Causal Intervention

Causal intervention is a rapidly developing field focusing on identifying and manipulating causal relationships within complex systems, particularly in machine learning models. Current research emphasizes using causal inference techniques, such as do-calculus and backdoor adjustment, to improve model robustness, fairness, and interpretability by mitigating confounding factors and spurious correlations. This approach is applied across various domains, including natural language processing, computer vision, and healthcare, leading to advancements in tasks like counterfactual detection, model merging, and domain generalization. The ultimate goal is to build more reliable and trustworthy AI systems that are less susceptible to biases and better reflect true causal mechanisms.

Papers

October 28, 2024

Causal Interventions on Causal Paths: Mapping GPT-2's Reasoning From Syntax to Semantics
Isabelle Lee, Joshua Lum, Ziyi Liu, Dani Yogatama
Complex Reasoning Causal Structure Semantics Surfaced Causal Direction Natural Language Reasoning Causal Intervention GPT 2

October 14, 2024

A Practical Approach to Causal Inference over Time
Martina Cinquini, Isacco Beretta, Salvatore Ruggieri, Isabel Valera
Causal Inference Time Matter Autoregressive Model Causal Model Causal Intervention Practical Approach

September 25, 2024

Topic-aware Causal Intervention for Counterfactual Detection
Thong Nguyen, Truc-My Nguyen
High Quality Counterfactuals Causal Intervention Counterfactual State

August 18, 2024

Activated Parameter Locating via Causal Intervention for Model Merging
Fanshuang Kong, Richong Zhang, Ziqiao Wang
Fine Tuned Model Model Merging Feature Redundancy Causal Intervention

August 7, 2024

Mixstyle-Entropy: Domain Generalization with Causal Intervention and Perturbation
Luyao Tang, Yuxuan Yuan, Chaoqi Chen, Xinghao Ding, Yue Huang
Causal Intervention Causal Variable Small Perturbation Causal Entropy

July 24, 2024

Revisiting Who's Harry Potter: Towards Targeted Unlearning from a Causal Intervention Perspective
Yujian Liu, Yang Zhang, Tommi Jaakkola, Shiyu Chang
Causal Intervention Knowledge Unlearning LLM Unlearning

June 13, 2024

Characterising Interventions in Causal Games
Manuj Mishra, James Fox, Michael Wooldridge
Health Intervention Causal Intervention Causal Query Mechanism Synthesis

March 26, 2024

Have Faith in Faithfulness: Going Beyond Circuit Overlap When Finding Model Mechanisms
Michael Hanna, Sandro Pezzelle, Yonatan Belinkov
Causal Intervention Edge Inference Interpretability Research Recent Language Model Circuit Analysis Interpretability Scale Computational Graph Model Mechanism

March 5, 2024

Causal Prompting: Debiasing Large Language Model Prompting based on Front-Door Adjustment
Congzhi Zhang, Linhai Zhang, Jialong Wu, Deyu Zhou, Yulan He
Large Language Model Natural Language Model Bias Causal Direction Causal Intervention Front Door Adjustment

February 18, 2024

Graph Out-of-Distribution Generalization via Causal Intervention
Qitian Wu, Fan Nie, Chenxiao Yang, Tianyi Bao, Junchi Yan
Strong Generalization Causal Inference Causal Intervention Graph Out of Distribution Generalization Ego Graph

November 20, 2023

Revealing behavioral impact on mobility prediction networks through causal interventions
Ye Hong, Yanan Xin, Simon Dirmeier, Fernando Perez-Cruz, Martin Raubal
Causal Intervention Mobility Prediction Next Location Prediction Mobility Model

September 17, 2023

Towards Debiasing Frame Length Bias in Text-Video Retrieval via Causal Intervention
Burak Satar, Hongyuan Zhu, Hanwang Zhang, Joo Hwee Lim
Video Text Retrieval Causal Intervention Text Video Retrieval Length Bias Video Text Task Temporal Bias Object Co Occurrence

