Honey, I Shrunk the Language: Language Model Behavior at Reduced Scale. (2023.findings-acl)
Copied to clipboard
| Challenge: | Recent studies have focused on high-compute settings, leaving the question of when these abilities begin to emerge largely unanswered. |
| Approach: | They investigate whether effects of pre-training can be observed when problem size is reduced, modeling a smaller, reduced-vocabulary language. |
| Outcome: | The proposed model performance is correlated with pre-training perplexity and performance. |
Similar Papers
How does the pre-training objective affect what large language models learn about linguistic properties? (2022.acl-short)
Copied to clipboard
| Challenge: | Several pre-training objectives have been proposed to pre-train language models . but, to our knowledge, no studies have investigated how different pre- training objectives affect what BERT learns about linguistic properties. |
| Approach: | They propose to use masked language modeling to pre-train language models . they propose to optimize a mangled language modeling objective to learn linguistic information . |
| Outcome: | The proposed objectives improve BERT's learning of linguistic properties compared to non-linguistically motivated objectives. |
To Pretrain or Not to Pretrain: Examining the Benefits of Pretrainng on Resource Rich Tasks (2020.acl-main)
Copied to clipboard
| Challenge: | Existing studies on pretraining NLP models with variants of Masked Language Model (MLM) objectives have shown that the number of training samples used in the downstream task is limited. |
| Approach: | They propose to use MLM objectives to pretrain NLP models with variants of Masked Language Model (MLM) objectives to improve accuracy on downstream tasks. |
| Outcome: | The proposed model can reach a diminishing return point as the supervised data size increases significantly. |
Not-Just-Scaling Laws: Towards a Better Understanding of the Downstream Impact of Language Model Design Decisions (2025.emnlp-main)
Copied to clipboard
Emmy Liu, Amanda Bertsch, Lintang Sutawika, Lindia Tjuatja, Patrick Fernandes, Lara Marinov, Michael Chen, Shreya Singhal, Carolin Lawrence, Aditi Raghunathan, Kiril Gashteovski, Graham Neubig
| Challenge: | Language model performance is largely dependent on pretraining decisions, but scaling laws based on only these two aspects do not always explain downstream task performance. |
| Approach: | They meta-analyze 92 open-source pretrained models to quantify their impact on performance. |
| Outcome: | The framework lays a foundation for more systematic investigation of how model development choices shape final capabilities. |
Mask More and Mask Later: Efficient Pre-training of Masked Language Models by Disentangling the [MASK] Token (2022.findings-emnlp)
Copied to clipboard
| Challenge: | Large-scale pre-trained MLMs can be used to generalize well to a wide range of tasks. |
| Approach: | They propose to append [MASK]s at a later layer to reduce sequence length for earlier layers. |
| Outcome: | The proposed method outperforms RoBERTa for 6 out of 8 GLUE tasks on average by 0.4%. |
Frustratingly Simple Pretraining Alternatives to Masked Language Modeling (2021.emnlp-main)
Copied to clipboard
| Challenge: | Masked language modeling (MLM) is widely used in natural language processing for self-supervised learning of text representations. |
| Approach: | They propose to use token-level classification tasks as main pretraining objectives instead of Masked language modeling (MLM) . Empirical results show that pretraining a model with 41% of the BERT-BASE’s parameters, BERT MEDIUM results in only a 1% drop in GLUE scores with their best objective. |
| Outcome: | Empirical results show that the proposed methods achieve comparable or better performance to MLM using a BERT-BASE architecture. |
Scaling Laws for BERT in Low-Resource Settings (2023.findings-acl)
Copied to clipboard
| Challenge: | Large language models require huge training corpora, which is unobtainable for most NLP practitioners. |
| Approach: | They propose power-law formulas that relate model size, corpora size and computation power to find the optimal settings in advance given a fixed budget. |
| Outcome: | The proposed models perform better on MLM and NLU tasks on four languages of different linguistic characteristics. |
How does the task complexity of masked pretraining objectives affect downstream performance? (2023.findings-acl)
Copied to clipboard
| Challenge: | Masked language modeling (MLM) is a widely used self-supervised pretraining objective. |
| Approach: | They propose to use a mask-based objective to predict a token that is replaced with a masked token given its context. |
| Outcome: | The proposed objectives show that they should have half the complexity needed to perform comparably to MLM. |
Training Trajectories of Language Models Across Scales (2023.acl-long)
Copied to clipboard
Mengzhou Xia, Mikel Artetxe, Chunting Zhou, Xi Victoria Lin, Ramakanth Pasunuru, Danqi Chen, Luke Zettlemoyer, Veselin Stoyanov
| Challenge: | Scaling up language models has led to unprecedented performance gains, but little is understood about how the training dynamics change as models get larger. |
| Approach: | They analyze the training checkpoints of different-sized OPT models on next-token prediction, sequence-level generation and downstream tasks. |
| Outcome: | The results show that language models of different sizes learn more during training . small models halt at hallucinations, larger ones learn to assign lower probabilities . |
How Far Is Too Far? Studying the Effects of Domain Discrepancy on Masked Language Models (2024.lrec-main)
Copied to clipboard
| Challenge: | Pre-trained masked language models perform strongly on a wide variety of NLP tasks. |
| Approach: | They propose a mechanism to quantify the difference in domains between the pre-trained model and the task and partition it using a cloze task. |
| Outcome: | The proposed model performs better on openly available e-commerce datasets than the original model on scientific and biomedical datasets. |
The Diminishing Returns of Masked Language Models to Science (2023.findings-acl)
Copied to clipboard
| Challenge: | Existing studies have shown that masked language models can improve downstream tasks by pretraining larger models for longer on more data. |
| Approach: | They empirically evaluate the extent to which these results extend to tasks in science by using 14 domain-specific transformer-based masked language models. |
| Outcome: | The proposed model can improve on 12 scientific tasks, but not all. |