Task-Aware LLM Routing with Multi-Level Task-Profile-Guided Data Synthesis for Cold-Start Scenarios

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Liu, Hui, Zou, Bin, Chen, Kecheng, Liu, Jie, Wang, Wenya, Li, Haoliang
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Computation and Language
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

RouteProfile: Graph-Based Profiling for Cold-Start LLM Routing
di: Xu, Jingjun, et al.
Pubblicazione: (2026)

Interpretable Multimodal Misinformation Detection with Logic Reasoning
di: Liu, Hui, et al.
Pubblicazione: (2023)

TELLER: A Trustworthy Framework for Explainable, Generalizable and Controllable Fake News Detection
di: Liu, Hui, et al.
Pubblicazione: (2024)

Beyond Heuristic Prompting: A Concept-Guided Bayesian Framework for Zero-Shot Image Recognition
di: Liu, Hui, et al.
Pubblicazione: (2026)

Disentangling Instruction Influence in Diffusion Transformers for Parallel Multi-Instruction-Guided Image Editing
di: Liu, Hui, et al.
Pubblicazione: (2025)

FlyRoute: Self-Evolving Agent Profiling via Data Flywheel for Adaptive Task Routing
di: Li, Rongjun, et al.
Pubblicazione: (2026)

Modeling Data Diversity for Joint Instance and Verbalizer Selection in Cold-Start Scenarios
di: Chakraborty, Mohna, et al.
Pubblicazione: (2025)

THOR-MoE: Hierarchical Task-Guided and Context-Responsive Routing for Neural Machine Translation
di: Liang, Yunlong, et al.
Pubblicazione: (2025)

Self-Distilled Trajectory-Aware Boltzmann Modeling: Bridging the Training-Inference Discrepancy in Diffusion Language Models
di: Chen, Kecheng, et al.
Pubblicazione: (2026)

EvoSelect: Data-Efficient LLM Evolution for Targeted Task Adaptation
di: Li, Ting-Wei, et al.
Pubblicazione: (2026)

Task-KV: Task-aware KV Cache Optimization via Semantic Differentiation of Attention Heads
di: He, Xingyang, et al.
Pubblicazione: (2025)

Transferring Structure Knowledge: A New Task to Fake news Detection Towards Cold-Start Propagation
di: Wei, Lingwei, et al.
Pubblicazione: (2024)

Beyond Confidence: Adaptive and Coherent Decoding for Diffusion Language Models
di: Chen, Kecheng, et al.
Pubblicazione: (2025)

Unraveling the Mechanics of Learning-Based Demonstration Selection for In-Context Learning
di: Liu, Hui, et al.
Pubblicazione: (2024)

From Parameters to Data: A Task-Parameter-Guided Fine-Tuning Pipeline for Efficient LLM Alignment
di: Chen, Hao, et al.
Pubblicazione: (2026)

POLIS-Bench: Towards Multi-Dimensional Evaluation of LLMs for Bilingual Policy Tasks in Governmental Scenarios
di: Yang, Tingyue, et al.
Pubblicazione: (2025)

AIDE: Attribute-Guided MultI-Hop Data Expansion for Data Scarcity in Task-Specific Fine-tuning
di: Li, Jiayu, et al.
Pubblicazione: (2024)

Multi-Task GRPO: Reliable LLM Reasoning Across Tasks
di: Ramesh, Shyam Sundhar, et al.
Pubblicazione: (2026)

Towards Generalizable Implicit In-Context Learning with Attention Routing
di: Li, Jiaqian, et al.
Pubblicazione: (2025)

NeuroLoRA: Context-Aware Neuromodulation for Parameter-Efficient Multi-Task Adaptation
di: Yang, Yuxin, et al.
Pubblicazione: (2026)

TA&AT: Enhancing Task-Oriented Dialog with Turn-Level Auxiliary Tasks and Action-Tree Based Scheduled Sampling
di: Liu, Longxiang, et al.
Pubblicazione: (2024)

Enhancing Zero-Shot Image Recognition in Vision-Language Models through Human-like Concept Guidance
di: Liu, Hui, et al.
Pubblicazione: (2025)

SAGE-HLS: Syntax-Aware AST-Guided LLM for High-Level Synthesis Code Generation
di: Khan, M Zafir Sadik, et al.
Pubblicazione: (2025)

Cross-Task Experiential Learning on LLM-based Multi-Agent Collaboration
di: Li, Yilong, et al.
Pubblicazione: (2025)

From Myopic Selection to Long-Horizon Awareness: Sequential LLM Routing for Multi-Turn Dialogue
di: Zhang, Jiarui, et al.
Pubblicazione: (2026)

LLM-Driven Multi-Turn Task-Oriented Dialogue Synthesis for Realistic Reasoning
di: Zhu, Yu, et al.
Pubblicazione: (2026)

DESIGNER: Design-Logic-Guided Multidisciplinary Data Synthesis for LLM Reasoning
di: Liu, Weize, et al.
Pubblicazione: (2025)

A Speaker Turn-Aware Multi-Task Adversarial Network for Joint User Satisfaction Estimation and Sentiment Analysis
di: Song, Kaisong, et al.
Pubblicazione: (2024)

AutoTask: Task Aware Multi-Faceted Single Model for Multi-Task Ads Relevance
di: Guo, Shouchang, et al.
Pubblicazione: (2024)

CSRM-LLM: Embracing Multilingual LLMs for Cold-Start Relevance Matching in Emerging E-commerce Markets
di: Wang, Yujing, et al.
Pubblicazione: (2025)

Does In-Context Learning Really Learn? Rethinking How Large Language Models Respond and Solve Tasks via In-Context Learning
di: Long, Quanyu, et al.
Pubblicazione: (2024)

Layer-Aware Task Arithmetic: Disentangling Task-Specific and Instruction-Following Knowledge
di: Chen, Yan-Lun, et al.
Pubblicazione: (2025)

PEMT: Multi-Task Correlation Guided Mixture-of-Experts Enables Parameter-Efficient Transfer Learning
di: Lin, Zhisheng, et al.
Pubblicazione: (2024)

Xpertbench: Expert Level Tasks with Rubrics-Based Evaluation
di: Liu, Xue, et al.
Pubblicazione: (2026)

Cold-Starting Podcast Ads and Promotions with Multi-Task Learning on Spotify
di: Verma, Shivam, et al.
Pubblicazione: (2026)

Textualized Agent-Style Reasoning for Complex Tasks by Multiple Round LLM Generation
di: Liang, Chen, et al.
Pubblicazione: (2024)

Systematic Evaluation of LLM-as-a-Judge in LLM Alignment Tasks: Explainable Metrics and Diverse Prompt Templates
di: Wei, Hui, et al.
Pubblicazione: (2024)

Task-Aware Reduction for Scalable LLM-Database Systems
di: Barnes, Marcus Emmanuel, et al.
Pubblicazione: (2025)

Beyond Sample-Level Feedback: Using Reference-Level Feedback to Guide Data Synthesis
di: Mehri, Shuhaib, et al.
Pubblicazione: (2025)

Which Agent Causes Task Failures and When? On Automated Failure Attribution of LLM Multi-Agent Systems
di: Zhang, Shaokun, et al.
Pubblicazione: (2025)