Emerging synergies in causality and deep generative models: A survey

G Zhou, S Xie, G Hao, S Chen, B Huang, X Xu… - arXiv preprint arXiv …, 2023 - arxiv.org
In the field of artificial intelligence (AI), the quest to understand and model data-generating
processes (DGPs) is of paramount importance. Deep generative models (DGMs) have …

Cladder: Assessing causal reasoning in language models

Z Jin, Y Chen, F Leeb, L Gresele, O Kamal… - … conference on neural …, 2023 - openreview.net
The ability to perform causal reasoning is widely considered a core feature of intelligence. In
this work, we investigate whether large language models (LLMs) can coherently reason …

An interdisciplinary outlook on large language models for scientific research

J Boyko, J Cohen, N Fox, MH Veiga, JI Li, J Liu… - arXiv preprint arXiv …, 2023 - arxiv.org
In this paper, we describe the capabilities and constraints of Large Language Models
(LLMs) within disparate academic disciplines, aiming to delineate their strengths and …

Diffusion language models can perform many tasks with scaling and instruction-finetuning

J Ye, Z Zheng, Y Bao, L Qian, Q Gu - arXiv preprint arXiv:2308.12219, 2023 - arxiv.org
The recent surge of generative AI has been fueled by the generative power of diffusion
probabilistic models and the scalable capabilities of large language models. Despite their …

Towards causal foundation model: on duality between causal inference and attention

J Zhang, J Jennings, C Zhang, C Ma - arXiv preprint arXiv:2310.00809, 2023 - arxiv.org
Foundation models have brought changes to the landscape of machine learning,
demonstrating sparks of human-level intelligence across a diverse array of tasks. However …

GPT-based models meet simulation: how to efficiently use large-scale pre-trained language models across simulation tasks

PJ Giabbanelli - 2023 Winter Simulation Conference (WSC), 2023 - ieeexplore.ieee.org
The disruptive technology provided by large-scale pre-trained language models (LLMs)
such as ChatGPT or GPT-4 has received significant attention in several application domains …

Applying large language models for causal structure learning in non small cell lung cancer

N Naik, A Khandelwal, M Joshi, M Atre… - 2024 IEEE 12th …, 2024 - ieeexplore.ieee.org
Causal discovery is becoming a key part in medical AI research. These methods can
enhance healthcare by identifying causal links between biomarkers, demographics …

Llm-enhanced causal discovery in temporal domain from interventional data

P Li, X Wang, Z Zhang, Y Meng, F Shen, Y Li… - arXiv preprint arXiv …, 2024 - arxiv.org
In the field of Artificial Intelligence for Information Technology Operations, causal discovery
is pivotal for operation and maintenance of graph construction, facilitating downstream …

CausalBench: A Comprehensive Benchmark for Causal Learning Capability of Large Language Models

Y Zhou, X Wu, B Huang, J Wu, L Feng… - arXiv preprint arXiv …, 2024 - arxiv.org
Causality reveals fundamental principles behind data distributions in real-world scenarios,
and the capability of large language models (LLMs) to understand causality directly impacts …

Steering LLMs Towards Unbiased Responses: A Causality-Guided Debiasing Framework

J Li, Z Tang, X Liu, P Spirtes, K Zhang, L Leqi… - arXiv preprint arXiv …, 2024 - arxiv.org
Large language models (LLMs) can easily generate biased and discriminative responses.
As LLMs tap into consequential decision-making (eg, hiring and healthcare), it is of crucial …