Fact-checkers want automated fact-checking explanations that trace the reasoning path, cite checkable evidence, and clearly flag uncertainty and information gaps, not just confidence scores.
In: Proceedings of the 28th International Conference on Computational Lin- guistics, International Committee on Computational Linguistics, pp
7 Pith papers cite this work. Polarity classification is still indexing.
7
Pith papers citing it
representative citing papers
HKVM-RAG uses key-value-separated hypergraphs to organize LLM evidence tuples into answer-path hyperedges, yielding F1 gains over KG-PPR on two multi-hop QA benchmarks and further gains when combined with dense retrievers.
PyTerrier-RAG extends PyTerrier with datatypes, readers, datasets, and metrics for building and evaluating declarative retrieval-augmented generation pipelines.
A contrastive learning framework uses inductive logic programming to generate hard positive and negative pairs, improving BERT and RoBERTa accuracy on synthetic cross-domain NLI tasks.
EviReform improves multi-hop graph retrieval by generating residual queries from initially retrieved evidence and combining them with the original question before graph propagation.
The paper releases SignNet-1M, a 1M-scale augmented dataset for ASL, CSL and DGS with 3DGS and diffusion-based variations, plus benchmarks showing improved cross-shift generalization.
A stream-based classifier with LLM-generated natural-language explanations claims around 90% accuracy for disinformation detection on Wikivoyage and Wikipedia edit streams.
citing papers explorer
-
Show Me the Work: Fact-Checkers' Requirements for Explainable Automated Fact-Checking
Fact-checkers want automated fact-checking explanations that trace the reasoning path, cite checkable evidence, and clearly flag uncertainty and information gaps, not just confidence scores.
-
HKVM-RAG: Key-Value-Separated Hypergraph Evidence Organization for Multi-Hop RAG
HKVM-RAG uses key-value-separated hypergraphs to organize LLM evidence tuples into answer-path hyperedges, yielding F1 gains over KG-PPR on two multi-hop QA benchmarks and further gains when combined with dense retrievers.
-
Constructing and Evaluating Declarative RAG Pipelines in PyTerrier
PyTerrier-RAG extends PyTerrier with datatypes, readers, datasets, and metrics for building and evaluating declarative retrieval-augmented generation pipelines.
-
Neuro-Symbolic Contrastive Learning for Cross-domain Inference
A contrastive learning framework uses inductive logic programming to generate hard positive and negative pairs, improving BERT and RoBERTa accuracy on synthetic cross-domain NLI tasks.
-
EviReform: Evidence-Guided Query Reformulation for Multi-Hop Graph Retrieval
EviReform improves multi-hop graph retrieval by generating residual queries from initially retrieved evidence and combining them with the original question before graph propagation.
-
SignNet-1M: Large-Scale Multilingual Sign Language Video Dataset with Downstream Benchmarks
The paper releases SignNet-1M, a 1M-scale augmented dataset for ASL, CSL and DGS with 3DGS and diffusion-based variations, plus benchmarks showing improved cross-shift generalization.
-
Identification and explanation of disinformation in wiki data streams
A stream-based classifier with LLM-generated natural-language explanations claims around 90% accuracy for disinformation detection on Wikivoyage and Wikipedia edit streams.