English
Related papers

Related papers: Implicit causality in GPT-2: a case study

200 papers

Natural language processing (NLP) models trained on people-generated data can be unreliable because, without any constraints, they can learn from spurious correlations that are not relevant to the task. We hypothesize that enriching models…

Computation and Language · Computer Science 2022-03-18 Alissa Ostapenko , Shuly Wintner , Melinda Fricke , Yulia Tsvetkov

Abstract grammatical knowledge - of parts of speech and grammatical patterns - is key to the capacity for linguistic generalization in humans. But how abstract is grammatical knowledge in large language models? In the human literature,…

Computation and Language · Computer Science 2023-11-16 James A. Michaelov , Catherine Arnett , Tyler A. Chang , Benjamin K. Bergen

Neural Machine Translation (NMT) models are state-of-the-art for machine translation. However, these models are known to have various social biases, especially gender bias. Most of the work on evaluating gender bias in NMT has focused…

Computation and Language · Computer Science 2024-11-05 Pushpdeep Singh

There has been increasing interest in evaluations of language models for a variety of risks and characteristics. Evaluations relying on natural language understanding for grading can often be performed at scale by using other language…

Computation and Language · Computer Science 2023-12-11 Simon Lermen , Ondřej Kvapil

Word embedding has become essential for natural language processing as it boosts empirical performances of various tasks. However, recent research discovers that gender bias is incorporated in neural word embeddings, and downstream tasks…

Computation and Language · Computer Science 2019-11-26 Zekun Yang , Juan Feng

Causal learning is the cognitive process of developing the capability of making causal inferences based on available information, often guided by normative principles. This process is prone to errors and biases, such as the illusion of…

Large language models have demonstrated surprising ability to perform in-context learning, i.e., these models can be directly applied to solve numerous downstream tasks by conditioning on a prompt constructed by a few input-output examples.…

Computation and Language · Computer Science 2023-04-03 Huan Ma , Changqing Zhang , Yatao Bian , Lemao Liu , Zhirui Zhang , Peilin Zhao , Shu Zhang , Huazhu Fu , Qinghua Hu , Bingzhe Wu

Modern natural language models such as the GPT-2/GPT-3 contain tremendous amounts of information about human belief in a consistently testable form. If these models could be shown to accurately reflect the underlying beliefs of the human…

Artificial Intelligence · Computer Science 2020-09-30 Philip Feldman , Antonio Bucchiarone

Illusions of causality occur when people develop the belief that there is a causal connection between two variables with no supporting evidence. This cognitive bias has been proposed to underlie many societal problems including social…

Artificial Intelligence · Computer Science 2024-10-16 María Victoria Carro , Francisca Gauna Selasco , Denise Alejandra Mester , Mario Alejandro Leiva

Mechanistic interpretability aims to reverse engineer neural networks by uncovering which high-level algorithms they implement. Causal abstraction provides a precise notion of when a network implements an algorithm, i.e., a causal model of…

Machine Learning · Computer Science 2025-03-17 Theodora-Mara Pîslar , Sara Magliacane , Atticus Geiger

With a handful of demonstration examples, large-scale language models show strong capability to perform various tasks by in-context learning from these examples, without any fine-tuning. We demonstrate that in-context learning performance…

Computation and Language · Computer Science 2022-11-10 Yiming Zhang , Shi Feng , Chenhao Tan

In various fields of knowledge creation, including science, new ideas often build on pre-existing information. In this work, we explore this concept within the context of language models. Specifically, we explore the potential of…

Computation and Language · Computer Science 2024-04-04 David Herel , Tomas Mikolov

The nouns of our language refer to either concrete entities (like a table) or abstract concepts (like justice or love), and cognitive psychology has established that concreteness influences how words are processed. Accordingly,…

Computation and Language · Computer Science 2025-05-22 Cosimo Iaia , Bhavin Choksi , Emily Wiebers , Gemma Roig , Christian J. Fiebach

Interpretability can be implemented to understand decisions taken by (black box) models, such as neural machine translation (NMT) or large language models (LLMs). Yet, research in this area has been limited in relation to a manifested…

Computation and Language · Computer Science 2026-03-05 Janiça Hackenbuchner , Arda Tezcan , Joke Daems

The ability to process idiomatic or literal multiword expressions is a crucial aspect of understanding and generating any language. The task of generating contextually relevant continuations for narratives containing idiomatic (or literal)…

Computation and Language · Computer Science 2023-11-07 Rhitabrat Pokharel , Ameeta Agrawal

Transformer language models can generate strikingly natural text by modeling language as a sequence of tokens, but by relying primarily on surface-level co-occurrence statistics they fail to form globally consistent latent representations…

Computation and Language · Computer Science 2026-01-14 Nasim Borazjanizadeh , James McClelland

As Machine Translation (MT) has become increasingly more powerful, accessible, and widespread, the potential for the perpetuation of bias has grown alongside its advances. While overt indicators of bias have been studied in machine…

Computation and Language · Computer Science 2021-08-25 Chloe Ciora , Nur Iren , Malihe Alikhani

We investigate neural models' ability to capture lexicosyntactic inferences: inferences triggered by the interaction of lexical and syntactic information. We take the task of event factuality prediction as a case study and build a…

Computation and Language · Computer Science 2018-08-21 Aaron Steven White , Rachel Rudinger , Kyle Rawlins , Benjamin Van Durme

Language models (LMs) are statistical models trained to assign probability to human-generated text. As such, it is reasonable to question whether they approximate linguistic variability exhibited by humans well. This form of statistical…

Computation and Language · Computer Science 2024-03-19 Evgenia Ilia , Wilker Aziz

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
‹ Prev 1 4 5 6 7 8 10 Next ›