PluRule is a new multimodal multilingual benchmark showing that state-of-the-art vision-language models perform only marginally better than a trivial baseline at detecting specific rule violations in pluralistic online communities.
A survey on neural open information extraction: Current status and future directions
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
verdicts
UNVERDICTED 3representative citing papers
A Multi-L KG and Quest-GNN with question-adaptive intra/inter-level message passing and synthesized pre-training data improves multi-hop RAG performance up to 33.8% on high-hop questions.
Hybrid-IR combines graph and dense retrieval with iterative retrieve-reason loops and shows gains on three medical QA benchmarks.
citing papers explorer
-
PluRule: A Benchmark for Moderating Pluralistic Communities on Social Media
PluRule is a new multimodal multilingual benchmark showing that state-of-the-art vision-language models perform only marginally better than a trivial baseline at detecting specific rule violations in pluralistic online communities.
-
Question-Adaptive Graph Learning for Multi-hop Retrieval Augmented Generation
A Multi-L KG and Quest-GNN with question-adaptive intra/inter-level message passing and synthesized pre-training data improves multi-hop RAG performance up to 33.8% on high-hop questions.
-
Hybrid-IR: Dual-Path Hybrid Retrieval with Iterative Reasoning for Complex Medical Question Answering
Hybrid-IR combines graph and dense retrieval with iterative retrieve-reason loops and shows gains on three medical QA benchmarks.