Papers by Haojie Wei

5 papers
AgentV-RL: Scaling Reward Modeling with Agentic Verifier (2026.findings-acl)

Copied to clipboard

Challenge: Existing approaches to improve LLM reasoning are limited in complex domains and lack external grounding makes verifiers unreliable on computation-intensive tasks.
Approach: They propose a framework that transforms reward modeling into a multi-turn, tool-augmented deliberative process.
Outcome: The proposed framework surpasses state-of-the-art ORMs by 25.2% under parallel and sequential TTS.
Unveiling and Consulting Core Experts in Retrieval-Augmented MoE-based LLMs (2024.emnlp-main)

Copied to clipboard

Challenge: Existing research seeks to enhance RAG performance by retrieving higher-quality documents or designing RAG-specific LLMs, but internal mechanisms that contribute to RAG’s effectiveness remain underexplored.
Approach: They propose to examine the internal mechanisms within the popular Mixture-of-Expert (MoE)-based LLMs and examine their ability to improve RAG by examining expert activations.
Outcome: The proposed method significantly improved the ability of Large Language Models (LLMs) to solve knowledge-intensive tasks.
RACQC: Advanced Retrieval-Augmented Generation for Chinese Query Correction (2025.findings-emnlp)

Copied to clipboard

Challenge: Large language models (LLMs) exhibit remarkable capabilities across many tasks, but face critical challenges in the CSC scenario: (1) poor generalization to rare entities in open-domain searches; and (2) failure to adapt to temporal entity variations due to static parameters, resulting in serious over-correction issues.
Approach: They propose a Chinese Spelling Check system with RAG and multi-task learning that integrates dynamic knowledge retrieval and entity-centric RAG to address rare entities.
Outcome: The proposed system outperforms existing baselines in the CSC task and achieves a maximum improvement of +9.92% on the search scenario benchmark and +3.2% on the general-domain dataset.
Beyond Dialogue: A Profile-Dialogue Alignment Framework Towards General Role-Playing Language Model (2025.acl-long)

Copied to clipboard

Challenge: Existing role-playing training methods often lack profile-dialogue alignment at the sentence level.
Approach: They propose a framework that aligns dialogue with profile traits for each scenario, eliminating biases during training.
Outcome: The proposed model outperforms most proprietary role-playing models and is fully automated and low-cost.
Matching Article Pairs with Graphical Decomposition and Convolutions (P19-1)

Copied to clipboard

Challenge: Existing methods for matching sentence pairs do not perform well in longer documents . Existing approaches for matching sentences do not work in longer document understanding tasks .
Approach: They propose to model article pairs by comparing sentences that enclose same concept vertex . they propose to use a concept interaction graph to match articles by encoding sentences .
Outcome: The proposed methods show significant improvements over existing methods . the proposed datasets consist of 30K pairs of breaking news articles .

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