Cover Image

Inverse Reinforcement Learning with Dynamic Reward Scaling for LLM Alignment

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Cheng, Ruoxi, Ma, Haoxuan, Wang, Weixin, Duan, Ranjie, Liu, Jiexi, Jia, Xiaoshuang, Qin, Simeng, Cao, Xiaochun, Liu, Yang, Jia, Xiaojun
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

PBI-Attack: Prior-Guided Bimodal Interactive Black-Box Jailbreak Attack for Toxicity Maximization
by: Cheng, Ruoxi, et al.
Published: (2024)

SeCon-RAG: A Two-Stage Semantic Filtering and Conflict-Free Framework for Trustworthy RAG
by: Si, Xiaonan, et al.
Published: (2025)

Obscure but Effective: Classical Chinese Jailbreak Prompt Optimization via Bio-Inspired Search
by: Huang, Xun, et al.
Published: (2026)

GeoShield: Safeguarding Geolocation Privacy from Vision-Language Models via Adversarial Perturbations
by: Liu, Xinwei, et al.
Published: (2025)

Reasoning as an Attack Surface: Adaptive Evolutionary CoT Jailbreaks for LLMs
by: Li, Jianan, et al.
Published: (2026)

ODAR: Principled Adaptive Routing for LLM Reasoning via Active Inference
by: Ma, Siyuan, et al.
Published: (2026)

Dynamic Policy Induction for Adaptive Prompt Optimization: Bridging the Efficiency-Accuracy Gap via Lightweight Reinforcement Learning
by: Xu, Jiexi
Published: (2025)

AGR: Age Group fairness Reward for Bias Mitigation in LLMs
by: Cao, Shuirong, et al.
Published: (2024)

Heuristic-Induced Multimodal Risk Distribution Jailbreak Attack for Multimodal Large Language Models
by: Teng, Ma, et al.
Published: (2024)

Strata-Sword: A Hierarchical Safety Evaluation towards LLMs based on Reasoning Complexity of Jailbreak Instructions
by: Zhao, Shiji, et al.
Published: (2025)

Oyster-I: Beyond Refusal -- Constructive Safety Alignment for Responsible Language Models
by: Duan, Ranjie, et al.
Published: (2025)

Evolution-based Region Adversarial Prompt Learning for Robustness Enhancement in Vision-Language Models
by: Jia, Xiaojun, et al.
Published: (2025)

No Query, No Access
by: Wang, Wenqiang, et al.
Published: (2025)

Text Style Transfer with Parameter-efficient LLM Finetuning and Round-trip Translation
by: Liu, Ruoxi, et al.
Published: (2026)

Teaching LLM to be Persuasive: Reward-Enhanced Policy Optimization for Alignment from Heterogeneous Rewards
by: Zeng, Xia, et al.
Published: (2025)

Not All Tokens Matter: Towards Efficient LLM Reasoning via Token Significance in Reinforcement Learning
by: Liu, Hanbing, et al.
Published: (2025)

SelfPrompt: Autonomously Evaluating LLM Robustness via Domain-Constrained Knowledge Guidelines and Refined Adversarial Prompts
by: Pei, Aihua, et al.
Published: (2024)

OmniSafeBench-MM: A Unified Benchmark and Toolbox for Multimodal Jailbreak Attack-Defense Evaluation
by: Jia, Xiaojun, et al.
Published: (2025)

Targeting Misalignment: A Conflict-Aware Framework for Reward-Model-based LLM Alignment
by: Liu, Zixuan, et al.
Published: (2025)

MESA: Improving MoE Safety Alignment via Decentralized Expertise
by: Sun, Yitong, et al.
Published: (2026)

R-Search: Empowering LLM Reasoning with Search via Multi-Reward Reinforcement Learning
by: Zhao, Qingfei, et al.
Published: (2025)

Learning to Optimize Multi-Objective Alignment Through Dynamic Reward Weighting
by: Lu, Yining, et al.
Published: (2025)

Generalizing Reward Modeling for Out-of-Distribution Preference Learning
by: Jia, Chen
Published: (2024)

SkillJect: Effectively Automating Skill-Based Prompt Injection for Skill-Enabled Agents
by: Jia, Xiaojun, et al.
Published: (2026)

DAPO: An Open-Source LLM Reinforcement Learning System at Scale
by: Yu, Qiying, et al.
Published: (2025)

EcoAlign: An Economically Rational Framework for Efficient LVLM Alignment
by: Cheng, Ruoxi, et al.
Published: (2025)

Improved Techniques for Optimization-Based Jailbreaking on Large Language Models
by: Jia, Xiaojun, et al.
Published: (2024)

SGHA-Attack: Semantic-Guided Hierarchical Alignment for Transferable Targeted Attacks on Vision-Language Models
by: Wang, Haobo, et al.
Published: (2026)

Insights from the Inverse: Reconstructing LLM Training Goals Through Inverse Reinforcement Learning
by: Joselowitz, Jared, et al.
Published: (2024)

Reinforcement Learning with Conditional Expectation Reward
by: Xiao, Changyi, et al.
Published: (2026)

Consistent Paths Lead to Truth: Self-Rewarding Reinforcement Learning for LLM Reasoning
by: Zhang, Kongcheng, et al.
Published: (2025)

Directional Alignment Mitigates Reward Hacking in Reinforcement Learning for Language Models
by: Deng, Wenlong, et al.
Published: (2026)

Progtuning: Progressive Fine-tuning Framework for Transformer-based Language Models
by: Ji, Xiaoshuang, et al.
Published: (2025)

Reinforcement Learning with Semantic Rewards Enables Low-Resource Language Expansion without Alignment Tax
by: Su, Zeli, et al.
Published: (2026)

STAIR: Improving Safety Alignment with Introspective Reasoning
by: Zhang, Yichi, et al.
Published: (2025)

AlphaPO: Reward Shape Matters for LLM Alignment
by: Gupta, Aman, et al.
Published: (2025)

RMB: Comprehensively Benchmarking Reward Models in LLM Alignment
by: Zhou, Enyu, et al.
Published: (2024)

Dynamic Optimizations of LLM Ensembles with Two-Stage Reinforcement Learning Agents
by: Tekin, Selim Furkan, et al.
Published: (2025)

The Past Is Not Past: Memory-Enhanced Dynamic Reward Shaping
by: Liu, Yang, et al.
Published: (2026)

Agentic Reinforcement Learning with Implicit Step Rewards
by: Liu, Xiaoqian, et al.
Published: (2025)