Imagen de Portada

D.Va: Validate Your Demonstration First Before You Use It

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Zhang, Qi, Xiao, Zhiqing, Xiao, Ruixuan, Gao, Lirong, Zhao, Junbo
Formato:	Preprint
Publicado:	2025
Materias:	Computation and Language
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

ALPS: Attention Localization and Pruning Strategy for Efficient Alignment of Large Language Models
por: Chen, Hao, et al.
Publicado: (2025)

DORY: Deliberative Prompt Recovery for LLM
por: Gao, Lirong, et al.
Publicado: (2024)

On LLMs-Driven Synthetic Data Generation, Curation, and Evaluation: A Survey
por: Long, Lin, et al.
Publicado: (2024)

FLoE: Fisher-Based Layer Selection for Efficient Sparse Adaptation of Low-Rank Experts
por: Wang, Xinyi, et al.
Publicado: (2025)

Before You Interpret the Profile: Validity Scaling for LLM Metacognitive Self-Report
por: Cacioli, Jon-Paul
Publicado: (2026)

Look Before You Leap: Towards Decision-Aware and Generalizable Tool-Usage for Large Language Models
por: Gui, Anchun, et al.
Publicado: (2024)

Know You Before You Speak: User-State Modeling for LLM Personalization in Multi-Turn Conversation
por: Luo, Jiani, et al.
Publicado: (2026)

FlowBench: Revisiting and Benchmarking Workflow-Guided Planning for LLM-based Agents
por: Xiao, Ruixuan, et al.
Publicado: (2024)

Think Thrice Before You Act: Progressive Thought Refinement in Large Language Models
por: Du, Chengyu, et al.
Publicado: (2024)

Your Students Don't Use LLMs Like You Wish They Did
por: Kobler, Sebastian, et al.
Publicado: (2026)

Look Before You Leap: Autonomous Exploration for LLM Agents
por: Ye, Ziang, et al.
Publicado: (2026)

Screen Before You Interpret: A Portable Validity Protocol for Benchmark-Based LLM Confidence Signals
por: Cacioli, Jon-Paul
Publicado: (2026)

Can LLMs Act as Historians? Evaluating Historical Research Capabilities of LLMs via the Chinese Imperial Examination
por: Gao, Lirong, et al.
Publicado: (2026)

Stop Unnecessary Reflection: Training LRMs for Efficient Reasoning with Adaptive Reflection and Length Coordinated Penalty
por: Yu, Zewei, et al.
Publicado: (2026)

Look Before You Leap: Enhancing Attention and Vigilance Regarding Harmful Content with GuidelineLLM
por: Zhang, Shaoqing, et al.
Publicado: (2024)

Teaching Language Models to Self-Improve through Interactive Demonstrations
por: Yu, Xiao, et al.
Publicado: (2023)

RECOST: External Knowledge Guided Data-efficient Instruction Tuning
por: Zhang, Qi, et al.
Publicado: (2024)

LeTS: Learning to Think-and-Search via Process-and-Outcome Reward Hybridization
por: Zhang, Qi, et al.
Publicado: (2025)

Should You Use Your Large Language Model to Explore or Exploit?
por: Harris, Keegan, et al.
Publicado: (2025)

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

CrossICL: Cross-Task In-Context Learning via Unsupervised Demonstration Transfer
por: Gao, Jinglong, et al.
Publicado: (2025)

Think Before You Prune: Selective Self-Generated Calibration for Pruning Large Reasoning Models
por: Xiang, Yang, et al.
Publicado: (2025)

Thinking Before You Speak: A Proactive Test-time Scaling Approach
por: Liu, Cong, et al.
Publicado: (2025)

Walk Before You Run! Concise LLM Reasoning via Reinforcement Learning
por: Song, Mingyang, et al.
Publicado: (2025)

Listen and Chant Before You Read: The Ladder of Beauty in LM Pre-Training
por: Nomura, Yoshinori
Publicado: (2026)

Self-Train Before You Transcribe
por: Flynn, Robert, et al.
Publicado: (2024)

Talk Before You Retrieve: Agent-Led Discussions for Better RAG in Medical QA
por: Dong, Xuanzhao, et al.
Publicado: (2025)

Cite Before You Speak: Enhancing Context-Response Grounding in E-commerce Conversational LLM-Agents
por: Zeng, Jingying, et al.
Publicado: (2025)

Watch Before You Answer: Learning from Visually Grounded Post-Training
por: Zhang, Yuxuan, et al.
Publicado: (2026)

Shorten After You're Right: Lazy Length Penalties for Reasoning RL
por: Yuan, Danlong, et al.
Publicado: (2025)

SnapKV: LLM Knows What You are Looking for Before Generation
por: Li, Yuhong, et al.
Publicado: (2024)

Think Before You Prune: Self-Reflective Structured Pruning for Reasoning Language Models
por: Wang, Ziyan, et al.
Publicado: (2025)

Are Your LLMs Capable of Stable Reasoning?
por: Liu, Junnan, et al.
Publicado: (2024)

LLMs Corrupt Your Documents When You Delegate
por: Laban, Philippe, et al.
Publicado: (2026)

Think Twice Before You Judge: Mixture of Dual Reasoning Experts for Multimodal Sarcasm Detection
por: Jana, Soumyadeep, et al.
Publicado: (2025)

Check Yourself Before You Wreck Yourself: Selectively Quitting Improves LLM Agent Safety
por: Bonagiri, Vamshi Krishna, et al.
Publicado: (2025)

Divide-or-Conquer? Which Part Should You Distill Your LLM?
por: Wu, Zhuofeng, et al.
Publicado: (2024)

RPDR: A Round-trip Prediction-Based Data Augmentation Framework for Long-Tail Question Answering
por: Zhang, Yiming, et al.
Publicado: (2026)

Think Before You Act: Decision Transformers with Working Memory
por: Kang, Jikun, et al.
Publicado: (2023)

Think Before You Lie: How Reasoning Leads to Honesty
por: Yuan, Ann, et al.
Publicado: (2026)