5 papers
HC-RAG: Evidence-Centric Retrieval-Augmented Generation over Heterogeneous Financial Filings
Siyuan Chen, Huaye Tan, You Li +1
Financial question answering over annual reports requires more than retrieving semantically similar passages. It often involves identifying relevant companies and fiscal years, loc…
CAGE-SGG: Counterfactual Active Graph Evidence for Open-Vocabulary Scene Graph Generation
Suiyang Guang, Chenyu Liu, Ruohan Zhang +1
Open-vocabulary scene graph generation (SGG) aims to describe visual scenes with flexible and fine-grained relation phrases beyond a fixed predicate vocabulary. While recent vision…
Aligning by Misaligning: Boundary-aware Curriculum Learning for Multimodal Alignment
Hua Ye, Hang Ding, Siyuan Chen +3
Most multimodal models treat every negative pair alike, ignoring the ambiguous negatives that differ from the positive by only a small detail. We propose Boundary-Aware Curriculum…
Synergy over Discrepancy: A Partition-Based Approach to Multi-Domain LLM Fine-Tuning
Hua Ye, Siyuan Chen, Haoliang Zhang +3
Large language models (LLMs) demonstrate impressive generalization abilities, yet adapting them effectively across multiple heterogeneous domains remains challenging due to inter-d…
Seeing through the Conflict: Transparent Knowledge Conflict Handling in Retrieval-Augmented Generation
Hua Ye, Siyuan Chen, Ziqi Zhong +4
Large language models (LLMs) equipped with retrieval--the Retrieval-Augmented Generation (RAG) paradigm--should combine their parametric knowledge with external evidence, yet in pr…