Update 2026:

wait for a while

Update 2025:

• Nature Computational Science [Algorithms for reliable decision-making need causal reasoning] (https://www.nature.com/articles/s43588-025-00814-9)

• Arxiv 2025 [CARE: Turning LLMs Into Causal Reasoning Expert] (https://arxiv.org/abs/2511.16016)

• ACL 2025 Findings [Are the Values of LLMs Structurally Aligned with Humans? A Causal Perspective] (https://aclanthology.org/2025.findings-acl.1188/)

• ACL 2025 Findings [Beyond Verbal Cues: Emotional Contagion Graph Network for Causal Emotion Entailment] (https://arxiv.org/abs/2208.09329)

• ACL 2025 Findings [Causal Estimation of Tokenisation Bias] (https://aclanthology.org/2025.acl-long.1374.pdf)

• ACL 2025 [Causal Graph based Event Reasoning using Semantic Relation Experts] (https://aclanthology.org/2025.acl-long.1269.pdf)

• NAACL 2025 Findings [Causal Inference with Large Language Model- A Survey] (https://aclanthology.org/2025.findings-naacl.327/)

• ACL 2025 Findings [Causal interventions expose implicit situation models for commonsense language understanding] (https://arxiv.org/pdf/2207.11652)

• ACL 2025 Findings [CausalLink: An Interactive Evaluation Framework for Causal Reasoning] (https://aclanthology.org/2025.findings-acl.1147.pdf)

• ACL 2025 Findings [CausalAbstain- Enhancing Multilingual LLMs with Causal Reasoning for Trustworthy Abstention] (https://arxiv.org/pdf/2506.00519)

• ICLR 2025 [Causal Invariance-aware Augmentation for Brain Graph Contrastive Learning] (https://icml.cc/virtual/2025/poster/45908)

• ACL 2025 Findings [CausalRAG- Integrating Causal Graphs into Retrieval-Augmented Generation] (https://aclanthology.org/2025.findings-acl.1165/)

• ICML 2025 [Unbiased Evaluation of Large Language Models from a Causal Perspective] (https://arxiv.org/abs/2502.06655)

• ICLR 2025 [PROMPTING FAIRNESS- INTEGRATING CAUSALITY TO DEBIAS LARGE LANGUAGE MODELS] (https://arxiv.org/abs/2403.08743)

• ACL 2025 [On the Reliability of Large Language Models for Causal Discovery] (https://aclanthology.org/2025.acl-long.471/)

• ACL 2025 Findings [Multimodal Causal Reasoning Benchmark- Challenging Multimodal Large Language Models to Discern Causal Links Across Modalities] (https://aclanthology.org/2025.findings-acl.288.pdf)

• ICLR 2025 [MITIGATING MODALITY PRIOR-INDUCED HALLUCINATIONS IN MULTIMODAL LARGE LANGUAGE MODELS VIA DECIPHERING ATTENTION CAUSALITY] (https://arxiv.org/abs/2410.04780)

• ICLR 2025 [Do Contemporary Causal Inference Models Capture Real-World Heterogeneity? Findings from a Large-Scale Benchmark] (https://openreview.net/forum?id=Q2bJ2qgcP1

• ICLR 2025 [Language Agents Meet Causality -- Bridging LLMs and Causal World Models] (https://openreview.net/forum?id=y9A2TpaGsE)

• ICML 2025 [Preference Learning for AI Alignment: a Causal Perspective] (https://openreview.net/forum?id=iuD649wPAw)

• ICML 2025 [FairPFN: A Tabular Foundation Model for Causal Fairness] (https://openreview.net/pdf?id=I8DVh2jnEA)

• ICML 2025 [A Causal World Model Underlying Next Token Prediction: Exploring GPT in a Controlled Environment] (https://openreview.net/pdf?id=qA3xHJzF6B)

• ICML 2025 [Learning Invariant Causal Mechanism from Vision-Language Models] (https://openreview.net/pdf?id=GB9XiKIwfp)

