5 papers
Advancing Edge Classification through High-Dimensional Causal Modeling of Node-Edge Interplay
Duanyu Feng, Li Ding, Hongru Liang +1
Edge classification, a crucial task for graph applications, remains relatively under-explored compared to link prediction. Current methods often overlook the potential causal influ…
SCOP: Evaluating the Comprehension Process of Large Language Models from a Cognitive View
Yongjie Xiao, Hongru Liang, Peixin Qin +2
Despite the great potential of large language models(LLMs) in machine comprehension, it is still disturbing to fully count on them in real-world scenarios. This is probably because…
BAR: A Backward Reasoning based Agent for Complex Minecraft Tasks
Weihong Du, Wenrui Liao, Binyu Yan +3
Large language model (LLM) based agents have shown great potential in following human instructions and automatically completing various tasks. To complete a task, the agent needs t…
CARE: A Clue-guided Assistant for CSRs to Read User Manuals
Weihong Du, Jia Liu, Zujie Wen +3
It is time-saving to build a reading assistant for customer service representations (CSRs) when reading user manuals, especially information-rich ones. Current solutions don't fit…
PAGED: A Benchmark for Procedural Graphs Extraction from Documents
Weihong Du, Wenrui Liao, Hongru Liang +1
Automatic extraction of procedural graphs from documents creates a low-cost way for users to easily understand a complex procedure by skimming visual graphs. Despite the progress i…