Answer-Set Programs for Reasoning about Counterfactual Interventions and Responsibility Scores for Classification

• URL: http://arxiv.org/abs/2107.10159v1
• Date: Wed, 21 Jul 2021 15:41:56 GMT
• Title: Answer-Set Programs for Reasoning about Counterfactual Interventions and Responsibility Scores for Classification
• Authors: Leopoldo Bertossi and Gabriela Reyes
• Abstract summary: We describe how answer-set programs can be used to declaratively specify counterfactual interventions on entities under classification. In particular, they can be used to define and compute responsibility scores as attribution-based explanations for outcomes from classification models.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We describe how answer-set programs can be used to declaratively specify counterfactual interventions on entities under classification, and reason about them. In particular, they can be used to define and compute responsibility scores as attribution-based explanations for outcomes from classification models. The approach allows for the inclusion of domain knowledge and supports query answering. A detailed example with a naive-Bayes classifier is presented.

Related papers

• Open-Set Knowledge-Based Visual Question Answering with Inference Paths [79.55742631375063]
  The purpose of Knowledge-Based Visual Question Answering (KB-VQA) is to provide a correct answer to the question with the aid of external knowledge bases. We propose a new retriever-ranker paradigm of KB-VQA, Graph pATH rankER (GATHER for brevity) Specifically, it contains graph constructing, pruning, and path-level ranking, which not only retrieves accurate answers but also provides inference paths that explain the reasoning process.
  arXiv  Detail & Related papers  (2023-10-12T09:12:50Z)
• Mitigating Word Bias in Zero-shot Prompt-based Classifiers [55.60306377044225]
  We show that matching class priors correlates strongly with the oracle upper bound performance. We also demonstrate large consistent performance gains for prompt settings over a range of NLP tasks.
  arXiv  Detail & Related papers  (2023-09-10T10:57:41Z)
• Using Natural Language Explanations to Rescale Human Judgments [81.66697572357477]
  We propose a method to rescale ordinal annotations and explanations using large language models (LLMs) We feed annotators' Likert ratings and corresponding explanations into an LLM and prompt it to produce a numeric score anchored in a scoring rubric. Our method rescales the raw judgments without impacting agreement and brings the scores closer to human judgments grounded in the same scoring rubric.
  arXiv  Detail & Related papers  (2023-05-24T06:19:14Z)
• When in Doubt: Improving Classification Performance with Alternating Normalization [57.39356691967766]
  We introduce Classification with Alternating Normalization (CAN), a non-parametric post-processing step for classification. CAN improves classification accuracy for challenging examples by re-adjusting their predicted class probability distribution. We empirically demonstrate its effectiveness across a diverse set of classification tasks.
  arXiv  Detail & Related papers  (2021-09-28T02:55:42Z)
• Reasoning about Counterfactuals and Explanations: Problems, Results and Directions [0.0]
  These approaches are flexible and modular in that they allow the seamless addition of domain knowledge. The programs can be used to specify and compute responsibility-based numerical scores as attributive explanations for classification results.
  arXiv  Detail & Related papers  (2021-08-25T01:04:49Z)
• Score-Based Explanations in Data Management and Machine Learning: An Answer-Set Programming Approach to Counterfactual Analysis [0.0]
  We describe some recent approaches to score-based explanations for query answers in databases and outcomes from classification models in machine learning. Special emphasis is placed on declarative approaches based on answer-set programming to the use of counterfactual reasoning for score specification and computation.
  arXiv  Detail & Related papers  (2021-06-19T19:21:48Z)
• Hierarchical Modeling for Out-of-Scope Domain and Intent Classification [55.23920796595698]
  This paper focuses on out-of-scope intent classification in dialog systems. We propose a hierarchical multi-task learning approach based on a joint model to classify domain and intent simultaneously. Experiments show that the model outperforms existing methods in terms of accuracy, out-of-scope recall and F1.
  arXiv  Detail & Related papers  (2021-04-30T06:38:23Z)
• Declarative Approaches to Counterfactual Explanations for Classification [0.0]
  We propose answer-set programs that specify and compute counterfactual interventions on entities that are input on a classification model. The resulting counterfactual entities serve as a basis for the definition and computation of causality-based explanation scores for the feature values in the entity under classification.
  arXiv  Detail & Related papers  (2020-11-15T00:44:33Z)
• Score-Based Explanations in Data Management and Machine Learning [0.0]
  We consider explanations for query answers in databases, and for results from classification models. The described approaches are mostly of a causal and counterfactual nature.
  arXiv  Detail & Related papers  (2020-07-24T23:13:27Z)
• Visual Question Answering with Prior Class Semantics [50.845003775809836]
  We show how to exploit additional information pertaining to the semantics of candidate answers. We extend the answer prediction process with a regression objective in a semantic space. Our method brings improvements in consistency and accuracy over a range of question types.
  arXiv  Detail & Related papers  (2020-05-04T02:46:31Z)
• An ASP-Based Approach to Counterfactual Explanations for Classification [0.0]
  We propose answer-set programs that specify and compute counterfactual interventions as a basis for causality-based explanations to decisions produced by classification models. They can be applied with black-box models and models that can be specified as logic programs, such as rule-based classifiers.
  arXiv  Detail & Related papers  (2020-04-28T01:36:26Z)

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.