Interactive and interpretable machine learning models for human machine collaboration

By Been Kim. 2015

103 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Natural Language Processing

Citations in the corpus

Ethical Challenges in Data-Driven Dialogue Systems (2017, background): “stems. Ethics and safety in artiﬁcial intelligence (AI) has recently gained popularity as a ﬁeld due to performance gains in AI models, investigating issues like: interpretability of model decisions (Kim 2015), worst-case performance guarantees (Garcıa and Fernandez 2015), and many others. In´ the c”
The mythos of model interpretability (2016, background): “ronment. Thus interpretations serve those objectives that we deem important but struggle to model formally. Trust: Some papers motivate interpretability by suggesting it to be prerequisite for trust (Kim, 2015; Ribeiro et al., 2016). But what is trust? Is it simply conﬁdence that a model will perfor”
Adversarial Risk and the Dangers of Evaluating Against Weak Attacks (2018, background): “lyzed suggests the potential for fruitful exchange of ideas (Christiano, 2016). Whileinthemodelinterpretabilitycommunity, transparency is often measured qualitatively from the perspective of a human (Kim, 2015; Krakovna and Doshi-Velez, 2016; Ross and Doshi-Velez, 2018), we note that obscurity as we”
How Do Decisions Emerge across Layers in Neural Models? Interpretation with Differentiable Masking (2020, background): “This lack of interpretability can prevent users from trusting model predictions (Kim, 2015; Ribeiro et al., 2016), makes it hard to detect model or data deﬁciencies (Gururangan et al., 2018; Kaushik and Lipton, 2018) or verify that a model is fair and does not exhibit harmful biases (Sun et al.,…”
Approximate and Exact Enumeration of Rule Models (2018, background): “The need for model interpretability is particularly strong in some practical situations, such as the following (Kim 2015; Doshi-Velez and Kim 2017).”
Interpretable R-CNN (2017, background): “In the context of supervised learning, Lipton [49] investigated the motives for interpretability including trust [38, 62], causality [58], transferability [5] and informativeness [38], and properties of interpretable models including transparency in terms of simulatability and decomposability and po”
Interpreting Graph Neural Networks for NLP With Differentiable Edge Masking (2020, background): “Furthermore, this opaqueness decreases user trust, impedes the discovery of harmful biases, and complicates error analysis (Kim, 2015; Ribeiro et al., 2016b; Sun et al., 2019b; Holstein et al., 2019).”
Reasons, Values, Stakeholders: A Philosophical Framework for Explainable Artificial Intelligence (2021, background): “…concretely, the development of explainable AI systems is motivated by several social and ethical reasons (see, for example, [10, 11, 12, 13, 14, 15, 16, 17, 18, 19]): increasing societal acceptance of prediction-based decisions, establishing trust in the results of these decisions, making…”