English
Related papers

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

200 papers

Previous studies investigating the syntactic abilities of deep learning models have not targeted the relationship between the strength of the grammatical generalization and the amount of evidence to which the model is exposed during…

Computation and Language · Computer Science 2020-11-05 Tristan Thrush , Ethan Wilcox , Roger Levy

Prediction head is a crucial component of Transformer language models. Despite its direct impact on prediction, this component has often been overlooked in analyzing Transformers. In this study, we investigate the inner workings of the…

Computation and Language · Computer Science 2023-05-30 Goro Kobayashi , Tatsuki Kuribayashi , Sho Yokoi , Kentaro Inui

Detecting ambiguity is important for language understanding, including uncertainty estimation, humour detection, and processing garden path sentences. We assess language models' sensitivity to ambiguity by introducing an adversarial…

Computation and Language · Computer Science 2025-06-03 Antonia Karamolegkou , Oliver Eberle , Phillip Rust , Carina Kauf , Anders Søgaard

Are generative pre-trained transformer (GPT) models, trained only to predict the next token, implicitly learning a world model from which sequences are generated one token at a time? We address this question by deriving a causal…

Artificial Intelligence · Computer Science 2025-07-08 Raanan Y. Rohekar , Yaniv Gurwicz , Sungduk Yu , Estelle Aflalo , Vasudev Lal

Hate speech detection is a crucial area of research in natural language processing, essential for ensuring online community safety. However, detecting implicit hate speech, where harmful intent is conveyed in subtle or indirect ways,…

Computation and Language · Computer Science 2025-04-17 Yumin Kim , Hwanhee Lee

This study evaluates the GPT-4 Large Language Model's abductive reasoning in complex fields like medical diagnostics, criminology, and cosmology. Using an interactive interview format, the AI assistant demonstrated reliability in generating…

Artificial Intelligence · Computer Science 2023-07-21 Remo Pareschi

We present a simple way to merge masked language modeling with causal language modeling. This hybrid training objective results in a model that combines the strengths of both modeling paradigms within a single transformer stack: GPT-BERT…

Computation and Language · Computer Science 2024-12-31 Lucas Georges Gabriel Charpentier , David Samuel

Understanding predictions made by deep neural networks is notoriously difficult, but also crucial to their dissemination. As all machine learning based methods, they are as good as their training data, and can also capture unwanted biases.…

Computation and Language · Computer Science 2022-11-15 Amir Feder , Nadav Oved , Uri Shalit , Roi Reichart

While various approaches have recently been studied for bias identification, little is known about how implicit language that does not explicitly convey a viewpoint affects bias amplification in large language models. To examine the…

Computation and Language · Computer Science 2024-08-19 Abeer Aldayel , Areej Alokaili , Rehab Alahmadi

We have recently witnessed a number of impressive results on hard mathematical reasoning problems with language models. At the same time, the robustness of these models has also been called into question; recent works have shown that models…

Computation and Language · Computer Science 2023-06-09 Alessandro Stolfo , Zhijing Jin , Kumar Shridhar , Bernhard Schölkopf , Mrinmaya Sachan

Both humans and large language models are able to learn language without explicit structural supervision. What inductive biases make this learning possible? We address this fundamental cognitive question by leveraging transformer language…

Computation and Language · Computer Science 2023-10-31 Isabel Papadimitriou , Dan Jurafsky

Large language models sometimes produce structured, first-person descriptions that explicitly reference awareness or subjective experience. To better understand this behavior, we investigate one theoretically motivated condition under which…

Computation and Language · Computer Science 2025-10-31 Cameron Berg , Diogo de Lucena , Judd Rosenblatt

We investigate the extent to which modern, neural language models are susceptible to structural priming, the phenomenon whereby the structure of a sentence makes the same structure more probable in a follow-up sentence. We explore how…

Computation and Language · Computer Science 2022-06-30 Arabella Sinclair , Jaap Jumelet , Willem Zuidema , Raquel Fernández

Large scale Pre-trained Language Models have proven to be very powerful approach in various Natural language tasks. OpenAI's GPT-2 \cite{radford2019language} is notable for its capability to generate fluent, well formulated, grammatically…

Computation and Language · Computer Science 2020-06-11 Chaitra Hegde , Shrikumar Patil

Language modeling on large-scale datasets leads to impressive performance gains on various downstream language tasks. The validation pre-training loss (or perplexity in autoregressive language modeling) is often used as the evaluation…

Machine Learning · Computer Science 2022-10-26 Hong Liu , Sang Michael Xie , Zhiyuan Li , Tengyu Ma

Research in mechanistic interpretability seeks to explain behaviors of machine learning models in terms of their internal components. However, most previous work either focuses on simple behaviors in small models, or describes complicated…

Machine Learning · Computer Science 2022-11-02 Kevin Wang , Alexandre Variengien , Arthur Conmy , Buck Shlegeris , Jacob Steinhardt

Pre-trained language models (PLMs) like BERT are being used for almost all language-related tasks, but interpreting their behavior still remains a significant challenge and many important questions remain largely unanswered. In this work,…

Computation and Language · Computer Science 2021-09-28 Samuel Stevens , Yu Su

When people interpret text, they rely on inferences that go beyond the observed language itself. Inspired by this observation, we introduce a method for the analysis of text that takes implicitly communicated content explicitly into…

Computation and Language · Computer Science 2025-02-25 Alexander Hoyle , Rupak Sarkar , Pranav Goel , Philip Resnik

Pre-trained Language Models are widely used in many important real-world applications. However, recent studies show that these models can encode social biases from large pre-training corpora and even amplify biases in downstream…

Computation and Language · Computer Science 2023-10-20 Xiangjue Dong , Ziwei Zhu , Zhuoer Wang , Maria Teleki , James Caverlee

We present a systematic evaluation of large language models' sensitivity to argument roles, i.e., who did what to whom, by replicating psycholinguistic studies on human argument role processing. In three experiments, we find that language…

Computation and Language · Computer Science 2024-10-22 Eun-Kyoung Rosa Lee , Sathvik Nair , Naomi Feldman