Causal Interpretation

Causal interpretation aims to understand and model cause-and-effect relationships within data, moving beyond simple correlations to reveal underlying mechanisms. Current research focuses on developing and evaluating methods for causal inference in various domains, including natural language processing (using large language models and counterfactual reasoning), machine learning (leveraging techniques like disentanglement and structural equation models), and even social sciences (analyzing social media data to understand behavior). This work is significant because establishing causality allows for more robust predictions, improved model explainability, and better-informed decision-making in diverse fields like healthcare, AI safety, and social sciences.

Papers

November 5, 2024

Controlling for Unobserved Confounding with Large Language Model Classification of Patient Smoking Status
Samuel Lee, Zach Wood-Doughty
Large Language Model Classification Code Causal Inference Causal Effect Unobserved Confounders Causal Interpretation Unmeasured Confounding Unobservable State

October 25, 2024

Language Agents Meet Causality -- Bridging LLMs and Causal World Models
John Gkountouras, Matthias Lindemann, Phillip Lippe, Efstratios Gavves, Ivan Titov
Large Language Model Causal Representation Learning Causal Language Causal Knowledge Causal Approach Causal Interpretation Causal World Model

October 21, 2024

Linking Model Intervention to Causal Interpretation in Model Explanation
Debo Cheng, Ziqi Xu, Jiuyong Li, Lin Liu, Kui Yu, Thuc Duy Le, Jixue Liu
Model Explanation Causal Interpretation Model Interpretation Intervention Effect

July 23, 2024

Causal Understanding For Video Question Answering
Bhanu Prakash Reddy Guda, Tanmay Kulkarni, Adithya Sampath, Swarnashree Mysore Sathyendra
Video Question Answering Causal Interpretation Temporal Question Whole Video Neural Execution Tree

July 10, 2024

A Critical Review of Causal Reasoning Benchmarks for Large Language Models
Linying Yang, Vik Shirvaikar, Oscar Clivio, Fabian Falck
Causal Inference Causal Discovery Causal Pattern Critical Review Counterfactual Reasoning Causal Interpretation

June 30, 2024

Disentangled Representations for Causal Cognition
Filippo Torresan, Manuel Baltieri
Disentangled Representation Causal Interpretation Causal Perception

April 22, 2024

Mechanistic Interpretability for AI Safety -- A Review
Leonard Bereska, Efstratios Gavves
Narrative Review Artificial Intelligence System Mechanistic Interpretability Computational Approach AI Safety Causal Interpretation

April 9, 2024

CausalBench: A Comprehensive Benchmark for Causal Learning Capability of LLMs
Yu Zhou, Xingyu Wu, Beicheng Huang, Jibin Wu, Liang Feng, Kay Chen Tan
Comprehensive Benchmark Causal Learning Causal Interpretation Causal Network Causality Analysis CausalBench Challenge

February 1, 2024

Bayesian Causal Inference with Gaussian Process Networks
Enrico Giudice, Jack Kuipers, Giusi Moffa
Gaussian Process Causal Inference Causal Discovery Causal Graph Causal Interpretation

January 29, 2024

Emergent Explainability: Adding a causal chain to neural network inference
Adam Perrett
Explainable AI Emergent Communication Neural Network Inference Causal Interpretation Transparent AI

December 28, 2023

LLM4Causal: Democratized Causal Tools for Everyone via Large Language Model
Haitao Jiang, Lin Ge, Yuhe Gao, Jianian Wang, Rui Song
Large Language Model Decision Theory Causal Effect Identification Causal Interpretation

November 7, 2023

CRAB: Assessing the Strength of Causal Relationships Between Real-world Events
Angelika Romanou, Syrielle Montariol, Debjit Paul, Leo Laugier, Karl Aberer, Antoine Bosselut
Real World Causal Discovery Causal Structure Causal Relationship Causal Reasoning Estimated Team Strength Causal Interpretation Rule Abstraction

October 31, 2023

Causal Interpretation of Self-Attention in Pre-Trained Transformers
Raanan Y. Rohekar, Yaniv Gurwicz, Shami Nisimov
Self Attention Causal Structure Pre Trained Transformer Causal Explanation Causal Interpretation Zero Shot Causal

October 24, 2023

Causal Understanding of Why Users Share Hate Speech on Social Media
Dominique Geissler, Abdurahman Maarouf, Stefan Feuerriegel
Social Medium Causal Inference Hate Speech User Base Social Medium Data Propensity Score Causal Interpretation

April 25, 2023

CIMLA: Interpretable AI for inference of differential causal networks
Payam Dibaeinia, Saurabh Sinha
Scientific Inference Causal Relationship Single Cell Feature Attribution Method Interpretable AI Regulatory Network Causal Interpretation

April 11, 2023

Understanding Causality with Large Language Models: Feasibility and Opportunities
Cheng Zhang, Stefan Bauer, Paul Bennett, Jiangfeng Gao, Wenbo Gong, Agrin Hilmkil, Joel Jennings, Chao Ma, Tom Minka, Nick Pawlowski, James Vaughan
Large Language Model Emerging Opportunity Causal Pattern Task Feasibility Causal Knowledge Causal Query Causal Interpretation

December 6, 2022

Counterfactual reasoning: Do language models need world knowledge for causal understanding?
Jiaxuan Li, Lang Yu, Allyson Ettinger
Language Model High Quality Counterfactuals Counterfactual Reasoning Counterfactual Prediction Causal Interpretation World Knowledge Lexical Matching Psycholinguistic Experiment

October 27, 2022

Grasping Causality for the Explanation of Criticality for Automated Driving
Tjark Koopmann, Christian Neurohr, Lina Putze, Lukas Westhofen, Roman Gansch, Ahmad Adee
Line by Line Explanation Causal Structure Automated Driving Causal Knowledge Causal Query Causal Interpretation Criticality Ordered Spin Sequence Causality Based Perspective

October 17, 2022

Affective Idiosyncratic Responses to Music
Sky CH-Wang, Evan Li, Oliver Li, Smaranda Muresan, Zhou Yu
Music Industry Causal Interpretation Weibo Dataset Affective Response Music Cognition Self Disclosure

October 13, 2022

Counterfactual Multihop QA: A Cause-Effect Approach for Reducing Disconnected Reasoning
Wangzhen Guo, Qinkang Gong, Hanjiang Lai
Multi Hop Reasoning Human Reasoning Causal Interpretation Multi Hop QA