A unified logical framework for explanations in classifier systems

• URL: http://arxiv.org/abs/2105.14452v8
• Date: Sat, 8 Jul 2023 20:20:03 GMT
• Title: A unified logical framework for explanations in classifier systems
• Authors: Xinghan Liu and Emiliano Lorini
• Abstract summary: We present a modal language of a ceteris paribus nature which supports reasoning about binary input classifiers and their properties. We study a family of models, axiomatize it as two proof systems regarding the cardinality of the language and show completeness of our axiomatics. We leverage the language to formalize counterfactual conditional as well as a variety of notions of explanation including abductive, contrastive and counterfactual explanations.
• Score: 10.256904719009471
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Recent years have witnessed a renewed interest in Boolean function in explaining binary classifiers in the field of explainable AI (XAI). The standard approach of Boolean function is propositional logic. We present a modal language of a ceteris paribus nature which supports reasoning about binary input classifiers and their properties. We study a family of classifier models, axiomatize it as two proof systems regarding the cardinality of the language and show completeness of our axiomatics. Moreover, we prove that satisfiability checking problem for our modal language is NEXPTIME-complete in the infinite-variable case, while it becomes polynomial in the finite-variable case. We furthermore identify an interesting NP fragment of our language in the infinite-variable case. We leverage the language to formalize counterfactual conditional as well as a variety of notions of explanation including abductive, contrastive and counterfactual explanations, and biases. Finally, we present two extensions of our language: a dynamic extension by the notion of assignment enabling classifier change and an epistemic extension in which the classifier's uncertainty about the actual input can be represented.

Related papers

• On the Representational Capacity of Neural Language Models with Chain-of-Thought Reasoning [87.73401758641089]
  Chain-of-thought (CoT) reasoning has improved the performance of modern language models (LMs) We show that LMs can represent the same family of distributions over strings as probabilistic Turing machines.
  arXiv  Detail & Related papers  (2024-06-20T10:59:02Z)
• A Semantic Approach to Decidability in Epistemic Planning (Extended Version) [72.77805489645604]
  We use a novel semantic approach to achieve decidability. Specifically, we augment the logic of knowledge S5$_n$ and with an interaction axiom called (knowledge) commutativity. We prove that our framework admits a finitary non-fixpoint characterization of common knowledge, which is of independent interest.
  arXiv  Detail & Related papers  (2023-07-28T11:26:26Z)
• Lexinvariant Language Models [84.2829117441298]
  Token embeddings, a mapping from discrete lexical symbols to continuous vectors, are at the heart of any language model (LM) We study textitlexinvariantlanguage models that are invariant to lexical symbols and therefore do not need fixed token embeddings in practice. We show that a lexinvariant LM can attain perplexity comparable to that of a standard language model, given a sufficiently long context.
  arXiv  Detail & Related papers  (2023-05-24T19:10:46Z)
• Language Models as Inductive Reasoners [125.99461874008703]
  We propose a new paradigm (task) for inductive reasoning, which is to induce natural language rules from natural language facts. We create a dataset termed DEER containing 1.2k rule-fact pairs for the task, where rules and facts are written in natural language. We provide the first and comprehensive analysis of how well pretrained language models can induce natural language rules from natural language facts.
  arXiv  Detail & Related papers  (2022-12-21T11:12:14Z)
• On Computing Probabilistic Abductive Explanations [30.325691263226968]
  The most widely studied explainable AI (XAI) approaches are unsound. PI-explanations also exhibit important drawbacks, the most visible of which is arguably their size. This paper investigates practical approaches for computing relevant sets for a number of widely used classifiers.
  arXiv  Detail & Related papers  (2022-12-12T15:47:10Z)
• A substructural logic for quantum measurements [1.8782750537161614]
  This paper presents a substructural logic of sequents with very restricted exchange and weakening rules. It is sound with respect to sequences of measurements of a quantic system.
  arXiv  Detail & Related papers  (2022-12-06T09:11:42Z)
• Join-Chain Network: A Logical Reasoning View of the Multi-head Attention in Transformer [59.73454783958702]
  We propose a symbolic reasoning architecture that chains many join operators together to model output logical expressions. In particular, we demonstrate that such an ensemble of join-chains can express a broad subset of ''tree-structured'' first-order logical expressions, named FOET. We find that the widely used multi-head self-attention module in transformer can be understood as a special neural operator that implements the union bound of the join operator in probabilistic predicate space.
  arXiv  Detail & Related papers  (2022-10-06T07:39:58Z)
• On Deciding Feature Membership in Explanations of SDD & Related Classifiers [0.685316573653194]
  The paper shows that the feature membership problem (FMP) is hard for $SigmaP$ for a broad class of classifiers. The paper proposes propositional encodings for classifiers represented with Sentential Decision Diagrams (SDDs) and for other propositional languages.
  arXiv  Detail & Related papers  (2022-02-15T16:38:53Z)
• Neural Unification for Logic Reasoning over Natural Language [0.28675177318965034]
  Automated Theorem Proving deals with the development of computer programs being able to show that some conjectures (queries) are a logical consequence of a set of axioms (facts and rules) Recent approaches have proposed transformer-based architectures for deriving conjectures given axioms expressed in natural language (English) In this work we propose a new architecture, namely the Neural Unifier, which achieves state-of-the-art results in term of generalisation.
  arXiv  Detail & Related papers  (2021-09-17T10:48:39Z)
• Prediction or Comparison: Toward Interpretable Qualitative Reasoning [16.02199526395448]
  Current approaches use either semantics to transform natural language inputs into logical expressions or a "black-box" model to solve them in one step. In this work, we categorize qualitative reasoning tasks into two types: prediction and comparison. In particular, we adopt neural network modules trained in an end-to-end manner to simulate the two reasoning processes.
  arXiv  Detail & Related papers  (2021-06-04T10:27:55Z)
• Foundations of Reasoning with Uncertainty via Real-valued Logics [70.43924776071616]
  We give a sound and strongly complete axiomatization that can be parametrized to cover essentially every real-valued logic. Our class of sentences are very rich, and each describes a set of possible real values for a collection of formulas of the real-valued logic.
  arXiv  Detail & Related papers  (2020-08-06T02:13:11Z)

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.