Causality for Natural Language Processing
It addresses the problem of improving causal understanding in AI systems for applications like computational social science, though it appears incremental in building foundational knowledge.
This thesis investigates the causal reasoning abilities of large language models (LLMs) across various NLP tasks, identifying challenges and opportunities to enhance their capabilities through novel datasets and benchmarks.
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 understanding in large language models (LLMs). It encompasses a series of studies that explore the causal inference skills of LLMs, the mechanisms behind their performance, and the implications of causal and anticausal learning for natural language processing (NLP) tasks. Additionally, it investigates the application of causal reasoning in text-based computational social science, specifically focusing on political decision-making and the evaluation of scientific impact through citations. Through novel datasets, benchmark tasks, and methodological frameworks, this work identifies key challenges and opportunities to improve the causal capabilities of LLMs, providing a comprehensive foundation for future research in this evolving field.