| Challenge: | generative language models have redefined performance standards across tasks . current research on the influence of training data on autoregressivity remains underexplored . |
| Approach: | They propose a parameterized simulation to assess the impact of training examples on the training dynamics of GPT models. |
| Outcome: | The proposed approach compares existing methods with existing methods across training scenarios in generative language models, spanning tasks across 14 million to 2.8 billion parameters. |
Similar Papers
Unlearning Traces the Influential Training Data of Language Models (2024.acl-long)
Copied to clipboard
| Challenge: | Large language models (LLMs) exhibit remarkable abilities without being explicitly trained for such tasks. |
| Approach: | They propose a method that unlearns a test dataset and evaluates the unlearned model on training datasets. |
| Outcome: | The proposed method resembles UnTrac, while being efficient for massive training datasets. |
A Survey of Post-Training Scaling in Large Language Models (2025.acl-long)
Copied to clipboard
Hanyu Lai, Xiao Liu, Junjie Gao, Jiale Cheng, Zehan Qi, Yifan Xu, Shuntian Yao, Dan Zhang, Jinhua Du, Zhenyu Hou, Xin Lv, Minlie Huang, Yuxiao Dong, Jie Tang
| Challenge: | Large language models (LLMs) have demonstrated proficiency in understanding and generating human natural languages. |
| Approach: | They propose a framework for scaling large language models using supervised fine-tuning, RLxF and test-time compute methodologies. |
| Outcome: | The proposed model can be used to understand and generate human natural languages. |
Unveiling Imitation Learning: Exploring the impact of Data Falsity to Large Language Model (2024.findings-acl)
Copied to clipboard
| Challenge: | Recent studies have focused on improving open-source language models through imitation learning. |
| Approach: | They propose to use false pairs to control the factuality ratio of a dataset to study noise. |
| Outcome: | The proposed model is based on a Falsity-Controllable dataset with false pairs and false pairs to control the factuality ratio. |
How Much Do Language Models Copy From Their Training Data? Evaluating Linguistic Novelty in Text Generation Using RAVEN (2023.tacl-1)
Copied to clipboard
| Challenge: | Current language models generate high-quality text, but are they copying it or have they learned generalizable linguistic abstractions? |
| Approach: | They propose a suite of analyses for assessing the novelty of generated text . they focus on sequential structure (n-grams) and syntactic structure (syntactical structure). |
| Outcome: | The proposed model-generated text is as novel as the baseline human-generated model- generated text, but it is copied substantially, the authors show . |
Training Dynamics for Text Summarization Models (2022.findings-acl)
Copied to clipboard
| Challenge: | Pre-trained language models have shown impressive results when fine-tuned on large summarization datasets. |
| Approach: | They analyze the training dynamics for generation models, focusing on summarization . they find that a propensity to copy the input is learned early in the training process . |
| Outcome: | The proposed model learns at different stages of fine-tuning, the authors show . they show that factual errors are learnt in later stages, but not at high-loss tokens . |
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. |
The Curious Decline of Linguistic Diversity: Training Language Models on Synthetic Text (2024.findings-naacl)
Copied to clipboard
| Challenge: | a new study examines the effects of training language models on synthetic data generated by their predecessors. |
| Approach: | They propose to use recursive finetuning techniques to assess linguistic diversity of models. |
| Outcome: | The proposed metrics show a decrease in diversity of model outputs through successive iterations, especially for tasks demanding high levels of creativity. |
Curating Datasets for Better Performance with Example Training Dynamics (2023.findings-acl)
Copied to clipboard
| Challenge: | Existing methods to improve data quality but rely on data quantity to improve performance are not effective. |
| Approach: | They propose a method for weighing the relative importance of examples in a dataset based on their Example Training dynamics (ETD) they propose an active learning approach for computing ETD during training rather than as a preprocessing step. |
| Outcome: | The proposed method can be used to improve performance in in-distribution and out-of-distortion testing. |
GPT-Fathom: Benchmarking Large Language Models to Decipher the Evolutionary Path towards GPT-4 and Beyond (2024.findings-naacl)
Copied to clipboard
| Challenge: | Existing LLM leaderboards often reference scores reported in other papers without consistent settings and prompts, which may encourage cherry-picking favored settings and for better results. |
| Approach: | They propose an open-source and reproducible LLM evaluation suite built on top of OpenAI Evals that systematically evaluates 10+ leading LLMs and OpenAI’s legacy models on 20+ curated benchmarks across 7 capability categories. |
| Outcome: | The evaluation suite is built on top of OpenAI Evals and evaluates 10+ leading LLMs and OpenAI’s legacy models on 20+ curated benchmarks across 7 capability categories. |
It’s Not Just Size That Matters: Small Language Models Are Also Few-Shot Learners (2021.naacl-main)
Copied to clipboard
| Challenge: | Pretraining ever-larger language models on massive corpora requires enormous amounts of compute. |
| Approach: | They propose to convert textual inputs into cloze questions that contain a task description . they also exploit unlabeled data to improve their performance . |
| Outcome: | The proposed model outperforms GPT-3 with PET/iPET with cloze questions and unlabeled data. |