A self-reflective agent pipeline with evidence-drift and reasoning-reflection checks reports new state-of-the-art Macro-F1 on HOVER and EX-FEVER multi-hop fact verification.
A Multi-Level Attention Model for Evidence-Based Fact Checking
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
Evidence-based fact checking aims to verify the truthfulness of a claim against evidence extracted from textual sources. Learning a representation that effectively captures relations between a claim and evidence can be challenging. Recent state-of-the-art approaches have developed increasingly sophisticated models based on graph structures. We present a simple model that can be trained on sequence structures. Our model enables inter-sentence attentions at different levels and can benefit from joint training. Results on a large-scale dataset for Fact Extraction and VERification (FEVER) show that our model outperforms the graph-based approaches and yields 1.09% and 1.42% improvements in label accuracy and FEVER score, respectively, over the best published model.
fields
cs.AI 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
ReflectFact: Self-Reflective Agents for Improving Comprehension and Reasoning in Multi-Hop Fact Verification
A self-reflective agent pipeline with evidence-drift and reasoning-reflection checks reports new state-of-the-art Macro-F1 on HOVER and EX-FEVER multi-hop fact verification.