NELLIE: A Neuro-Symbolic Inference Engine for Grounded, Compositional, and Explainable Reasoning

• URL: http://arxiv.org/abs/2209.07662v5
• Date: Mon, 12 Aug 2024 23:42:17 GMT
• Title: NELLIE: A Neuro-Symbolic Inference Engine for Grounded, Compositional, and Explainable Reasoning
• Authors: Nathaniel Weir, Peter Clark, Benjamin Van Durme,
• Abstract summary: This paper proposes a new take on Prolog-based inference engines. We replace handcrafted rules with a combination of neural language modeling, guided generation, and semi dense retrieval. Our implementation, NELLIE, is the first system to demonstrate fully interpretable, end-to-end grounded QA.
• Score: 59.16962123636579
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Our goal is a modern approach to answering questions via systematic reasoning where answers are supported by human interpretable proof trees grounded in an NL corpus of authoritative facts. Such a system would help alleviate the challenges of interpretability and hallucination with modern LMs, and the lack of grounding of current explanation methods (e.g., Chain-of-Thought). This paper proposes a new take on Prolog-based inference engines, where we replace handcrafted rules with a combination of neural language modeling, guided generation, and semiparametric dense retrieval. Our implementation, NELLIE, is the first system to demonstrate fully interpretable, end-to-end grounded QA as entailment tree proof search, going beyond earlier work explaining known-to-be-true facts from text. In experiments, NELLIE outperforms a similar-sized state-of-the-art reasoner [Tafjord et al., 2022] while producing knowledge-grounded explanations. We also find NELLIE can exploit both semi-structured and NL text corpora to guide reasoning. Together these suggest a new way to jointly reap the benefits of both modern neural methods and traditional symbolic reasoning.

Related papers

• Towards a Mechanistic Interpretation of Multi-Step Reasoning Capabilities of Language Models [107.07851578154242]
  Language models (LMs) have strong multi-step (i.e., procedural) reasoning capabilities. It is unclear whether LMs perform tasks by cheating with answers memorized from pretraining corpus, or, via a multi-step reasoning mechanism. We show that MechanisticProbe is able to detect the information of the reasoning tree from the model's attentions for most examples.
  arXiv  Detail & Related papers  (2023-10-23T01:47:29Z)
• Emulating the Human Mind: A Neural-symbolic Link Prediction Model with Fast and Slow Reasoning and Filtered Rules [4.979279893937017]
  We introduce a novel Neural-Symbolic model named FaSt-FLiP. Our objective is to combine a logical and neural model for enhanced link prediction.
  arXiv  Detail & Related papers  (2023-10-21T12:45:11Z)
• Faithfulness Tests for Natural Language Explanations [87.01093277918599]
  Explanations of neural models aim to reveal a model's decision-making process for its predictions. Recent work shows that current methods giving explanations such as saliency maps or counterfactuals can be misleading. This work explores the challenging question of evaluating the faithfulness of natural language explanations.
  arXiv  Detail & Related papers  (2023-05-29T11:40:37Z)
• Explaining Deep Learning Hidden Neuron Activations using Concept Induction [3.6223658572137825]
  State of the art indicates that hidden node activations appear to be interpretable in a way that makes sense to humans. We show that we can automatically attach meaningful labels from the background knowledge to individual neurons in the dense layer of a Convolutional Neural Network.
  arXiv  Detail & Related papers  (2023-01-23T18:14:32Z)
• Explanatory Learning: Beyond Empiricism in Neural Networks [12.622254638367504]
  We introduce Explanatory Learning, a framework to let machines use existing knowledge buried in symbolic sequences. In EL, the burden of interpreting symbols is not left to humans or rigid human-coded compilers, as done in Program Synthesis. We show how CRNs outperform empiricist end-to-end approaches of similar size and architecture.
  arXiv  Detail & Related papers  (2022-01-25T10:21:53Z)
• Weakly Supervised Explainable Phrasal Reasoning with Neural Fuzzy Logic [24.868479255640718]
  Natural language inference aims to determine the logical relationship between two sentences among the target labels Entailment, Contradiction, and Neutral. Deep learning models have become a prevailing approach to NLI, but they lack interpretability and explainability. In this work, we address the explainability for NLI by weakly supervised logical reasoning.
  arXiv  Detail & Related papers  (2021-09-18T13:04:23Z)
• LNN-EL: A Neuro-Symbolic Approach to Short-text Entity Linking [62.634516517844496]
  We propose LNN-EL, a neuro-symbolic approach that combines the advantages of using interpretable rules with the performance of neural learning. Even though constrained to using rules, LNN-EL performs competitively against SotA black-box neural approaches.
  arXiv  Detail & Related papers  (2021-06-17T20:22:45Z)
• Explaining Answers with Entailment Trees [16.555369850015055]
  We aim to explain answers by showing how evidence leads to the answer in a systematic way. Our approach is to generate explanations in the form of entailment trees, namely a tree of entailment steps from facts that are known, through intermediate conclusions, to the final answer. To train a model with this skill, we created ENTAILMENTBANK, the first dataset to contain multistep entailment trees.
  arXiv  Detail & Related papers  (2021-04-17T23:13:56Z)
• Explainability in Deep Reinforcement Learning [68.8204255655161]
  We review recent works in the direction to attain Explainable Reinforcement Learning (XRL) In critical situations where it is essential to justify and explain the agent's behaviour, better explainability and interpretability of RL models could help gain scientific insight on the inner workings of what is still considered a black box.
  arXiv  Detail & Related papers  (2020-08-15T10:11:42Z)
• Compositional Explanations of Neurons [52.71742655312625]
  We describe a procedure for explaining neurons in deep representations by identifying compositional logical concepts. We use this procedure to answer several questions on interpretability in models for vision and natural language processing.
  arXiv  Detail & Related papers  (2020-06-24T20:37:05Z)

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.