mlsanityData to 14 Oct 2026

Isolated Causal Effects of Natural Language

arXiv 2410.14812 ↗First posted 18 Oct 2024cs.CL stat.MEcited by 2

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 21 of its 44 references that are in the map. First posted on arXiv 18 Oct 2024.

Builds on

21 of 44 references.

References · 21

  1. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,372
  2. 2017A Broad-Coverage Challenge Corpus for Sentence Understanding through Inferencecited by 2,682
  3. 2018Know What You Don't Know: Unanswerable Questions for SQuADcited by 1,554
  4. 2020MiniLM: Deep Self-Attention Distillation for Task-Agnostic Compression of Pre-Trained Transformerscited by 1,463
  5. 2020MPNet: Masked and Permuted Pre-training for Language Understandingcited by 981
  6. 2018A Survey Of Methods For Explaining Black Box Modelscited by 973
  7. 2018What is the Effect of Importance Weighting in Deep Learning?cited by 251
  8. 2023"Kelly is a Warm Person, Joseph is a Role Model": Gender Biases in LLM-Generated Reference Letterscited by 199
  9. 2022Semiparametric doubly robust targeted double machine learning: a reviewcited by 133
  10. 2023Fairness And Bias in Artificial Intelligence: A Brief Survey of Sources, Impacts, And Mitigation Strategiescited by 85
  11. 2018How to Make Causal Inferences Using Textscited by 59
  12. 2016Empath: Understanding Topic Signals in Large-Scale Textcited by 51
9 more
  1. 2020Causal Effects of Linguistic Propertiescited by 39
  2. 2022Doubly Robust Distributionally Robust Off-Policy Evaluation and Learningcited by 34
  3. 2021Long Story Short: Omitted Variable Bias in Causal Machine Learningcited by 23
  4. 2024End-To-End Causal Effect Estimation from Unstructured Natural Language Datacited by 18
  5. 2024Causal Inference with Generative Artificial Intelligence: Application to Texts as Treatmentscited by 16
  6. 2024Optimizing Language Models for Human Preferences is a Causal Inference Problemcited by 8
  7. 2023Text-Transport: Toward Learning Causal Effects of Natural Languagecited by 6
  8. 2023SenteCon: Leveraging Lexicons to Learn Human-Interpretable Language Representationscited by 2
  9. 2024Towards Representation Learning for Weighting Problems in Design-Based Causal Inferencecited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026Omitted Variable Bias in Language Models Under Distribution Shiftcited by 1
  2. 2026Social Circuits behind Multi-agent Echo Chamberscited by 0