Counterfactual reasoning requires predicting how alternative events, contrary to what actually happened, might have resulted in different outcomes. Despite being considered a necessary component of AI-complete systems, few resources have been developed for evaluating counterfactual reasoning in narratives. In this paper, we propose Counterfactual Story Rewriting: given an original story and an intervening counterfactual event, the task is to minimally revise the story to make it compatible with the given counterfactual event. Solving this task will require deep understanding of causal narrative chains and counterfactual invariance, and integration of such story reasoning capabilities into conditional language generation models. We present TimeTravel, a new dataset of 29,849 counterfactual rewritings, each with the original story, a counterfactual event, and human-generated revision of the original story compatible with the counterfactual event. Additionally, we include 80,115 counterfactual "branches" without a rewritten storyline to support future work on semi- or un-supervised approaches to counterfactual story rewriting. Finally, we evaluate the counterfactual rewriting capacities of several competitive baselines based on pretrained language models, and assess whether common overlap and model-based automatic metrics for text generation correlate well with human scores for counterfactual rewriting.
With the advent of GDPR, the domain of explainable AI and model interpretability has gained added GDPR's Right to Explanation impetus. Methods to extract and communicate visibility General Data Protection Regulation (GDPR) is a regulation into decision-making models have become focused on data protection and regulations regarding algorithmic legal requirement. Two specific types of explanations, decision-making and is abiding on companies operating contrastive and counterfactual have been in the European Union. One of the controversial regulations identified as suitable for human understanding. In of this directive is the'Right to Explanation' which allows this paper, we propose a model agnostic method those significantly (socially) impacted by the decision of an and its systemic implementation to generate these algorithm to demand an explanation or rationale behind the explanations using shapely additive explanations decision (Eg: Being denied a loan application).
Counterfactual statements, e.g., "my headache would be gone had I taken an aspirin" are central to scientific discourse, and are formally interpreted as statements derived from "alternative worlds". However, since they invoke hypothetical states of affairs, often incompatible with what is actually known or observed, testing counterfactuals is fraught with conceptual and practical difficulties. In this paper, we provide a complete characterization of "testable counterfactuals," namely, counterfactual statements whose probabilities can be inferred from physical experiments. We provide complete procedures for discerning whether a given counterfactual is testable and, if so, expressing its probability in terms of experimental data.
In this paper, we study counterfactual fairness in text classification, which asks the question: How would the prediction change if the sensitive attribute discussed in the example were something else? We offer a heuristic for measuring this particular form of fairness in text classifiers by substituting individual tokens pertaining to attributes (e.g. sexual orientation, race, and religion), and describe the relationship with other notions, including individual and group fairness. Further, we offer methods, including hard ablation, blindness, and counterfactual logit pairing, for optimizing this counterfactual fairness metric during model training, bridging the robustness literature and the fairness literature. Empirically, counterfactual logit pairing performs as well as hard ablation and blindness to sensitive tokens, but generalizes better to unseen tokens. Interestingly, we find that in practice, the methods do not significantly harm classifier performance, and have varying tradeoffs with group fairness. These approaches, both for measurement and optimization, provide a new path forward for addressing counterfactual fairness issues.
We introduce an off-policy evaluation procedure for highlighting episodes where applying a reinforcement learned (RL) policy is likely to have produced a substantially different outcome than the observed policy. In particular, we introduce a class of structural causal models (SCMs) for generating counterfactual trajectories in finite partially observable Markov Decision Processes (POMDPs). We see this as a useful procedure for off-policy "debugging" in high-risk settings (e.g., healthcare); by decomposing the expected difference in reward between the RL and observed policy into specific episodes, we can identify episodes where the counterfactual difference in reward is most dramatic. This in turn can be used to facilitate review of specific episodes by domain experts. We demonstrate the utility of this procedure with a synthetic environment of sepsis management.