Related papers: Causal Micro-Narratives
This paper investigates the capability of LLMs in storytelling, focusing on narrative development and plot progression. We introduce a novel computational framework to analyze narratives through three discourse-level aspects: i) story arcs,…
Moral stories are a time-tested vehicle for transmitting values, yet modern NLP lacks a large, structured corpus that couples coherent narratives with explicit ethical lessons. We present TF1-EN-3M, to our knowledge the first open dataset…
Predictions about people, such as their expected educational achievement or their credit risk, can be performative and shape the outcome that they aim to predict. Understanding the causal effect of these predictions on the eventual outcomes…
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…
The increasing size and complexity of modern ML systems has improved their predictive capabilities but made their behavior harder to explain. Many techniques for model explanation have been developed in response, but we lack clear criteria…
In-context learning (ICL) excels at new tasks from minimal examples, yet we still lack a mechanistic explanation of how few-shot prompts shape a model's function vector (FV)--a causal activation direction that drives task behavior on the…
The paper describes the work that has been submitted to the 5th workshop on Challenges and Applications of Automated Extraction of socio-political events from text (CASE 2022). The work is associated with Subtask 1 of Shared Task 3 that…
The task of inferring high-level causal variables from low-level observations, commonly referred to as causal representation learning, is fundamentally underconstrained. As such, recent works to address this problem focus on various…
Adjusting for latent covariates is crucial for estimating causal effects from observational textual data. Most existing methods only account for confounding covariates that affect both treatment and outcome, potentially leading to biased…
Genes, proteins and other biological entities influence one another via causal molecular networks. Causal relationships in such networks are mediated by complex and diverse mechanisms, through latent variables, and are often specific to…
Meta-analysis, by synthesizing effect estimates from multiple studies conducted in diverse settings, stands at the top of the evidence hierarchy in clinical research. Yet, conventional approaches based on fixed- or random-effects models…
Causal representation learning (CRL) offers the promise of uncovering the underlying causal model by which observed data was generated, but the practical applicability of existing methods remains limited by the strong assumptions required…
Sentiment analysis (SA) aims to identify the sentiment expressed in a text, such as a product review. Given a review and the sentiment associated with it, this work formulates SA as a combination of two tasks: (1) a causal discovery task…
Despite surpassing human performance across mathematics, coding, and other knowledge-intensive tasks, large language models (LLMs) continue to struggle with causal reasoning. A core obstacle is the target data itself: causal systems are…
In this paper, we consider the process of transforming causal domain knowledge into a representation that aligns more closely with guidelines from causal data science. To this end, we introduce two novel tasks related to distilling causal…
Reasoning, a crucial aspect of NLP research, has not been adequately addressed by prevailing models including Large Language Model. Conversation reasoning, as a critical component of it, remains largely unexplored due to the absence of a…
Despite the major advances taken in causal modeling, causality is still an unfamiliar topic for many statisticians. In this paper, it is demonstrated from the beginning to the end how causal effects can be estimated from observational data…
Despite the remarkable success of large-scale Language Models (LLMs) such as GPT-3, their performances still significantly underperform fine-tuned models in the task of text classification. This is due to (1) the lack of reasoning ability…
We introduce context augmentation, a data-augmentation approach that uses large language models (LLMs) to generate contexts around observed strings as a means of facilitating valid frequentist inference. These generated contexts serve to…
We develop a method for generating causal post-hoc explanations of black-box classifiers based on a learned low-dimensional representation of the data. The explanation is causal in the sense that changing learned latent factors produces a…