Learning Semantic Structure through First-Order-Logic Translation
In this paper, we study whether transformer-based language models can extract predicate argument structure from simple sentences. We firstly show that language models sometimes confuse which predicates apply to which objects. To mitigate this, we explore two tasks: question answering (Q/A), and first order logic (FOL) translation, and two regimes, prompting and finetuning. In FOL translation, we finetune several large language models on synthetic datasets designed to gauge their generalization abilities. For Q/A, we finetune encoder models like BERT and RoBERTa and use prompting for LLMs. The results show that FOL translation for LLMs is better suited to learn predicate argument structure.
Code (0)
등록된 구현이 없습니다.
Tasks
Question AnsweringTranslationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Discussion Graph Semantics of First-Order Logic with Equality for Reasoning about Discussion and Argumentation
We formulate discussion graph semantics of first-order logic with equality for reasoning about discussion and argumentation as naturally as we would reason about sentences. While there are a few existing proposals to use…
Formal LogicDivide and Translate: Compositional First-Order Logic Translation and Verification for Complex Logical Reasoning
Complex logical reasoning tasks require a long sequence of reasoning, which a large language model (LLM) with chain-of-thought prompting still falls short. To alleviate this issue, neurosymbolic approaches incorporate a …
Language ModellingLarge Language ModelLogical ReasoningLogic Grid PuzzleDeep Adaptive Semantic Logic (DASL): Compiling Declarative Knowledge into Deep Neural Networks
We introduce Deep Adaptive Semantic Logic (DASL), a novel framework for automating the generation of deep neural networks that incorporates user-provided formal knowledge to improve learning from data. We provide formal …
image-classificationImage ClassificationRelationship DetectionVisual Relationship DetectionNeurosymbolic Framework for Concept-Driven Logical Reasoning in Skeleton-Based Human Action Recognition
Skeleton-based human activity recognition has achieved strong empirical performance, yet most existing models remain black boxes and difficult to interpret. In this work, we introduce a neurosymbolic formulation of skele…
Human Activity RecognitionRepresentation LearningAction UnderstandingAction RecognitionQMFOL: Benchmarking Large Language Model Reasoning via Quantifiable Monadic First-Order Logic Test Case Generation
Large Language Models (LLMs) have made significant progress in reasoning, particularly in deductive reasoning, which is crucial for high-stakes decision-making. As models improve, evaluation benchmarks should evolve to k…