English
Related papers

Related papers: Causal Interventions on Causal Paths: Mapping GPT-…

200 papers

How does a cause lead to an effect, and which intermediate causal steps explain their connection? This work scrutinizes the mechanistic causal reasoning capabilities of large language models (LLMs) to answer these questions through the task…

Artificial Intelligence · Computer Science 2026-03-19 Liesbeth Allein , Nataly Pineda-Castañeda , Andrea Rocci , Marie-Francine Moens

Mechanistic interpretability identifies internal circuits responsible for model behaviors, yet translating these findings into human-understandable explanations remains an open problem. We present a pipeline that bridges circuit-level…

Computation and Language · Computer Science 2026-03-12 Ajay Pravin Mahale

The ability to robustly identify causal relationships is essential for autonomous decision-making and adaptation to novel scenarios. However, accurately inferring causal structure requires integrating both world knowledge and abstract…

Machine Learning · Computer Science 2025-06-17 Khurram Yamin , Shantanu Gupta , Gaurav R. Ghosal , Zachary C. Lipton , Bryan Wilder

Numerous decision-making tasks require estimating causal effects under interventions on different parts of a system. As practitioners consider using large language models (LLMs) to automate decisions, studying their causal reasoning…

Machine Learning · Computer Science 2024-12-24 Tejas Kasetty , Divyat Mahajan , Gintare Karolina Dziugaite , Alexandre Drouin , Dhanya Sridhar

Large language models (LLMs) have shown various ability on natural language processing, including problems about causality. It is not intuitive for LLMs to command causality, since pretrained models usually work on statistical associations,…

Computation and Language · Computer Science 2024-08-27 Chenyang Zhang , Haibo Tong , Bin Zhang , Dongyu Zhang

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 about causality. Much of the existing work in natural…

Causal reasoning is one of the primary bottlenecks that Large Language Models (LLMs) must overcome to attain human-level intelligence. Recent studies indicate that LLMs display near-random performance on reasoning tasks. To address this, we…

Logic in Computer Science · Computer Science 2025-11-10 Abdolmahdi Bagheri , Matin Alinejad , Mahdi Dehshiri , Kevin Bello , Alireza Akhondi-Asl

Due to the size and complexity of modern large language models (LLMs), it has proven challenging to uncover the underlying mechanisms that models use to solve reasoning problems. For instance, is their reasoning for a specific problem…

Machine Learning · Computer Science 2025-06-23 Guan Zhe Hong , Nishanth Dikkala , Enming Luo , Cyrus Rashtchian , Xin Wang , Rina Panigrahy

Causal reasoning is a cornerstone of human intelligence and a critical capability for artificial systems aiming to achieve advanced understanding and decision-making. This thesis delves into various dimensions of causal reasoning and…

Computation and Language · Computer Science 2025-04-22 Zhijing Jin

The causal capabilities of large language models (LLMs) are a matter of significant debate, with critical implications for the use of LLMs in societally impactful domains such as medicine, science, law, and policy. We conduct a "behavorial"…

Artificial Intelligence · Computer Science 2024-08-21 Emre Kıcıman , Robert Ness , Amit Sharma , Chenhao Tan

We show how causal interventions in Transformer models provide insights into English syntax by focusing on a long-standing challenge for syntactic theory: syntactic islands. Extraction from coordinated verb phrases is often degraded, yet…

Computation and Language · Computer Science 2026-04-16 Sasha Boguraev , Kyle Mahowald

With the rapid progress of Large Language Models (LLMs), it becomes increasingly important to understand their abilities and limitations. In two experiments, we investigate the causal and compositional reasoning abilities of LLMs and humans…

Computation and Language · Computer Science 2025-02-27 Magnus F. Gjerde , Vanessa Cheung , David Lagnado

Rigorous evaluation of the causal effects of semantic features on language model predictions can be hard to achieve for natural language reasoning problems. However, this is such a desirable form of analysis from both an interpretability…

Computation and Language · Computer Science 2024-04-04 Julia Rozanova , Marco Valentino , André Freitas

Rigorous evaluation of the causal effects of semantic features on language model predictions can be hard to achieve for natural language reasoning problems. However, this is such a desirable form of analysis from both an interpretability…

Computation and Language · Computer Science 2024-04-04 Julia Rozanova , Marco Valentino , Andre Freitas

Causal inference has shown potential in enhancing the predictive accuracy, fairness, robustness, and explainability of Natural Language Processing (NLP) models by capturing causal relationships among variables. The emergence of generative…

Computation and Language · Computer Science 2025-03-24 Xiaoyu Liu , Paiheng Xu , Junda Wu , Jiaxin Yuan , Yifan Yang , Yuhang Zhou , Fuxiao Liu , Tianrui Guan , Haoliang Wang , Tong Yu , Julian McAuley , Wei Ai , Furong Huang

Causality is essential for understanding complex systems, such as the economy, the brain, and the climate. Constructing causal graphs often relies on either data-driven or expert-driven approaches, both fraught with challenges. The former…

Artificial Intelligence · Computer Science 2024-06-12 Kai-Hendrik Cohrs , Gherardo Varando , Emiliano Diaz , Vasileios Sitokonstantinou , Gustau Camps-Valls

Causal inference has been a pivotal challenge across diverse domains such as medicine and economics, demanding a complicated integration of human knowledge, mathematical reasoning, and data mining capabilities. Recent advancements in…

Computation and Language · Computer Science 2025-02-11 Jing Ma

We present a mechanistic interpretability study of GPT-2 that causally examines how sentiment information is processed across its transformer layers. Using systematic activation patching across all 12 layers, we test the hypothesized…

Computation and Language · Computer Science 2025-12-09 Amartya Hatua

Transformer-based language models have achieved significant success; however, their internal mechanisms remain largely opaque due to the complexity of non-linear interactions and high-dimensional operations. While previous studies have…

Artificial Intelligence · Computer Science 2025-02-17 Lin Zhang , Lijie Hu , Di Wang

Causal reasoning capability is critical in advancing large language models (LLMs) toward strong artificial intelligence. While versatile LLMs appear to have demonstrated capabilities in understanding contextual causality and providing…

Artificial Intelligence · Computer Science 2025-06-30 Haoang Chi , He Li , Wenjing Yang , Feng Liu , Long Lan , Xiaoguang Ren , Tongliang Liu , Bo Han
‹ Prev 1 2 3 10 Next ›