Copertina

Mixture-of-Skills: Learning to Optimize Data Usage for Fine-Tuning Large Language Models

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Wu, Minghao, Vu, Thuy-Trang, Qu, Lizhen, Haffari, Gholamreza
Natura:	Preprint
Pubblicazione:	2024
Soggetti:	Computation and Language
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

The Best of Both Worlds: Bridging Quality and Diversity in Data Selection with Bipartite Graph
di: Wu, Minghao, et al.
Pubblicazione: (2024)

Adapting Large Language Models for Document-Level Machine Translation
di: Wu, Minghao, et al.
Pubblicazione: (2024)

SCAR: Data Selection via Style Consistency-Aware Response Ranking for Efficient Instruction-Tuning of Large Language Models
di: Li, Zhuang, et al.
Pubblicazione: (2024)

Conversational SimulMT: Efficient Simultaneous Translation with Large Language Models
di: Wang, Minghan, et al.
Pubblicazione: (2024)

Assistive Large Language Model Agents for Socially-Aware Negotiation Dialogues
di: Hua, Yuncheng, et al.
Pubblicazione: (2024)

Continual Learning for Large Language Models: A Survey
di: Wu, Tongtong, et al.
Pubblicazione: (2024)

Simultaneous Machine Translation with Large Language Models
di: Wang, Minghan, et al.
Pubblicazione: (2023)

Importance-Aware Data Augmentation for Document-Level Neural Machine Translation
di: Wu, Minghao, et al.
Pubblicazione: (2024)

Jigsaw Puzzles: Splitting Harmful Questions to Jailbreak Large Language Models
di: Yang, Hao, et al.
Pubblicazione: (2024)

AIPO: Learning to Reason from Active Interaction
di: Liu, Junnan, et al.
Pubblicazione: (2026)

Discrete Minds in a Continuous World: Do Language Models Know Time Passes?
di: Wang, Minghan, et al.
Pubblicazione: (2025)

SituatedThinker: Grounding LLM Reasoning with Real-World through Situated Thinking
di: Liu, Junnan, et al.
Pubblicazione: (2025)

Towards Inference-time Scaling for Continuous Space Reasoning
di: Wang, Minghan, et al.
Pubblicazione: (2025)

Beyond Imitation: Recovering Dense Rewards from Demonstrations
di: Li, Jiangnan, et al.
Pubblicazione: (2025)

Reshaping Representation Space to Balance the Safety and Over-rejection in Large Audio Language Models
di: Yang, Hao, et al.
Pubblicazione: (2025)

Active Continual Learning: On Balancing Knowledge Retention and Learnability
di: Vu, Thuy-Trang, et al.
Pubblicazione: (2023)

Extending LLMs to New Languages: A Case Study of Llama and Persian Adaptation
di: Sani, Samin Mahdizadeh, et al.
Pubblicazione: (2024)

Exploring the Potential of Multimodal LLM with Knowledge-Intensive Multimodal ASR
di: Wang, Minghan, et al.
Pubblicazione: (2024)

On the Reliability of Large Language Models for Causal Discovery
di: Feng, Tao, et al.
Pubblicazione: (2024)

Audio Is the Achilles' Heel: Red Teaming Audio Large Multimodal Models
di: Yang, Hao, et al.
Pubblicazione: (2024)

Towards Probing Speech-Specific Risks in Large Multimodal Models: A Taxonomy, Benchmark, and Insights
di: Yang, Hao, et al.
Pubblicazione: (2024)

SpeechDialogueFactory: Generating High-Quality Speech Dialogue Data to Accelerate Your Speech-LLM Development
di: Wang, Minghan, et al.
Pubblicazione: (2025)

IRIS: An Iterative and Integrated Framework for Verifiable Causal Discovery in the Absence of Tabular Data
di: Feng, Tao, et al.
Pubblicazione: (2025)

GTS: Inference-Time Scaling of Latent Reasoning with a Learnable Gaussian Thought Sampler
di: Wang, Minghan, et al.
Pubblicazione: (2026)

Resurfacing Paralinguistic Awareness in Large Audio Language Models
di: Yang, Hao, et al.
Pubblicazione: (2026)

LiveCultureBench: a Multi-Agent, Multi-Cultural Benchmark for Large Language Models in Dynamic Social Simulations
di: Pham, Viet-Thanh, et al.
Pubblicazione: (2026)

CausalScore: An Automatic Reference-Free Metric for Assessing Response Relevance in Open-Domain Dialogue Systems
di: Feng, Tao, et al.
Pubblicazione: (2024)

Zero-Shot Privacy-Aware Text Rewriting via Iterative Tree Search
di: Huang, Shuo, et al.
Pubblicazione: (2025)

CONGRAD:Conflicting Gradient Filtering for Multilingual Preference Alignment
di: Li, Jiangnan, et al.
Pubblicazione: (2025)

RIDE: Enhancing Large Language Model Alignment through Restyled In-Context Learning Demonstration Exemplars
di: Hua, Yuncheng, et al.
Pubblicazione: (2025)

IMO: Greedy Layer-Wise Sparse Representation Learning for Out-of-Distribution Text Classification with Pre-trained Models
di: Feng, Tao, et al.
Pubblicazione: (2024)

HBO: Hierarchical Balancing Optimization for Fine-Tuning Large Language Models
di: Wang, Weixuan, et al.
Pubblicazione: (2025)

Direct Evaluation of Chain-of-Thought in Multi-hop Reasoning with Knowledge Graphs
di: Nguyen, Minh-Vuong, et al.
Pubblicazione: (2024)

Proverbs Run in Pairs: Evaluating Proverb Translation Capability of Large Language Model
di: Wang, Minghan, et al.
Pubblicazione: (2025)

Reasoning on Graphs: Faithful and Interpretable Large Language Model Reasoning
di: Luo, Linhao, et al.
Pubblicazione: (2023)

Simple Yet Effective: Extracting Private Data Across Clients in Federated Fine-Tuning of Large Language Models
di: Hu, Yingqi, et al.
Pubblicazione: (2025)

Discourse Graph Guided Document Translation with Large Language Models
di: Pham, Viet-Thanh, et al.
Pubblicazione: (2025)

NAP^2: A Benchmark for Naturalness and Privacy-Preserving Text Rewriting by Learning from Human
di: Huang, Shuo, et al.
Pubblicazione: (2024)

Graph-constrained Reasoning: Faithful Reasoning on Knowledge Graphs with Large Language Models
di: Luo, Linhao, et al.
Pubblicazione: (2024)

Evidence-based Distributional Alignment for Large Language Models
di: Pham, Viet-Thanh, et al.
Pubblicazione: (2026)