FEVER Breaker’s Run of Team NbAuzDrLqg

Kim, Youngwoo; Allan, James

doi:10.18653/v1/d19-6615

Cited by 7 publications

(6 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The first two winning systems (Niewinski et al, 2019;Hidey et al, 2020) produce claims requiring multi-hop reasoning, which has been shown to be challenging for fact checking models (Ostrowski et al, 2020). The other remaining system (Kim and Allan, 2019) generates adversarial attacks manually. We instead find universal adversarial attacks that can be applied to most existing inputs while markedly decreasing fact checking performance.…”

Section: Fact Checkingmentioning

confidence: 99%

Generating Label Cohesive and Well-Formed Adversarial Claims

Atanasova

Wright

Augenstein

2020

Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)

View full text Add to dashboard Cite

Adversarial attacks reveal important vulnerabilities and flaws of trained models. One potent type of attack are universal adversarial triggers, which are individual n-grams that, when appended to instances of a class under attack, can trick a model into predicting a target class. However, for inference tasks such as fact checking, these triggers often inadvertently invert the meaning of instances they are inserted in. In addition, such attacks produce semantically nonsensical inputs, as they simply concatenate triggers to existing samples. Here, we investigate how to generate adversarial attacks against fact checking systems that preserve the ground truth meaning and are semantically valid. We extend the HotFlip attack algorithm used for universal trigger generation by jointly minimizing the target class loss of a fact checking model and the entailment class loss of an auxiliary natural language inference model. We then train a conditional language model to generate semantically valid statements, which include the found universal triggers. We find that the generated attacks maintain the directionality and semantic validity of the claim better than previous work. * denotes equal contribution Dissociative disorders have been attributed to disruptions in memory caused by trauma or other forms of stress. SUPPORTS REFUTESDissociative identity disorder, or DID, may be the result of memory disruptions that have been induced by psychological trauma. CLAIMdon,already,more,during,home GPT-2 Claim GenerationDissociative disorders have been attributed to disrupted brain activity during trauma or other forms of stress.

show abstract

Section: Fact Checkingmentioning

confidence: 99%

Generating Label Cohesive and Well-Formed Adversarial Claims

Atanasova

Wright

Augenstein

2020

Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)

View full text Add to dashboard Cite

show abstract

“…Finally, (Thorne and Vlachos, 2019) provided a baseline for the FEVER 2.0 shared task with entailment-based perturbations. Other participants generated adversarial claims using implicative phrases such as "not clear" (Kim and Allan, 2019) or GPT-2 (Niewinski et al, 2019). In comparison, we present a diverse set of attacks motivated by realistic, challenging categories and further develop models to address those attacks.…”

Section: Related Workmentioning

confidence: 99%

“…Niewinski et al (2019) trained a GPT-2-based model on the FEVER data and manually filtered disfluent claims. Kim and Allan (2019) considered a variety of approaches, the majority of which required understanding area comparisons between different regions or understanding implications (e.g. that "not clear" implies NEI).…”

Section: Adversarial Dataset Evaluationmentioning

confidence: 99%

“…While GPT-2 is effective, our approach is controllable and targeted at real-world challenges. Finally, Table 3 shows that when we select our top 200 most effective examples (multi-hop reasoning and multi-hop temporal reasoning) and compare to the approaches of Niewinski et al (2019) and Kim and Allan (2019) (who both provided less than 204 examples total) our potency is much higher. In particular, multi-hop reasoning has a potency of 88% for SUPPORT relations and 93% for REFUTES relations and multi-hop temporal reasoning obtains 98% for SUPPORT and REFUTES relations.…”

Section: Adversarial Dataset Evaluationmentioning

confidence: 99%

See 1 more Smart Citation

DeSePtion: Dual Sequence Prediction and Adversarial Examples for Improved Fact-Checking

Hidey

Chakrabarty

Alhindi

et al. 2020

Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics

View full text Add to dashboard Cite

The increased focus on misinformation has spurred development of data and systems for detecting the veracity of a claim as well as retrieving authoritative evidence. The Fact Extraction and VERification (FEVER) dataset provides such a resource for evaluating endto-end fact-checking, requiring retrieval of evidence from Wikipedia to validate a veracity prediction. We show that current systems for FEVER are vulnerable to three categories of realistic challenges for fact-checking -multiple propositions, temporal reasoning, and ambiguity and lexical variation -and introduce a resource with these types of claims. Then we present a system designed to be resilient to these "attacks" using multiple pointer networks for document selection and jointly modeling a sequence of evidence sentences and veracity relation predictions. We find that in handling these attacks we obtain state-of-the-art results on FEVER, largely due to improved evidence retrieval.

show abstract

“…Team NbAuzDrLqg (Kim and Allan, 2019) submitted mostly manually created adversarial claims targeting the retrieval as well as the NLI components of FEVER systems. For the retrieval attacks, the team created claims that didn't contain enti- Table 4: Breakdown of attack type for each breaker and average FEVER scores and Label accuracy for the 8 systems used in the shared task.…”

Section: Breakers Phasementioning

confidence: 99%

The FEVER2.0 Shared Task

Thorne¹,

Vlachos²,

Cocarascu³

et al. 2019

Proceedings of the Second Workshop on Fact Extraction and VERification (FEVER)

View full text Add to dashboard Cite

We present the results of the second Fact Extraction and VERification (FEVER2.0) Shared Task. The task challenged participants to both build systems to verify factoid claims using evidence retrieved from Wikipedia and to generate adversarial attacks against other participant's systems. The shared task had three phases: building, breaking and fixing. There were 8 systems in the builder's round, three of which were new qualifying submissions for this shared task, and 5 adversaries generated instances designed to induce classification errors and one builder submitted a fixed system which had higher FEVER score and resilience than their first submission. All but one newly submitted systems attained FEVER scores higher than the best performing system from the first shared task and under adversarial evaluation, all systems exhibited losses in FEVER score. There was a great variety in adversarial attack types as well as the techniques used to generate the attacks, In this paper, we present the results of the shared task and a summary of the systems, highlighting commonalities and innovations among participating systems.

show abstract

FEVER Breaker’s Run of Team NbAuzDrLqg

Cited by 7 publications

References 5 publications

Generating Label Cohesive and Well-Formed Adversarial Claims

Generating Label Cohesive and Well-Formed Adversarial Claims

DeSePtion: Dual Sequence Prediction and Adversarial Examples for Improved Fact-Checking

The FEVER2.0 Shared Task

Contact Info

Product

Resources

About