paper-with-me

홈 › Papers

Towards Generating Effective Explanations of Logical Formulas: Challenges and Strategies

2020-11-01 · ACL (NL4XAI, INLG) 2020 11 · Alexandra Mayn, Kees Van Deemter

While the problem of natural language generation from logical formulas has a long tradition, thus far little attention has been paid to ensuring that the generated explanations are optimally effective for the user. We discuss issues related to deciding what such output should look like and strategies for addressing those issues. We stress the importance of informing generation of NL explanations of logical formulas through reader studies and findings on the comprehension of logic from Pragmatics and Cognitive Science. We then illustrate the discussed issues and potential ways of addressing them using a simple demo system’s output generated from a propositional logic formula.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Text Generation

Similar Papers 제목 키워드 기반

Scaling the Explanation of Multi-Class Bayesian Network Classifiers

2026-03-15 · Yaofang Zhang, Adnan Darwiche arxiv

We propose a new algorithm for compiling Bayesian network classifier (BNC) into class formulas. Class formulas are logical formulas that represent a classifier's input-output behavior, and are crucial in the recent line …

Logical Reasoning

Local-to-Global Logical Explanations for Deep Vision Models

2026-01-19 · Bhavan Vasu, Giuseppe Raffa, Prasad Tadepalli arxiv

While deep neural networks are extremely effective at classifying images, they remain opaque and hard to interpret. We introduce local and global explanation methods for black-box models that generate explanations in ter…

Short Boolean Formulas as Explanations in Practice

2023-07-13 · Reijo Jaakkola, Tomi Janhunen, Antti Kuusisto, Masood Feyzbakhsh Rankooh 외

We investigate explainability via short Boolean formulas in the data model based on unary relations. As an explanation of length k, we take a Boolean formula of length k that minimizes the error with respect to the targe…

Attribute

Towards a fuller understanding of neurons with Clustered Compositional Explanations

2023-10-27 · NeurIPS 2023 11 · Biagio La Rosa, Leilani H. Gilpin, Roberto Capobianco

Compositional Explanations is a method for identifying logical formulas of concepts that approximate the neurons' behavior. However, these explanations are linked to the small spectrum of neuron activations (i.e., the hi…

Applying Second-Order Quantifier Elimination in Inspecting Gödel's Ontological Proof

2021-10-21 · Christoph Wernhard

In recent years, G\"odel's ontological proof and variations of it were formalized and analyzed with automated tools in various ways. We supplement these analyses with a modeling in an automated environment based on first…

Automated Theorem Proving