• ICML 2025 [Towards the Causal Complete Cause of Multi-Modal Representation Learning] (https://openreview.net/pdf?id=9c4YYoBS4N)

• ICML 2025 [Hierarchical Reinforcement Learning with Targeted Causal Interventions] (https://arxiv.org/abs/2507.04373)

• ACL 2025 Findings [ExpliCa- Evaluating Explicit Causal Reasoning in Large Language Models] (https://aclanthology.org/2025.findings-acl.891.pdf)

• ACL 2025 Findings [Are the Values of LLMs Structurally Aligned with Humans? A Causal Perspective] (https://aclanthology.org/2025.findings-acl.1188/)

• ACL 2025 [Com2 - A Causal-Guided Benchmark for Exploring Complex Commonsense Reasoning in Large Language Models] (https://aclanthology.org/2025.acl-long.785/)

• ICML 2025 [Compositional Causal Reasoning Evaluation in Language Models] (https://openreview.net/forum?id=OJ3dQNRnsx)

• Arxiv 2024 [EFFICIENT CAUSAL GRAPH DISCOVERY USING LARGE LANGUAGE MODELS] (https://arxiv.org/abs/2402.01207)

• AAAI 2025 [When Open-Vocabulary Visual Question Answering Meets Causal Adapter- Benchmark and Approach] (https://ojs.aaai.org/index.php/AAAI/article/view/33072)

• AAAI 2025 [Toward Causal Generative Modeling- From Representation to Generation] (https://ojs.aaai.org/index.php/AAAI/article/view/35215

• AAAI 2025 [Representation Learning- A Causal Perspective] (https://ojs.aaai.org/index.php/AAAI/article/view/35124)

• IJCAI 2025 [MCF-Spouse- A Multi-Label Causal Feature Selection Method with Optimal Spouses Discovery] (https://www.ijcai.org/proceedings/2025/658)

• IJCAI 2025 [PROMPTING FAIRNESS- INTEGRATING CAUSALITY TO DEBIAS LARGE LANGUAGE MODELS] (https://arxiv.org/abs/2403.08743)

• IJCAI 2025 [Enhancing Automated Grading in Science Education through LLM-Driven Causal Reasoning and Multimodal Analysis] (https://www.ijcai.org/proceedings/2025/1150)

• IJCAI 2025 [Eliciting Causal Abilities in Large Language Models for Reasoning Tasks] (https://arxiv.org/abs/2412.15314)

• AAAI 2025 [Causal Prompting- Debiasing Large Language Model Prompting Based on Front-Door Adjustment] (https://arxiv.org/abs/2403.02738)

• CVPR 2025 [Cross-modal Causal Relation Alignment for Video Question Grounding] (https://openaccess.thecvf.com/content/CVPR2025/html/Chen_Cross-modal_Causal_Relation_Alignment_for_Video_Question_Grounding_CVPR_2025_paper.html)

• CVPR 2025 [Joint Scheduling of Causal Prompts and Tasks for Multi-Task Learning] (https://openaccess.thecvf.com/content/CVPR2025/papers/Li_Joint_Scheduling_of_Causal_Prompts_and_Tasks_for_Multi-Task_Learning_CVPR_2025_paper.pdf)

• CVPR 2025 [Sim-to-Real Causal Transfer:A Metric Learning Approach to Causally-Aware Interaction Representations] (https://openaccess.thecvf.com/content/CVPR2025/papers/Rahimi_Sim-to-Real_Causal_Transfer_A_Metric_Learning_Approach_to_Causally-Aware_Interaction_CVPR_2025_paper.pdf)

• CVPR 2025 [Towards Precise Embodied Dialogue Localization via Causality Guided Diffusion] (https://openaccess.thecvf.com/content/CVPR2025/papers/Wang_Towards_Precise_Embodied_Dialogue_Localization_via_Causality_Guided_Diffusion_CVPR_2025_paper.pdf)

------------------------------------------------------------I am a line------------------------------------------------------------------------------------------------------------------------------I am a line------------------------------------------------------------------------

