Papers by Naibo Wang

2 papers
RIPRAG: Hack a Black-box Retrieval-Augmented Generation Question-Answering System with Reinforcement Learning (2026.findings-acl)

Copied to clipboard

Challenge: Existing methods to generate RAG documents require knowledge of the target RAG system’s internal composition and implementation details, whereas black-box methods are unable to utilize interactive information.
Approach: They propose a RIPRAG attack framework that treats the target RAG system as a black box and leverages a Reinforcement Learning from Black-box Feedback (RLBF) method to optimize the generation model for poisoned documents.
Outcome: The proposed method achieves an attack success rate (ASR) improvement of up to 0.72 compared to baseline methods.
AgentPro: Enhancing LLM Agents with Automated Process Supervision (2025.emnlp-main)

Copied to clipboard

Challenge: Existing frameworks lack explicit supervision during the reasoning process, which may lead to error propagation across reasoning chains.
Approach: They propose a framework which automates process supervision for large language model agents by automatically generating step-level annotations and developing a process reward model based on these annotations.
Outcome: The proposed framework outperforms existing agent-based methods on four datasets and achieves a 6.32% increase in accuracy.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations