubblicazione: (2026)

Granite Code Models: A Family of Open Foundation Models for Code Intelligence
di: Mishra, Mayank, et al.
Pubblicazione: (2024)

Code-Mixer Ya Nahi: Novel Approaches to Measuring Multilingual LLMs' Code-Mixing Capabilities
di: Gupta, Ayushman, et al.
Pubblicazione: (2024)

Pruning via Merging: Compressing LLMs via Manifold Alignment Based Layer Merging
di: Liu, Deyuan, et al.
Pubblicazione: (2024)

Can Small Language Models Handle Context-Summarized Multi-Turn Customer-Service QA? A Synthetic Data-Driven Comparative Evaluation
di: Cooray, Lakshan, et al.
Pubblicazione: (2026)

Generalizable Chain-of-Thought Prompting in Mixed-task Scenarios with Large Language Models
di: Zou, Anni, et al.
Pubblicazione: (2023)

Trustful LLMs: Customizing and Grounding Text Generation with Knowledge Bases and Dual Decoders
di: Zhu, Xiaofeng, et al.
Pubblicazione: (2024)

HM3: Heterogeneous Multi-Class Model Merging
di: Hackmann, Stefan
Pubblicazione: (2024)

The Thinking Spectrum: An Empirical Study of Tunable Reasoning in LLMs through Model Merging
di: Lan, Xiaochong, et al.
Pubblicazione: (2025)

DPPA: Pruning Method for Large Language Model to Model Merging
di: Zhu, Yaochen, et al.
Pubblicazione: (2024)

CTourLLM: Enhancing LLMs with Chinese Tourism Knowledge
di: Wei, Qikai, et al.
Pubblicazione: (2024)

Multi-Stage Evolutionary Model Merging with Meta Data Driven Curriculum Learning for Sentiment-Specialized Large Language Modeling
di: Inoshita, Keito, et al.
Pubblicazione: (2026)

Multi-objective Evolutionary Merging Enables Efficient Reasoning Models
di: Iacobelli, Mario, et al.
Pubblicazione: (2026)

SuperMerge: An Approach For Gradient-Based Model Merging
di: Yang, Haoyu, et al.
Pubblicazione: (2024)

XLGoBench: Detecting cross-lingual skill gaps with algorithmic tasks
di: Jain, Purvam, et al.
Pubblicazione: (2026)

Fake News Detection: Comparative Evaluation of BERT-like Models and Large Language Models with Generative AI-Annotated Data
di: Raza, Shaina, et al.
Pubblicazione: (2024)

How Reliable are LLMs for Reasoning on the Re-ranking task?
di: Islam, Nafis Tanveer, et al.
Pubblicazione: (2025)

Persona-Coded Poly-Encoder: Persona-Guided Multi-Stream Conversational Sentence Scoring
di: Liu, Junfeng, et al.
Pubblicazione: (2023)

Transport and Merge: Cross-Architecture Merging for Large Language Models
di: Cui, Chenhang, et al.
Pubblicazione: (2026)

Deploying Multi-task Online Server with Large Language Model
di: Qu, Yincen, et al.
Pubblicazione: (2024)

Usage, Effects and Requirements for AI Coding Assistants in the Enterprise: An Empirical Study
di: Vukovic, Maja, et al.
Pubblicazione: (2026)

A Critical Study of What Code-LLMs (Do Not) Learn
di: Anand, Abhinav, et al.
Pubblicazione: (2024)

Adapting Language-Specific LLMs to a Reasoning Model in One Day via Model Merging -- An Open Recipe
di: Pipatanakul, Kunat, et al.
Pubblicazione: (2025)

MergeME: Model Merging Techniques for Homogeneous and Heterogeneous MoEs
di: Zhou, Yuhang, et al.
Pubblicazione: (2025)

SE-Merging: A Self-Enhanced Approach for Dynamic Model Merging
di: Chen, Zijun, et al.
Pubblicazione: (2025)

Split, Unlearn, Merge: Leveraging Data Attributes for More Effective Unlearning in LLMs
di: Kadhe, Swanand Ravindra, et al.
Pubblicazione: (2024)

Large Language Model as a Universal Clinical Multi-task Decoder
di: Wu, Yujiang, et al.
Pubblicazione: (2024)

Sens-Merging: Sensitivity-Guided Parameter Balancing for Merging Large Language Models
di: Liu, Shuqi, et al.
Pubblicazione: (2025)

QCG-Rerank: Chunks Graph Rerank with Query Expansion in Retrieval-Augmented LLMs for Tourism Domain
di: Wei, Qikai, et al.
Pubblicazione: (2024)

VisCodex: Unified Multimodal Code Generation via Merging Vision and Coding Models
di: Jiang, Lingjie, et al.
Pubblicazione: (2025)

MetaBench: A Multi-task Benchmark for Assessing LLMs in Metabolomics
di: Lu, Yuxing, et al.
Pubblicazione: (2025)

LoRE-Merging: Exploring Low-Rank Estimation For Large Language Model Merging
di: Liu, Zehua, et al.
Pubblicazione: (2025)

LED-Merging: Mitigating Safety-Utility Conflicts in Model Merging with Location-Election-Disjoint
di: Ma, Qianli, et al.
Pubblicazione: (2025)

AIM: Adaptive Inference of Multi-Modal LLMs via Token Merging and Pruning
di: Zhong, Yiwu, et al.
Pubblicazione: (2024)