Cover Image

No Prompt Left Behind: Exploiting Zero-Variance Prompts in LLM Reinforcement Learning via Entropy-Guided Advantage Shaping

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Le, Thanh-Long V., Jeon, Myeongho, Vu, Kim, Lai, Viet, Yang, Eunho
Format:	Preprint
Published:	2025
Subjects:	Computation and Language Artificial Intelligence Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

PromptKD: Distilling Student-Friendly Knowledge for Generative Language Models via Prompt Tuning
by: Kim, Gyeongman, et al.
Published: (2024)

Memory-Based Advantage Shaping for LLM-Guided Reinforcement Learning
by: Nourzad, Narjes, et al.
Published: (2026)

Adaptive Prompting for Continual Relation Extraction: A Within-Task Variance Perspective
by: Le, Minh, et al.
Published: (2024)

Manipulating LLM Web Agents with Indirect Prompt Injection Attack via HTML Accessibility Tree
by: Johnson, Sam, et al.
Published: (2025)

When Weak LLMs Speak with Confidence, Preference Alignment Gets Stronger
by: Afzali, Amirabbas, et al.
Published: (2026)

Stable-TTS: Stable Speaker-Adaptive Text-to-Speech Synthesis via Prosody Prompting
by: Han, Wooseok, et al.
Published: (2024)

No Token Left Behind: Reliable KV Cache Compression via Importance-Aware Mixed Precision Quantization
by: Yang, June Yong, et al.
Published: (2024)

Affordance-Guided Reinforcement Learning via Visual Prompting
by: Lee, Olivia Y., et al.
Published: (2024)

PromptDSI: Prompt-based Rehearsal-free Continual Learning for Document Retrieval
by: Huynh, Tuan-Luc, et al.
Published: (2024)

Preference-Guided Learning for Sparse-Reward Multi-Agent Reinforcement Learning
by: Bui, The Viet, et al.
Published: (2025)

Multi-agent Deep Reinforcement Learning for Distributed Load Restoration
by: Vu, Linh, et al.
Published: (2023)

PARASITE: Conditional System Prompt Poisoning to Hijack LLMs
by: Pham, Viet, et al.
Published: (2025)

Reinforcement Learning of Structured Control for Linear Systems with Unknown State Matrix
by: Mukherjee, Sayak, et al.
Published: (2020)

ConsPrompt: Exploiting Contrastive Samples for Fewshot Prompt Learning
by: Weng, Jinta, et al.
Published: (2022)

REP: Resource-Efficient Prompting for Rehearsal-Free Continual Learning
by: Jeon, Sungho, et al.
Published: (2024)

Formalization Driven LLM Prompt Jailbreaking via Reinforcement Learning
by: Wang, Zhaoqi, et al.
Published: (2025)

Prompt Optimization for LLM Code Generation via Reinforcement Learning
by: Esfahani, Ali Mohammadi, et al.
Published: (2026)

EntroAD: Structural Entropy-Guided Prompt Adaptation for Zero-Shot Anomaly Detection
by: Zhao, Xinyu, et al.
Published: (2026)

Reinforcement Learning for Diffusion LLMs with Entropy-Guided Step Selection and Stepwise Advantages
by: Kunde, Vishnu Teja, et al.
Published: (2026)

Explore Data Left Behind in Reinforcement Learning for Reasoning Language Models
by: Liu, Chenxi, et al.
Published: (2025)

StablePrompt: Automatic Prompt Tuning using Reinforcement Learning for Large Language Models
by: Kwon, Minchan, et al.
Published: (2024)

Feature-aligned N-BEATS with Sinkhorn divergence
by: Lee, Joonhun, et al.
Published: (2023)

Weak-to-Strong Generalization under Distribution Shifts
by: Jeon, Myeongho, et al.
Published: (2025)

An Analysis of Model Robustness across Concurrent Distribution Shifts
by: Jeon, Myeongho, et al.
Published: (2025)

Discrete Prompt Compression with Reinforcement Learning
by: Jung, Hoyoun, et al.
Published: (2023)

PromptMoE: Generalizable Zero-Shot Anomaly Detection via Visually-Guided Prompt Mixtures
by: Shao, Yuheng, et al.
Published: (2025)

Preserving Clusters in Prompt Learning for Unsupervised Domain Adaptation
by: Vuong, Tung-Long, et al.
Published: (2025)

EchoLeak: The First Real-World Zero-Click Prompt Injection Exploit in a Production LLM System
by: Reddy, Pavan, et al.
Published: (2025)

Med-PerSAM: One-Shot Visual Prompt Tuning for Personalized Segment Anything Model in Medical Domain
by: Yoon, Hangyul, et al.
Published: (2024)

What Happens to the Learning Outcomes of Left‐Behind Children When Parents are Away? Evidence From Four Pacific Island Countries
by: Trang Thu Vu, et al.
Published: (2025)

LLM-based Dynamic Differential Testing for Database Connectors with Reinforcement Learning-Guided Prompt Selection
by: Lyu, Ce, et al.
Published: (2025)

No Country Left Behind
by: Powell, Colin L
Published: (2005)

No Parent Left Behind
by: Brodie, Carolyn S., et al.
Published: (2006)

GuruAgents: Emulating Wise Investors with Prompt-Guided LLM Agents
by: Kim, Yejin, et al.
Published: (2025)

Prompt-Induced Score Variance in Zero-Shot Binary Vision-Language Safety Classification
by: Weng, Charles, et al.
Published: (2026)

Efficient and Effective Vocabulary Expansion Towards Multilingual Large Language Models
by: Kim, Seungduk, et al.
Published: (2024)

DVAO: Dynamic Variance-adaptive Advantage Optimization for Multi-reward Reinforcement Learning
by: Jiang, Guochao, et al.
Published: (2026)

Prompt-in-Content Attacks: Exploiting Uploaded Inputs to Hijack LLM Behavior
by: Lian, Zhuotao, et al.
Published: (2025)

EZ-HOI: VLM Adaptation via Guided Prompt Learning for Zero-Shot HOI Detection
by: Lei, Qinqian, et al.
Published: (2024)

WAVE++: Capturing Within-Task Variance for Continual Relation Extraction with Adaptive Prompting
by: Dao, Bao-Ngoc, et al.
Published: (2025)