Get Your Vitamin C! Robust Fact Verification with Contrastive Evidence
- URL: http://arxiv.org/abs/2103.08541v1
- Date: Mon, 15 Mar 2021 17:05:13 GMT
- Title: Get Your Vitamin C! Robust Fact Verification with Contrastive Evidence
- Authors: Tal Schuster, Adam Fisch, Regina Barzilay
- Abstract summary: VitaminC is a benchmark infused with challenging cases that require fact verification models to discern and adjust to slight factual changes.
We collect over 100,000 Wikipedia revisions that modify an underlying fact, and leverage these revisions to create over 400,000 claim-evidence pairs.
We show that training using this design increases robustness -- improving accuracy by 10% on adversarial fact verification and 6% on adversarial natural language inference.
- Score: 32.63174559281556
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Typical fact verification models use retrieved written evidence to verify
claims. Evidence sources, however, often change over time as more information
is gathered and revised. In order to adapt, models must be sensitive to subtle
differences in supporting evidence. We present VitaminC, a benchmark infused
with challenging cases that require fact verification models to discern and
adjust to slight factual changes. We collect over 100,000 Wikipedia revisions
that modify an underlying fact, and leverage these revisions, together with
additional synthetically constructed ones, to create a total of over 400,000
claim-evidence pairs. Unlike previous resources, the examples in VitaminC are
contrastive, i.e., they contain evidence pairs that are nearly identical in
language and content, with the exception that one supports a given claim while
the other does not. We show that training using this design increases
robustness -- improving accuracy by 10% on adversarial fact verification and 6%
on adversarial natural language inference (NLI). Moreover, the structure of
VitaminC leads us to define additional tasks for fact-checking resources:
tagging relevant words in the evidence for verifying the claim, identifying
factual revisions, and providing automatic edits via factually consistent text
generation.
Related papers
- Credible, Unreliable or Leaked?: Evidence Verification for Enhanced Automated Fact-checking [11.891881050619457]
"CREDible, Unreliable or LEaked" dataset consists of 91,632 articles classified as Credible, Unreliable and Fact checked (Leaked)
"EVidence VERification Network (EVVER-Net) trained on CREDULE to detect leaked and unreliable evidence in both short and long texts"
"EVVER-Net can demonstrate impressive performance of up to 91.5% and 94.4% accuracy"
arXiv Detail & Related papers (2024-04-29T13:47:04Z) - Give Me More Details: Improving Fact-Checking with Latent Retrieval [58.706972228039604]
Evidence plays a crucial role in automated fact-checking.
Existing fact-checking systems either assume the evidence sentences are given or use the search snippets returned by the search engine.
We propose to incorporate full text from source documents as evidence and introduce two enriched datasets.
arXiv Detail & Related papers (2023-05-25T15:01:19Z) - Read it Twice: Towards Faithfully Interpretable Fact Verification by
Revisiting Evidence [59.81749318292707]
We propose a fact verification model named ReRead to retrieve evidence and verify claim.
The proposed system is able to achieve significant improvements upon best-reported models under different settings.
arXiv Detail & Related papers (2023-05-02T03:23:14Z) - WiCE: Real-World Entailment for Claims in Wikipedia [63.234352061821625]
We propose WiCE, a new fine-grained textual entailment dataset built on natural claim and evidence pairs extracted from Wikipedia.
In addition to standard claim-level entailment, WiCE provides entailment judgments over sub-sentence units of the claim.
We show that real claims in our dataset involve challenging verification and retrieval problems that existing models fail to address.
arXiv Detail & Related papers (2023-03-02T17:45:32Z) - Implicit Temporal Reasoning for Evidence-Based Fact-Checking [14.015789447347466]
Our study demonstrates that time positively influences the claim verification process of evidence-based fact-checking.
Our findings show that the presence of temporal information and the manner in which timelines are constructed greatly influence how fact-checking models determine the relevance and supporting or refuting character of evidence documents.
arXiv Detail & Related papers (2023-02-24T10:48:03Z) - Synthetic Disinformation Attacks on Automated Fact Verification Systems [53.011635547834025]
We explore the sensitivity of automated fact-checkers to synthetic adversarial evidence in two simulated settings.
We show that these systems suffer significant performance drops against these attacks.
We discuss the growing threat of modern NLG systems as generators of disinformation.
arXiv Detail & Related papers (2022-02-18T19:01:01Z) - Evidence-based Factual Error Correction [18.52583883901634]
This paper introduces the task of factual error correction.
It provides a mechanism to correct written texts that are refuted or only partially supported by evidence.
arXiv Detail & Related papers (2021-06-02T11:00:17Z) - AmbiFC: Fact-Checking Ambiguous Claims with Evidence [57.7091560922174]
We present AmbiFC, a fact-checking dataset with 10k claims derived from real-world information needs.
We analyze disagreements arising from ambiguity when comparing claims against evidence in AmbiFC.
We develop models for predicting veracity handling this ambiguity via soft labels.
arXiv Detail & Related papers (2021-04-01T17:40:08Z) - Hierarchical Evidence Set Modeling for Automated Fact Extraction and
Verification [5.836068916903788]
Hierarchical Evidence Set Modeling (HESM) is a framework to extract evidence sets and verify a claim to be supported, refuted or not enough info.
Our experimental results show that HESM outperforms 7 state-of-the-art methods for fact extraction and claim verification.
arXiv Detail & Related papers (2020-10-10T22:27:17Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.