ProoFVer: Natural Logic Theorem Proving for Fact Verification
Fact verification systems typically rely on neural network classifiers for veracity prediction which lack explainability. This paper proposes ProoFVer, which uses a seq2seq model to generate natural logic-based inferences as proofs. These proofs consist of lexical mutations between spans in the claim and the evidence retrieved, each marked with a natural logic operator. Claim veracity is determined solely based on the sequence of these operators. Hence, these proofs are faithful explanations, and this makes ProoFVer faithful by construction. Currently, ProoFVer has the highest label accuracy and the second-best Score in the FEVER leaderboard. Furthermore, it improves by 13.21% points over the next best model on a dataset with counterfactual instances, demonstrating its robustness. As explanations, the proofs show better overlap with human rationales than attention-based highlights and the proofs help humans predict model decisions correctly more often than using the evidence directly.
Code (1)
Tasks
Automated Theorem ProvingcounterfactualDecision MakingFact VerificationNatural Language InferenceMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Learning as Abduction: Trainable Natural Logic Theorem Prover for Natural Language Inference
Tackling Natural Language Inference with a logic-based method is becoming less and less common. While this might have been counterintuitive several decades ago, nowadays it seems pretty obvious. The main reasons for such…
Automated Theorem ProvingNatural Language InferenceSentenceA Deep Reinforcement Learning Approach to First-Order Logic Theorem Proving
Automated theorem provers have traditionally relied on manually tuned heuristics to guide how they perform proof search. Deep reinforcement learning has been proposed as a way to obviate the need for such heuristics, how…
Automated Theorem ProvingDeep Reinforcement Learningreinforcement-learningReinforcement Learning+1Theorem Proving Based on Semantics of DNA Strand Graph
Because of several technological limitations of traditional silicon based computing, for past few years a paradigm shift, from silicon to carbon, is occurring in computational world. DNA computing has been considered to …
Automated Theorem ProvingRare Speed-up in Automatic Theorem Proving Reveals Tradeoff Between Computational Time and Information Value
We show that strategies implemented in automatic theorem proving involve an interesting tradeoff between execution speed, proving speedup/computational time and usefulness of information. We advance formal definitions fo…
Automated Theorem ProvingDeepTheorem: Advancing LLM Reasoning for Theorem Proving Through Natural Language and Reinforcement Learning
Theorem proving serves as a major testbed for evaluating complex reasoning abilities in large language models (LLMs). However, traditional automated theorem proving (ATP) approaches rely heavily on formal proof systems t…
Automated Theorem ProvingMathematical Reasoning