• TACL 2024 [Causal Inference in Natural Language Processing- Estimation, Prediction, Interpretation and Beyond] (https://aclanthology.org/2022.tacl-1.66/)
• Blog Adjustment (Frontdoor, Backdoor)
• Survey [The Odyssey of Commonsense Causality:From Foundational Benchmarks to Cutting-Edge Reasoning] (https://arxiv.org/pdf/2406.19307)
• Survey [Causal Inference with Large Language Model: A Survey] (https://aclanthology.org/2025.findings-naacl.327.pdf)
• Book [Causality for Natural Language Processing] (https://arxiv.org/pdf/2504.14530)

Six groups of causality in LLM and VLM

1. Evaluation of causal ability of LLM and VLM by prompt (in-context learning, ….), factual knowledge

2. Improve the model/framework performance on causal task (four levels: causality discovery, association, intervention, counteractuals)

3. Spurious relation elimination between features and prediction by causality inference on downstream tasks (mainly interventions, Do(), backdoor and frontdoor adjustment), aiming to improve model performance with consideration of causal inference

4. Domain adaptation of task with causal learning (related to #3) and the relationship between causality and generalization (exist or not) and why (probing task)

5. Bias elimination from Dataset or modality by causal inference

6. Metrics and benchmark for causal ability evaluation

Probing work, assessment in LLM

• ICLR 2024 [CAN LARGE LANGUAGE MODELS INFER CAUSATION FROM CORRELATION] (https://arxiv.org/abs/2306.05836)

• NIPS 2023 [CLADDER: Assessing Causal Reasoning in Language Models] (https://arxiv.org/abs/2312.04350)

• ACL 2023 [A Causal Framework to Quantify the Robustness of Mathematical Reasoning with Language Models] (https://arxiv.org/abs/2210.12023)

• Blog [Do causal predictors generalize better to new domains?] (https://www.aimodels.fyi/papers/arxiv/do-causal-predictors-generalize-better-to-new)

• EMNLP 2024 [CELLO: Causal Evaluation of Large Vision-Language Models] (https://aclanthology.org/2024.emnlp-main.1247.pdf)

• NAACL [Original or Translated? A Causal Analysis of the Impact of Translationese on Machine Translation Performance] (https://arxiv.org/abs/2205.02293)

• EMNLP 2024 [The Causal Influence of Grammatical Gender on Distributional Semantics] (https://arxiv.org/pdf/2311.18567)

• MM 2022 [Counterfactual Reasoning for Out-of-distribution Multimodal Sentiment Analysis] (https://arxiv.org/pdf/2207.11652)

Datasets

• EMNLP 2024 [CELLO: Causal Evaluation of Large Vision-Language Models] (https://aclanthology.org/2024.emnlp-main.1077.pdf)

Application in NLP task

Sentiment analysis

• Arxiv 2024 [On the Causal Nature of Sentiment Analysis] (https://arxiv.org/abs/2404.11055)

• COLING 2022 [Causal Intervention Improves Implicit Sentiment Analysis] (https://arxiv.org/abs/2208.09329)

• ACL 2024 [DINER- Debiasing Aspect-based Sentiment Analysis with Multi-variable Causal Inference] (https://arxiv.org/abs/2403.01166)

• ICLR 2025 reject [MULTIMODAL SENTIMENT ANALYSIS BASED ON CAUSAL REASONING] (https://arxiv.org/pdf/2412.07292)

• MM 2022 [Counterfactual reasoning for out-of-distribution multimodal sentiment analysis] (https://arxiv.org/pdf/2207.11652)

• Information Fusion [AtCAF- Attention-based causality-aware fusion network for multimodal sentiment analysis] (https://www.sciencedirect.com/science/article/pii/S1566253524005037)

Fact Checking

• AAAI 2024 [Causal walk: Debiasing multi-hop fact verification with front-door adjustment] (https://arxiv.org/abs/2403.02698)

