Cover Image

Training-free LLM Verification via Recycling Few-shot Examples

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Lee, Dongseok, Hong, Jimyung, Kim, Dongyoung, Kim, Jaehyung
Format:	Preprint
Published:	2025
Subjects:	Machine Learning Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Diet Your LLM: Dimension-wise Global Pruning of LLMs via Merging Task-specific Importance Score
by: Hong, Jimyung, et al.
Published: (2026)

Spread Preference Annotation: Direct Preference Judgment for Efficient LLM Alignment
by: Kim, Dongyoung, et al.
Published: (2024)

Few-shot Personalization of LLMs with Mis-aligned Responses
by: Kim, Jaehyung, et al.
Published: (2024)

Debiasing Online Preference Learning via Preference Feature Preservation
by: Kim, Dongyoung, et al.
Published: (2025)

Learning to Correct for QA Reasoning with Black-box LLMs
by: Kim, Jaehyung, et al.
Published: (2024)

LaRA: Layer-wise Representation Analysis for Detecting Data Contamination in RL Post-Training
by: Gwak, Minju, et al.
Published: (2026)

The Amazing Agent Race: Strong Tool Users, Weak Navigators
by: Kim, Zae Myung, et al.
Published: (2026)

A Ridge Too Far: Correcting Over-Shrinkage via Negative Regularization
by: Kim, Dongseok, et al.
Published: (2025)

Enhancing Instruction Following of LLMs via Activation Steering with Dynamic Rejection
by: Kang, Minjae, et al.
Published: (2026)

Verifier-free Test-Time Sampling for Vision Language Action Models
by: Jang, Suhyeok, et al.
Published: (2025)

Structural Reasoning Improves Molecular Understanding of LLM
by: Jang, Yunhui, et al.
Published: (2024)

MemLoss: Enhancing Adversarial Training with Recycling Adversarial Examples
by: Mahdi, Soroush, et al.
Published: (2025)

Efficient LLM Collaboration via Planning
by: Lee, Byeongchan, et al.
Published: (2025)

Episodic-free Task Selection for Few-shot Learning
by: Zhang, Tao
Published: (2024)

Gap-K%: Measuring Top-1 Prediction Gap for Detecting Pretraining Data
by: Kwak, Minseo, et al.
Published: (2026)

ICPL: Few-shot In-context Preference Learning via LLMs
by: Yu, Chao, et al.
Published: (2024)

Learning from the Undesirable: Robust Adaptation of Language Models without Forgetting
by: Nam, Yunhun, et al.
Published: (2025)

Optimized Feature Generation for Tabular Data via LLMs with Decision Tree Reasoning
by: Nam, Jaehyun, et al.
Published: (2024)

Accelerating Reinforcement Learning with Value-Conditional State Entropy Exploration
by: Kim, Dongyoung, et al.
Published: (2023)

Few-shot Steerable Alignment: Adapting Rewards and LLM Policies with Neural Processes
by: Kobalczyk, Katarzyna, et al.
Published: (2024)

Grouped Differential Attention
by: Lim, Junghwan, et al.
Published: (2025)

Dynamic User-controllable Privacy-preserving Few-shot Sensing Framework
by: Chathoth, Ajesh Koyatan, et al.
Published: (2025)

Dynamic Tokenization via Reinforcement Patching: End-to-end Training and Zero-shot Transfer
by: Wu, Yulun, et al.
Published: (2026)

QUICK: Quantization-aware Interleaving and Conflict-free Kernel for efficient LLM inference
by: Kim, Taesu, et al.
Published: (2024)

Meta-Controller: Few-Shot Imitation of Unseen Embodiments and Tasks in Continuous Control
by: Cho, Seongwoong, et al.
Published: (2024)

CUBE: Contrastive Understanding by Balanced Experiments
by: Kim, Dongseok, et al.
Published: (2025)

Towards Efficient Few-shot Graph Neural Architecture Search via Partitioning Gradient Contribution
by: Song, Wenhao, et al.
Published: (2025)

To FP8 and Back Again: Quantifying Reduced Precision Effects on LLM Training Stability
by: Lee, Joonhyung, et al.
Published: (2024)

AnomalyLLM: Few-shot Anomaly Edge Detection for Dynamic Graphs using Large Language Models
by: Liu, Shuo, et al.
Published: (2024)

Forget and Explain: Transparent Verification of GNN Unlearning
by: Ahsan, Imran, et al.
Published: (2025)

From Street to Orbit: Training-Free Cross-View Retrieval via Location Semantics and LLM Guidance
by: Min, Jeongho, et al.
Published: (2025)

Does Prior Data Matter? Exploring Joint Training in the Context of Few-Shot Class-Incremental Learning
by: Kim, Shiwon, et al.
Published: (2025)

Fast and Fluent Diffusion Language Models via Convolutional Decoding and Rejective Fine-tuning
by: Seo, Yeongbin, et al.
Published: (2025)

Provably Robust Pre-Trained Ensembles for Biomarker-Based Cancer Classification
by: Lee, Chongmin, et al.
Published: (2024)

Towards Few-shot Self-explaining Graph Neural Networks
by: Peng, Jingyu, et al.
Published: (2024)

HyperFlow: Gradient-Free Emulation of Few-Shot Fine-Tuning
by: Kim, Donggyun, et al.
Published: (2025)

How Prompts Move Language Model Behavior: Frames, Salience, and Construal as Semantic Control
by: Kim, Dongseok, et al.
Published: (2025)

Neural Force Field: Few-shot Learning of Generalized Physical Reasoning
by: Li, Shiqian, et al.
Published: (2025)

Large Language Models are Few-shot Multivariate Time Series Classifiers
by: Chen, Yakun, et al.
Published: (2025)

TransNet: Transfer Knowledge for Few-shot Knowledge Graph Completion
by: Liu, Lihui, et al.
Published: (2025)