On the Diversity and Limits of Human Explanations
- URL: http://arxiv.org/abs/2106.11988v1
- Date: Tue, 22 Jun 2021 18:00:07 GMT
- Title: On the Diversity and Limits of Human Explanations
- Authors: Chenhao Tan
- Abstract summary: A growing effort in NLP aims to build datasets of human explanations.
Our goal is to provide an overview of diverse types of explanations and human limitations.
- Score: 11.44224857047629
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: A growing effort in NLP aims to build datasets of human explanations.
However, the term explanation encompasses a broad range of notions, each with
different properties and ramifications. Our goal is to provide an overview of
diverse types of explanations and human limitations, and discuss implications
for collecting and using explanations in NLP. Inspired by prior work in
psychology and cognitive sciences, we group existing human explanations in NLP
into three categories: proximal mechanism, evidence, and procedure. These three
types differ in nature and have implications for the resultant explanations.
For instance, procedure is not considered explanations in psychology and
connects with a rich body of work on learning from instructions. The diversity
of explanations is further evidenced by proxy questions that are needed for
annotators to interpret and answer open-ended why questions. Finally,
explanations may require different, often deeper, understandings than
predictions, which casts doubt on whether humans can provide useful
explanations in some tasks.
Related papers
- An Incomplete Loop: Deductive, Inductive, and Abductive Learning in Large Language Models [99.31449616860291]
Modern language models (LMs) can learn to perform new tasks in different ways.
In instruction following, the target task is described explicitly in natural language; in few-shot prompting, the task is specified implicitly.
In instruction inference, LMs are presented with in-context examples and are then prompted to generate a natural language task description.
arXiv Detail & Related papers (2024-04-03T19:31:56Z) - Providing personalized Explanations: a Conversational Approach [0.5156484100374058]
We propose an approach for an explainer to communicate personalized explanations to an explainee through having consecutive conversations with the explainee.
We prove that the conversation terminates due to the explainee's justification of the initial claim as long as there exists an explanation for the initial claim that the explainee understands and the explainer is aware of.
arXiv Detail & Related papers (2023-07-21T09:34:41Z) - Complementary Explanations for Effective In-Context Learning [77.83124315634386]
Large language models (LLMs) have exhibited remarkable capabilities in learning from explanations in prompts.
This work aims to better understand the mechanisms by which explanations are used for in-context learning.
arXiv Detail & Related papers (2022-11-25T04:40:47Z) - "Mama Always Had a Way of Explaining Things So I Could Understand'': A
Dialogue Corpus for Learning to Construct Explanations [26.540485804067536]
We introduce a first corpus of dialogical explanations to enable NLP research on how humans explain.
The corpus consists of 65 transcribed English dialogues from the Wired video series emph5 Levels, explaining 13 topics to five explainees of different proficiency.
arXiv Detail & Related papers (2022-09-06T14:00:22Z) - Explanatory Paradigms in Neural Networks [18.32369721322249]
We present a leap-forward expansion to the study of explainability in neural networks by considering explanations as answers to reasoning-based questions.
The answers to these questions are observed correlations, observed counterfactuals, and observed contrastive explanations respectively.
The term observed refers to the specific case of post-hoc explainability, when an explanatory technique explains the decision $P$ after a trained neural network has made the decision $P$.
arXiv Detail & Related papers (2022-02-24T00:22:11Z) - Human Interpretation of Saliency-based Explanation Over Text [65.29015910991261]
We study saliency-based explanations over textual data.
We find that people often mis-interpret the explanations.
We propose a method to adjust saliencies based on model estimates of over- and under-perception.
arXiv Detail & Related papers (2022-01-27T15:20:32Z) - Diagnosing AI Explanation Methods with Folk Concepts of Behavior [70.10183435379162]
We consider "success" to depend not only on what information the explanation contains, but also on what information the human explainee understands from it.
We use folk concepts of behavior as a framework of social attribution by the human explainee.
arXiv Detail & Related papers (2022-01-27T00:19:41Z) - Explanation as a process: user-centric construction of multi-level and
multi-modal explanations [0.34410212782758043]
We present a process-based approach that combines multi-level and multi-modal explanations.
We use Inductive Logic Programming, an interpretable machine learning approach, to learn a comprehensible model.
arXiv Detail & Related papers (2021-10-07T19:26:21Z) - Prompting Contrastive Explanations for Commonsense Reasoning Tasks [74.7346558082693]
Large pretrained language models (PLMs) can achieve near-human performance on commonsense reasoning tasks.
We show how to use these same models to generate human-interpretable evidence.
arXiv Detail & Related papers (2021-06-12T17:06:13Z) - The Struggles of Feature-Based Explanations: Shapley Values vs. Minimal
Sufficient Subsets [61.66584140190247]
We show that feature-based explanations pose problems even for explaining trivial models.
We show that two popular classes of explainers, Shapley explainers and minimal sufficient subsets explainers, target fundamentally different types of ground-truth explanations.
arXiv Detail & Related papers (2020-09-23T09:45:23Z)
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.