# Causality for Large Language Models

arXiv: https://arxiv.org/abs/2410.15319 · HTML: https://mlsanity.com/paper/2410.15319/

## Key facts

- Cited by 25 papers in the map (data through 14 Oct 2026).
- Builds on 94 of its 124 references that are in the map.
- First posted on arXiv 20 Oct 2024.

## Builds on (most cited first, 30 of 94)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [PaLM: Scaling Language Modeling with Pathways](https://mlsanity.com/paper/2204.02311/) (2022)
- [DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter](https://mlsanity.com/paper/1910.01108/) (2019)
- [Deep reinforcement learning from human preferences](https://mlsanity.com/paper/1706.03741/) (2017)
- [Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback](https://mlsanity.com/paper/2204.05862/) (2022)
- [QLoRA: Efficient Finetuning of Quantized LLMs](https://mlsanity.com/paper/2305.14314/) (2023)
- [Qwen Technical Report](https://mlsanity.com/paper/2309.16609/) (2023)
- [ALBERT: A Lite BERT for Self-supervised Learning of Language Representations](https://mlsanity.com/paper/1909.11942/) (2019)
- [Sparks of Artificial General Intelligence: Early experiments with GPT-4](https://mlsanity.com/paper/2303.12712/) (2023)
- [A Survey of Large Language Models](https://mlsanity.com/paper/2303.18223/) (2023)
- [BLOOM: A 176B-Parameter Open-Access Multilingual Language Model](https://mlsanity.com/paper/2211.05100/) (2022)
- [Invariant Risk Minimization](https://mlsanity.com/paper/1907.02893/) (2019)
- [A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions](https://mlsanity.com/paper/2311.05232/) (2023)
- [A Survey on Evaluation of Large Language Models](https://mlsanity.com/paper/2307.03109/) (2023)
- [Unifying Large Language Models and Knowledge Graphs: A Roadmap](https://mlsanity.com/paper/2306.08302/) (2023)
- [Bias and Fairness in Large Language Models: A Survey](https://mlsanity.com/paper/2309.00770/) (2023)
- [A Prompt Pattern Catalog to Enhance Prompt Engineering with ChatGPT](https://mlsanity.com/paper/2302.11382/) (2023)
- [Large Language Models: A Survey](https://mlsanity.com/paper/2402.06196/) (2024)
- [Learning the Difference that Makes a Difference with Counterfactually-Augmented Data](https://mlsanity.com/paper/1909.12434/) (2019)
- [The Reversal Curse: LLMs trained on "A is B" fail to learn "B is A"](https://mlsanity.com/paper/2309.12288/) (2023)