• ACL 2024 [CHECKWHY: Causal Fact Verification via Argument Structure] (https://arxiv.org/pdf/2408.10918)

• ACL 2023 [Causal Intervention and Counterfactual Reasoning for Multi-modal Fake News Detection] (https://aclanthology.org/2023.acl-long.37/)

• AAAI 2024 [Where and How to Attack? A Causality-Inspired Recipe for Generating Counterfactual Adversarial Examples] (https://arxiv.org/abs/2312.13628)

• SIGKDD 2021 [Causal understanding of fake news dissemination on social media] (https://arxiv.org/pdf/2010.10580)

• CVPR 2021 [Counterfactual VQA: A Cause-Effect Look at Language Bias] (https://arxiv.org/abs/2006.04315)

Named Entity Recognition

• EMNLP 2022 [Distilling Causal Effect from Miscellaneous Other-Class for Continual Named Entity Recognition] (https://aclanthology.org/2022.emnlp-main.236/)

• ACL 2021 [De-biasing distantly supervised named entity recognition via causal intervention] (https://arxiv.org/abs/2106.09233)

Reasoning

• CVPR 2023 [Discovering the Real Association: Multimodal Causal Reasoning in Video Question Answering] (https://openaccess.thecvf.com/content/CVPR2023/papers/Zang_Discovering_the_Real_Association_Multimodal_Causal_Reasoning_in_Video_Question_CVPR_2023_paper.pdf)

• ACL 2023 [Causal Intervention for Mitigating Name Bias in Machine Reading Comprehension] (https://aclanthology.org/2023.findings-acl.812/)

• ACL 2024 [Identifying while Learning for Document Event Causality Identification] (https://arxiv.org/pdf/2405.20608)

• CVPR 2024 [Mitigating Object Hallucinations in Large Vision-Language Models through Visual Contrastive Decoding] (https://arxiv.org/abs/2311.16922)

• CVPR 2024 [Mitigating Object Hallucinations in Large Vision-Language Models through Visual Contrastive Decoding] (https://arxiv.org/abs/2311.16922)

• ICLR 2024 [Alleviating Hallucination in Multi-Modal Large Language Models via Over-Trust Penalty and Retrospection-Allocation] (https://arxiv.org/abs/2311.17911)

Sequence Modeling

• IJCAI 2019 [Learning disentangled semantic representation for domain adaptation] (https://arxiv.org/abs/2012.11807)

• AAAI 2024 [Identification of Causal Structure with Latent Variables Based on Higher Order Cumulants] (https://arxiv.org/abs/2312.11934)

• NIPS 2021 [A Causal Lens for Controllable Text Generation] (https://arxiv.org/abs/2201.09119)

• AAAI 2021 [Time Series Domain Adaptation via Sparse Associative Structure Alignment] (https://arxiv.org/abs/2012.11797)

• COLING 2022 [Incorporating Causal Analysis into Diversified and Logical Response Generation] (https://aclanthology.org/2022.coling-1.30v2.pdf)

• CVPR 2024 [CaDeT- a Causal Disentanglement Approach for Robust Trajectory Prediction in Autonomous Driving] (https://openaccess.thecvf.com/content/CVPR2024/papers/Pourkeshavarz_CaDeT_a_Causal_Disentanglement_Approach_for_Robust_Trajectory_Prediction_in_CVPR_2024_paper.pdf)

• ICML 2024 [CauDiTS: Causal Disentangled Domain Adaptation of Multivariate Time Series] (https://openreview.net/pdf?id=lsavZkUjFZ)

• PLMR 2022 [Partial disentanglement for domain adaptation] (https://proceedings.mlr.press/v162/kong22a.html)

• Arxiv 2024 [On the Identification of Temporally Causal Representation with Instantaneous Dependence] (https://arxiv.org/abs/2405.15325)

• Arxiv 2024 [From Orthogonality to Dependency- Learning Disentangled Representation for Multi-Modal Time-Series Sensing Signals] (https://arxiv.org/abs/2405.16083)

