paper-with-me

Papers

DRPruning: Efficient Large Language Model Pruning through Distributionally Robust Optimization

2024-11-21 · Hexuan Deng, Wenxiang Jiao, Xuebo Liu, Min Zhang, Zhaopeng Tu

Large language models (LLMs) deliver impressive results but face challenges from increasing model sizes and computational costs. Structured pruning reduces model size and speeds up inference but often causes uneven degradation across domains, leading to biased performance. To address this, we propose DRPruning, which incorporates distributionally robust optimization to restore balanced performance across domains, along with further improvements to enhance robustness. Experiments in monolingual and multilingual settings show that our method surpasses similarly sized models in pruning and continued pretraining over perplexity, downstream tasks, and instruction tuning. We further provide analysis demonstrating the robustness of our method towards various domains and distribution shifts. Furthermore, our method automatically determines optimal reference losses and data ratios, suggesting potential for broader applications. Our code is available at https://github.com/hexuandeng/DRPruning.

📄 PDF Abstract BibTeX arXiv:2411.14055

Code (1)

hexuandeng/drpruning 공식 구현 pytorch

Tasks

Language ModelingLanguage ModellingLarge Language Model

Methods 이 논문이 사용한 방법론

Pruning 설명 없음

Similar Papers 제목 키워드 기반

DRoP: Distributionally Robust Pruning

2024-04-08 · Artem Vysogorets, Kartik Ahuja, Julia Kempe

In the era of exceptionally data-hungry models, careful selection of the training data is essential to mitigate the extensive costs of deep learning. Data pruning offers a solution by removing redundant or uninformative …

Fairness

Distributionally Robust Token Optimization in RLHF

2026-03-27 · Yeping Jin, Jiaming Hu, Ioannis Ch. Paschalidis arxiv

Large Language Models (LLMs) tend to respond correctly to prompts that align well with the data they were trained and fine-tuned on. Yet, small shifts in wording, format, or language can trigger surprisingly large failur…

Reinforcement Learning

Risk-Averse MDPs under Reward Ambiguity

2023-01-03 · Haolin Ruan, Zhi Chen, Chin Pang Ho

We propose a distributionally robust return-risk model for Markov decision processes (MDPs) under risk and reward ambiguity. The proposed model optimizes the weighted average of mean and percentile performances, and it c…

Structured Pruning of Large Language Models

2019-10-10 · EMNLP 2020 11 · Ziheng Wang, Jeremy Wohlwend, Tao Lei

Large language models have recently achieved state of the art performance across a wide variety of natural language tasks. Meanwhile, the size of these models and their latency have significantly increased, which makes t…

Language ModelingLanguage ModellingModel CompressionWord Embeddings

IG-Pruning: Input-Guided Block Pruning for Large Language Models

2025-11-04 · Kangyu Qiao, Shaolei Zhang, Yang Feng arxiv

With the growing computational demands of large language models (LLMs), efficient inference has become increasingly critical for practical deployment. Depth pruning has emerged as a promising approach for reducing the co…