A Language for Counterfactual Generative Models

被引:0
|
作者
Tavares, Zenna [1 ]
Koppel, James [1 ]
Zhang, Xin [2 ]
Das, Ria [1 ]
Solar-Lezama, Armando [1 ]
机构
[1] MIT, CSAIL, Cambridge, MA 02139 USA
[2] Peking Univ, Dept Comp Sci & Technol, Key Lab High Confidence Software Technol, Minist Educ, Beijing, Peoples R China
关键词
D O I
暂无
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
We present OMEGA(C), a probabilistic programming language with support for counterfactual inference. Counterfactual inference means to observe some fact in the present, and infer what would have happened had some past intervention been taken, e.g. "given that medication was not effective at dose x, what is the probability that it would have been effective at dose 2x?" We accomplish this by introducing a new operator to probabilistic programming akin to Pearl's do, define its formal semantics, provide an implementation, and demonstrate its utility through examples in a variety of simulation models.
引用
收藏
页码:7180 / 7191
页数:12
相关论文
共 50 条
  • [1] Counterfactual Generative Smoothing for Imbalanced Natural Language Classification
    Han, Hojae
    Choi, Seungtaek
    Jeong, Myeongho
    Park, Jin-Woo
    Hwang, Seung-Won
    [J]. PROCEEDINGS OF THE 30TH ACM INTERNATIONAL CONFERENCE ON INFORMATION & KNOWLEDGE MANAGEMENT, CIKM 2021, 2021, : 3058 - 3062
  • [2] Counterfactual Memorization in Neural Language Models
    Zhang, Chiyuan
    Ippolito, Daphne
    Lee, Katherine
    Jagielski, Matthew
    Tramer, Florian
    Carlini, Nicholas
    [J]. ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 36 (NEURIPS 2023), 2023,
  • [3] Counterfactual Inference with Hidden Confounders Using Implicit Generative Models
    Zhu, Fujin
    Lin, Adi
    Zhang, Guangquan
    Lu, Jie
    [J]. AI 2018: ADVANCES IN ARTIFICIAL INTELLIGENCE, 2018, 11320 : 519 - 530
  • [4] Counterfactual image generation by disentangling data attributes with deep generative models
    Lim, Jieon
    Joo, Weonyoung
    [J]. COMMUNICATIONS FOR STATISTICAL APPLICATIONS AND METHODS, 2023, 30 (06) : 589 - 603
  • [5] Evaluating generative patent language models
    Lee, Jieh-Sheng
    [J]. WORLD PATENT INFORMATION, 2023, 72
  • [6] Probabilistic generative transformer language models for generative design of molecules
    Wei, Lai
    Fu, Nihang
    Song, Yuqi
    Wang, Qian
    Hu, Jianjun
    [J]. JOURNAL OF CHEMINFORMATICS, 2023, 15 (01)
  • [7] Probabilistic generative transformer language models for generative design of molecules
    Lai Wei
    Nihang Fu
    Yuqi Song
    Qian Wang
    Jianjun Hu
    [J]. Journal of Cheminformatics, 15
  • [8] Foundation Models, Generative AI, and Large Language Models
    Ross, Angela
    McGrow, Kathleen
    Zhi, Degui
    Rasmy, Laila
    [J]. CIN-COMPUTERS INFORMATICS NURSING, 2024, 42 (05) : 377 - 387
  • [9] Reducing Sentiment Bias in Language Models via Counterfactual Evaluation
    Huang, Po-Sen
    Zhang, Huan
    Jiang, Ray
    Stanforth, Robert
    Welbl, Johannes
    Rae, Jack W.
    Maini, Vishal
    Yogatama, Dani
    Kohli, Pushmeet
    [J]. FINDINGS OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS, EMNLP 2020, 2020, : 65 - 83
  • [10] CausaLM: Causal Model Explanation Through Counterfactual Language Models
    Feder, Amir
    Oved, Nadav
    Shalit, Uri
    Reichart, Roi
    [J]. COMPUTATIONAL LINGUISTICS, 2021, 47 (02) : 333 - 386