paper-with-me

Papers

How does the pre-training objective affect what large language models learn about linguistic properties?

2022-03-20 · ACL 2022 5 · Ahmed Alajrami, Nikolaos Aletras

Several pre-training objectives, such as masked language modeling (MLM), have been proposed to pre-train language models (e.g. BERT) with the aim of learning better language representations. However, to the best of our knowledge, no previous work so far has investigated how different pre-training objectives affect what BERT learns about linguistics properties. We hypothesize that linguistically motivated objectives such as MLM should help BERT to acquire better linguistic knowledge compared to other non-linguistically motivated objectives that are not intuitive or hard for humans to guess the association between the input and the label to be predicted. To this end, we pre-train BERT with two linguistically motivated objectives and three non-linguistically motivated ones. We then probe for linguistic characteristics encoded in the representation of the resulting models. We find strong evidence that there are only small differences in probing performance between the representations learned by the two different types of objectives. These surprising results question the dominant narrative of linguistically informed pre-training.

📄 PDF Abstract BibTeX arXiv:2203.10415

Code (1)

aajrami/acl2022-pre-training-objectives-probing 공식 구현 pytorch

Tasks

Language ModelingLanguage ModellingMasked Language Modeling

Methods 이 논문이 사용한 방법론

Multi-Head Attention 설명 없음
Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Attention Dropout Attention Dropout is a type of dropout used in attention-based architectures, where elements are randomly dropped out of the…
Residual Connection 설명 없음
Linear Warmup With Linear Decay Linear Warmup With Linear Decay is a learning rate schedule in which we increase the learning rate linearly for $n$ updates and then linearly decay afterwards.
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Weight Decay 설명 없음

Similar Papers 제목 키워드 기반

How does the pre-training objective affect what large language models learn about linguistic properties?

2021-11-16 · ACL ARR November 2021 11 · Anonymous

Several pre-training objectives, such as masked language modeling (MLM), have been proposed to pre-train language models (e.g. BERT) with the aim of learning better language representations. However, to the best of our k…

Language ModelingLanguage ModellingMasked Language Modeling

Understanding the Role of Input Token Characters in Language Models: How Does Information Loss Affect Performance?

2023-10-26 · Ahmed Alajrami, Katerina Margatina, Nikolaos Aletras

Understanding how and what pre-trained language models (PLMs) learn about language is an open challenge in natural language processing. Previous work has focused on identifying whether they capture semantic and syntactic…

Is Saki #delicious? The Food Perception Gap on Instagram and Its Relation to Health

2017-02-21 · Ferda Ofli, Yusuf Aytar, Ingmar Weber, Raggi al Hammouri 외

Food is an integral part of our life and what and how much we eat crucially affects our health. Our food choices largely depend on how we perceive certain characteristics of food, such as whether it is healthy, delicious…

Relation

When Role-playing, Do Models Believe What They Say?

2026-06-09 · Benjamin Sturgeon, David Africa, Sid Black arxiv

Language models can state that "the Earth orbits the Sun" and, when role-playing Aristotle, assert the opposite. Recent work argues that persona adoption is fundamental to how language models behave, with models selectin…

Better World Models Can Lead to Better Post-Training Performance

2025-12-03 · Prakhar Gupta, Henry Conklin, Sarah-Jane Leslie, Andrew Lee arxiv

In this work we study how explicit world-modeling objectives affect the internal representations and downstream capability of Transformers across different training stages. We use a controlled 2x2x2 Rubik's Cube and ask:…

Reinforcement Learning