Projects

MARVEL ACL 2024 (oral)

MARVEL: Unlocking the Multi-Modal Capability of Dense Retrieval via Visual Module Plugin

NeuScraper ACL 2024 (oral)

Cleaner Pretraining Corpus Curation with Neural Web Scraping

INTERVENOR ACL 2024

INTERVENOR: Prompt the Coding Ability of Large Language Models with the Interactive Chain of Repairing

SANTA ACL 2023

Structure-Aware Language Model Pretraining Improves Dense Retrieval on Structured Data

OpenMatch SIGIR 2023

An Open-Source Package for Information Retrieval

P3Ranker SIGIR 2022

P3 Ranker: Mitigating the Gaps between Pre-training and Ranking Fine-tuning with Prompt-based Learning and Pre-finetuning

UniVL-DR ICLR 2023

Universal Vision-Language Dense Retrieval: Learning A Unified Representation Space for Multi-Modal Retrieval

Self-Guide CCL 2024

Self-Guide: A LLM Reasoning Enhancement Method Based on Self-Guided Planning

TASTE CIKM 2023

Text Matching Improves Sequential Recommendation by Reducing Popularity Biases

ConAE EMNLP 2022

Dimension Reduction for Efficient Dense Retrieval via Conditional Autoencoder

FiT5 COLING 2024

Fusion-in-T5: Unifying Variant Signals for Simple and Effective Document Ranking with Attention Fusion

CO-GAT TBD 2024

Multi-Evidence based Fact Verification via A Confidential Graph Neural Network

ActiveRAG

Revealing the Treasures of Knowledge via Active Learning

DebugEval

Enhancing the Code Debugging Ability of LLMs via Communicative Agent Based Data Refinement