• NIPS 2024 [Subspace Identification for Multi-Source Domain Adaptation] (https://arxiv.org/abs/2310.04723)

• ICML 2022 [Causal Transformer for Estimating Counterfactual Outcomes] (https://proceedings.mlr.press/v162/melnychuk22a.html)

• NIPS 2024 [Causal Contrastive Learning for Counterfactual Regression Over Time] (https://arxiv.org/abs/2406.00535)

Image Caption

• CVPR 2022 [Show, Deconfound and Tell: Image Captioning with Causal Inference] (https://openaccess.thecvf.com/content/CVPR2022/papers/Liu_Show_Deconfound_and_Tell_Image_Captioning_With_Causal_Inference_CVPR_2022_paper.pdf))

Reinforcement Learning

• ICLR 2024 [Fine-Grained Causal Dynamics Learning with Quantization for Improving Robustness in Reinforcement Learning] (https://arxiv.org/abs/2406.03234) (https://www.sanghacklee.me/assets/2024-ICML-CRL-poster.pdf)

Causal inference and LLM

• CVPR 2024 [Causal-CoG- A Causal-Effect Look at Context Generation for Boosting Multi-modal Language Models] (https://arxiv.org/abs/2312.06685)

• ACL 2022 [How pre-trained language models capture factual knowledge? a causal-inspired analysis] (https://arxiv.org/abs/2203.16747)

• EMNLP 2024 [LLMs Are Prone to Fallacies in Causal Inference] (https://aclanthology.org/2024.emnlp-main.590.pdf)

• EMNLP 2024 [Can Large Language Models Learn Independent Causal Mechanisms?] (https://aclanthology.org/2024.emnlp-main.381.pdf)

• ACL 2024 [Causal-Guided Active Learning for Debiasing Large Language Models] (https://arxiv.org/pdf/2408.12942?)

• Arxiv 2024 [Causal Evaluation of Language Models] (https://arxiv.org/abs/2405.00622)

• ACL 2024 [CAUSALCITE: A Causal Formulation of Paper Citations] (https://arxiv.org/abs/2311.02790)

• CVPR 2021 [Causal attention for vision-language tasks] (https://arxiv.org/abs/2103.03493)

• ACL 2024 [AGR: Reinforced Causal Agent-Guided Self-explaining Rationalization] (https://aclanthology.org/2024.acl-short.47.pdf)

• CVPR 2024 [Vision-and-Language Navigation via Causal Learning] (https://openaccess.thecvf.com/content/CVPR2024/papers/Wang_Vision-and-Language_Navigation_via_Causal_Learning_CVPR_2024_paper.pdf)

• ICML 2024 [Adaptive Online Experimental Design for Causal Discovery] (https://arxiv.org/abs/2405.11548)

• IJCAI 2019 [CounterFactual Regression with Importance Sampling Weights] (https://www.ijcai.org/proceedings/2019/0815.pdf)

• Arxiv 2024 [Mitigating Modality Prior-Induced Hallucinations in Multimodal Large Language Models via Deciphering Attention Causality] (https://arxiv.org/abs/2410.04780)

• COLM 2024 [LLM as a Mastermind: A Survey of Strategic Reasoning with Large Language Models] (https://arxiv.org/abs/2404.01230)

• Arxiv 2024 [Large Language Models and Causal Inference in Collaboration: A Comprehensive Survey] (https://arxiv.org/abs/2403.09606)

• CVPR 2024 [Link-Context Learning for Multimodal LLMs] (https://openaccess.thecvf.com/content/CVPR2024/papers/Tai_Link-Context_Learning_for_Multimodal_LLMs_CVPR_2024_paper.pdf)

• EMNLP 2023 [Causal Document-Grounded Dialogue Pre-training] (http://aclanthology.org/2023.emnlp-main.443/)

• Arxiv 2025 [CausalRAG: Integrating Causal Graphs into Retrieval-Augmented Generation] (https://arxiv.org/abs/2503.19878)