August 7, 2023

Diffusion Model in Causal Inference with Unmeasured Confounders
Tatsuhiro Shimizu
Diffusion Model Causal Inference Unobserved Confounders Causal Intervention Causal Query Counterfactual Distribution

June 6, 2023

Causal interventions expose implicit situation models for commonsense language understanding
Takateru Yamakoshi, James L. McClelland, Adele E. Goldberg, Robert D. Hawkins
Language Processing Causal Intervention Context Shift Situation Model Commonsense Understanding

May 31, 2023

Causal Intervention for Measuring Confidence in Drug-Target Interaction Prediction
Wenting Ye, Chen Li, Yang Xie, Wen Zhang, Hong-Yu Zhang, Bowen Wang, Debo Cheng, Zaiwen Feng
Drug Discovery High Confidence Confidence Estimation Causal Intervention Drug Target Interaction Drug Target Interaction Prediction

May 25, 2023

Passive learning of active causal strategies in agents and language models
Andrew Kyle Lampinen, Stephanie C Y Chan, Ishita Dasgupta, Andrew J Nam, Jane X Wang
Language Model Pre Trained Language Model Agent Smith Causal Intervention Passive Learning Active Causal

May 24, 2023

A Causal View of Entity Bias in (Large) Language Models
Fei Wang, Wenjie Mo, Yiwei Wang, Wenxuan Zhou, Muhao Chen
Language Model Structural Causal Model Causal Intervention Knowledge Conflict Causal View Entity Bias

May 23, 2023

Causal Intervention for Abstractive Related Work Generation
Jiachang Liu, Qi Zhang, Chongyang Shi, Usman Naseem, Shoujin Wang, Ivor Tsang
Causal Intervention Causal Intervention Module Related Work Generation

May 10, 2023

Clothes-Invariant Feature Learning by Causal Intervention for Clothes-Changing Person Re-identification
Xulin Li, Yan Lu, Bin Liu, Yuenan Hou, Yating Liu, Qi Chu, Wanli Ouyang, Nenghai Yu
Causal Intervention

March 10, 2023

Improving Weakly Supervised Sound Event Detection with Causal Intervention
Yifei Xin, Dongchao Yang, Fan Cui, Yujun Wang, Yuexian Zou
Structural Causal Model Sound Event Detection Sound Event Causal Intervention CLIP Level

Causal Intervention

Papers

Causal Interventions on Causal Paths: Mapping GPT-2's Reasoning From Syntax to Semantics

A Practical Approach to Causal Inference over Time

Topic-aware Causal Intervention for Counterfactual Detection

Activated Parameter Locating via Causal Intervention for Model Merging

Mixstyle-Entropy: Domain Generalization with Causal Intervention and Perturbation

Revisiting Who's Harry Potter: Towards Targeted Unlearning from a Causal Intervention Perspective

Characterising Interventions in Causal Games

Have Faith in Faithfulness: Going Beyond Circuit Overlap When Finding Model Mechanisms

Causal Prompting: Debiasing Large Language Model Prompting based on Front-Door Adjustment

Graph Out-of-Distribution Generalization via Causal Intervention

Revealing behavioral impact on mobility prediction networks through causal interventions

Towards Debiasing Frame Length Bias in Text-Video Retrieval via Causal Intervention

Diffusion Model in Causal Inference with Unmeasured Confounders

Causal interventions expose implicit situation models for commonsense language understanding

Causal Intervention for Measuring Confidence in Drug-Target Interaction Prediction

Passive learning of active causal strategies in agents and language models

A Causal View of Entity Bias in (Large) Language Models

Causal Intervention for Abstractive Related Work Generation

Clothes-Invariant Feature Learning by Causal Intervention for Clothes-Changing Person Re-identification

Improving Weakly Supervised Sound Event Detection with Causal Intervention