## Built on by (most cited first, 25 of 25)

- [AI Agents vs. Agentic AI: A Conceptual Taxonomy, Applications and Challenges](https://mlsanity.com/paper/2505.10468/) (2025)
- [Unveiling Causal Reasoning in Large Language Models: Reality or Mirage?](https://mlsanity.com/paper/2506.21215/) (2025)
- [Large language models for artificial general intelligence (AGI): A survey of foundational principles and approaches](https://mlsanity.com/paper/2501.03151/) (2025)
- [Position: Foundation Models Need Digital Twin Representations](https://mlsanity.com/paper/2505.03798/) (2025)
- [A Survey on Enhancing Causal Reasoning Ability of Large Language Models](https://mlsanity.com/paper/2503.09326/) (2025)
- [CAUSAL3D: A Comprehensive Benchmark for Causal Learning from Visual Data](https://mlsanity.com/paper/2503.04852/) (2025)
- [Unveiling and Causalizing CoT: A Causal Pespective](https://mlsanity.com/paper/2502.18239/) (2025)
- [Learning Causal Graphs at Scale: A Foundation Model Approach](https://mlsanity.com/paper/2506.18285/) (2025)
- [GraphLocator: Graph-guided Causal Reasoning for Issue Localization](https://mlsanity.com/paper/2512.22469/) (2025)
- [Correlation or Causation: Analyzing the Causal Structures of LLM and LRM Reasoning Process](https://mlsanity.com/paper/2509.17380/) (2025)
- [Causality Is Key to Understand and Balance Multiple Goals in Trustworthy ML and Foundation Models](https://mlsanity.com/paper/2502.21123/) (2025)
- [C2DLM: Causal Concept-Guided Diffusion Large Language Models](https://mlsanity.com/paper/2511.22146/) (2025)
- [CRAwDAD: Causal Reasoning Augmentation with Dual-Agent Debate](https://mlsanity.com/paper/2511.22854/) (2025)
- [Benchmarking LLMs for Pairwise Causal Discovery in Biomedical and Multi-Domain Contexts](https://mlsanity.com/paper/2601.15479/) (2026)
- [Why LLMs Fail at Causal Discovery and How Interventional Agents Escape](https://mlsanity.com/paper/2605.27567/) (2026)
- [Beyond Correlation: Towards Causal Large Language Model Agents in Biomedicine](https://mlsanity.com/paper/2505.16982/) (2025)
- [On using AI for EEG-based BCI applications: problems, current challenges and future trends](https://mlsanity.com/paper/2506.16168/) (2025)
- [XGen-Q: An Explainable Domain-Adaptive LLM Framework with Retrieval-Augmented Generation for Software Security](https://mlsanity.com/paper/2510.19006/) (2025)
- [HOLOGRAPH: Active Causal Discovery via Sheaf-Theoretic Alignment of Large Language Model Priors](https://mlsanity.com/paper/2512.24478/) (2025)
- [CAMO: An Agentic Framework for Automated Causal Discovery from Micro Behaviors to Macro Emergence in LLM Agent Simulations](https://mlsanity.com/paper/2604.14691/) (2026)
- [Mathematical Reasoning via Intervention-Based Time-Series Causal Discovery Using LLMs as Concept Mastery Simulators](https://mlsanity.com/paper/2605.07600/) (2026)
- [Multimodal LLMs under Pairwise Modalities](https://mlsanity.com/paper/2605.21059/) (2026)
- [Causal-Audit: Explicit and Auditable Graph-based Reasoning via Target-Aware Causal Chain Construction](https://mlsanity.com/paper/2607.15281/) (2026)
- [The Illusion of textitWhat If: Evaluating the Breakdown of Counterfactual Reasoning in LLMs](https://mlsanity.com/paper/2608.27953/) (2026)
- [CoBe: A Benchmark For Conversational Counterfactual Text Editing](https://mlsanity.com/paper/2610.13057/) (2026)

## Abstract (arXiv)

Recent breakthroughs in artificial intelligence have driven a paradigm shift, where large language models (LLMs) with billions or trillions of parameters are trained on vast datasets, achieving unprecedented success across a series of language tasks. However, despite these successes, LLMs still rely on probabilistic modeling, which often captures spurious correlations rooted in linguistic patterns and social stereotypes, rather than the true causal relationships between entities and events. This limitation renders LLMs vulnerable to issues such as demographic biases, social stereotypes, and LLM hallucinations. These challenges highlight the urgent need to integrate causality into LLMs, moving beyond correlation-driven paradigms to build more reliable and ethically aligned AI systems. While many existing surveys and studies focus on utilizing prompt engineering to activate LLMs for causal knowledge or developing benchmarks to assess their causal reasoning abilities, most of these efforts rely on human intervention to activate pre-trained models. How to embed causality into the training process of LLMs and build more general and intelligent models remains unexplored. Recent research highlights that LLMs function as causal parrots, capable of reciting causal knowledge without truly understanding or applying it. These prompt-based methods are still limited to human interventional improvements. This survey aims to address this gap by exploring how causality can enhance LLMs at every stage of their lifecycle-from token embedding learning and foundation model training to fine-tuning, alignment, inference, and evaluation-paving the way for more interpretable, reliable, and causally-informed models. Additionally, we further outline six promising future directions to advance LLM development, enhance their causal reasoning capabilities, and address the current limitations these models face.