Papers with PD
Pre-training Distillation for Large Language Models: A Design Space Exploration (2025.acl-long)
Copied to clipboard
| Challenge: | Knowledge distillation (KD) aims to transfer knowledge from a large teacher model to a smaller student model for model compression. |
| Approach: | They extend knowledge distillation to the pre-training phase of large language models . they first conduct an experiment using a teacher LLM to distill a 1.9B student LLM . |
| Outcome: | The proposed model can be used to distill a 1.9B student model using a teacher LLM. |
AEG: Argumentative Essay Generation via A Dual-Decoder Model with Content Planning (2022.emnlp-main)
Copied to clipboard
| Challenge: | Existing studies on argument generation focus on generating individual short arguments, while research on generating long and coherent argumentative essays is under-explored. |
| Approach: | They propose a task to automatically generate argumentative essays using a writing prompt. |
| Outcome: | The proposed model generates persuasive essays with higher diversity and less repetition compared to baselines. |
Evaluating Large Language Models along Dimensions of Language Variation: A Systematik Invesdigatiom uv Cross-lingual Generalization (2024.emnlp-main)
Copied to clipboard
| Challenge: | Xue et al., 2021) show that large language models suffer from performance degradation on unseen closely-related languages and dialects relative to their high-resource language neighbour (HRLN). |
| Approach: | They propose to model phonological, morphological, and lexical distance as Bayesian noise processes to synthesize artificial languages that are controllably distant from the HRLN. |
| Outcome: | The proposed model offers insights on model robustness to isolated and composed linguistic phenomena and the impact of task and HRL characteristics on PD. |
Preference Curriculum: LLMs Should Always Be Pretrained on Their Preferred Data (2025.findings-acl)
Copied to clipboard
Xuemiao Zhang, Xu Liangyu, Feiyu Duan, Yongwei Zhou, Sirui Wang, Rongxiang Weng, Jingang Wang, Xunliang Cai
| Challenge: | Existing methods of uniformly sampling data throughout the pretraining process are suboptimal because they overlook the model's evolving data preferences. |
| Approach: | They propose a Perplexity Difference (PD) based Preference Curriculum learning framework which perceives and uses the data preferred by LLMs as their capabilities improve . they propose PDPC to complete the arrangement of the dataset offline and ensure continuous training without interruption. |
| Outcome: | The proposed framework surpasses baselines on 1.3B and 3B models and achieves an increased average accuracy of over 8.1% across MMLU and CMMLU. |