Fact Verification
92 papers with code • 3 benchmarks • 14 datasets
Fact verification, also called "fact checking", is a process of verifying facts in natural text against a database of facts.
Benchmarks
These leaderboards are used to track progress in Fact Verification
| Trend | Dataset | Best Model | Paper | Code | Compare |
|---|---|---|---|---|---|
|
|||||
|
|||||
|
FEVER
KILT
VitaminC
FEVEROUS
CREAK
Snopes
X-Fact
FaVIQ
Most implemented papers
Multilingual Evidence Retrieval and Fact Verification to Combat Global Disinformation: The Power of Polyglotism
D-Roberts/multilingual_nli_ECIR2021
•
•
This article investigates multilingual evidence retrieval and fact verification as a step to combat global disinformation, a first effort of this kind, to the best of our knowledge.
FaVIQ: FAct Verification from Information-seeking Questions
faviq/faviq
•
•
ACL 2022
Claims in FAVIQ are verified to be natural, contain little lexical bias, and require a complete understanding of the evidence for verification.
CREAK: A Dataset for Commonsense Reasoning over Entity Knowledge
We introduce CREAK, a testbed for commonsense reasoning about entity knowledge, bridging fact-checking about entities (Harry Potter is a wizard and is skilled at riding a broomstick) with commonsense inferences (if you're good at a skill you can teach others how to do it).
Decorrelate Irrelevant, Purify Relevant: Overcome Textual Spurious Correlations from a Feature Perspective
coling2022-depro/depro
•
•
COLING 2022
Most of the existing debiasing methods often identify and weaken these samples with biased features (i. e., superficial surface features that cause such spurious correlations).
Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection
Our framework trains a single arbitrary LM that adaptively retrieves passages on-demand, and generates and reflects on retrieved passages and its own generations using special tokens, called reflection tokens.
DeFactoNLP: Fact Verification using Entity Recognition, TFIDF Vector Comparison and Decomposable Attention
DeFacto/DeFactoNLP
•
•
WS 2018
In this paper, we describe DeFactoNLP, the system we designed for the FEVER 2018 Shared Task.
TabFact: A Large-scale Dataset for Table-based Fact Verification
wenhuchen/Table-Fact-Checking
•
•
ICLR 2020
To this end, we construct a large-scale dataset called TabFact with 16k Wikipedia tables as the evidence for 118k human-annotated natural language statements, which are labeled as either ENTAILED or REFUTED.
Fine-grained Fact Verification with Kernel Graph Attention Network
Fact Verification requires fine-grained natural language inference capability that finds subtle clues to identify the syntactical and semantically correct but not well-supported claims.
Elastic weight consolidation for better bias inoculation
j6mes/eacl2021-debias-finetuning
•
•
EACL 2021
The biases present in training datasets have been shown to affect models for sentence pair classification tasks such as natural language inference (NLI) and fact verification.
Transformer-XH: Multi-Evidence Reasoning with eXtra Hop Attention
microsoft/Transformer-XH
•
•
ICLR 2020
Transformers have achieved new heights modeling natural language as a sequence of text tokens.
