Isolated Causal Effects of Natural Language
This work addresses the need for causal understanding in language technologies to inform applications like content moderation or misinformation detection, though it is incremental in formalizing existing challenges.
The paper tackles the problem of estimating isolated causal effects of language interventions, such as factual inaccuracies, on outcomes like reader beliefs, by introducing a formal framework that addresses bias from poor approximation of non-focal language, and validates it with experiments on semi-synthetic and real-world data.
As language technologies become widespread, it is important to understand how changes in language affect reader perceptions and behaviors. These relationships may be formalized as the isolated causal effect of some focal language-encoded intervention (e.g., factual inaccuracies) on an external outcome (e.g., readers' beliefs). In this paper, we introduce a formal estimation framework for isolated causal effects of language. We show that a core challenge of estimating isolated effects is the need to approximate all non-focal language outside of the intervention. Drawing on the principle of omitted variable bias, we provide measures for evaluating the quality of both non-focal language approximations and isolated effect estimates themselves. We find that poor approximation of non-focal language can lead to bias in the corresponding isolated effect estimates due to omission of relevant variables, and we show how to assess the sensitivity of effect estimates to such bias along the two key axes of fidelity and overlap. In experiments on semi-synthetic and real-world data, we validate the ability of our framework to correctly recover isolated effects and demonstrate the utility of our proposed measures.