paper-with-me

Papers

OpenGrok: Enhancing SNS Data Processing with Distilled Knowledge and Mask-like Mechanisms

2025-02-11 · Lumen AI, Zaozhuang No. 28 Middle School, Shihao Ji, Zihui Song, Fucheng Zhong, Jisen Jia, Zhaobo Wu, Zheyi Cao, Tianhao Xu

This report details Lumen Labs' novel approach to processing Social Networking Service (SNS) data. We leverage knowledge distillation, specifically a simple distillation method inspired by DeepSeek-R1's CoT acquisition, combined with prompt hacking, to extract valuable training data from the Grok model. This data is then used to fine-tune a Phi-3-mini model, augmented with a mask-like mechanism specifically designed for handling the nuances of SNS data. Our method demonstrates state-of-the-art (SOTA) performance on several SNS data processing tasks, outperforming existing models like Grok, Phi-3, and GPT-4. We provide a comprehensive analysis of our approach, including mathematical formulations, engineering details, ablation studies, and comparative evaluations.

📄 PDF Abstract BibTeX arXiv:2502.07312

Code (1)

Lumen-Laboratory/OpenGrok 공식 구현 pytorch

Tasks

Knowledge DistillationMMLUText-To-SQL

Methods 이 논문이 사용한 방법론

Golden Queue Managers 설명 없음
Attention 설명 없음
Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Residual Connection 설명 없음
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…
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.

Similar Papers 제목 키워드 기반

Enhancing deep learning models for time series classification via knowledge distillation

2026-07-07 · Javidan Abdullayev, Maxime Devanne, Jonathan Weber, Germain Forestier arxiv

Deep learning has achieved remarkable success in various domains including time series analysis, computer vision and natural language processing. However, high computational and memory demands of state-of-the-art archite…

Time Series ClassificationKnowledge DistillationTime Series Analysis

Multi-Stage Balanced Distillation: Addressing Long-Tail Challenges in Sequence-Level Knowledge Distillation

2024-06-19 · YuHang Zhou, Jing Zhu, Paiheng Xu, Xiaoyu Liu 외

Large language models (LLMs) have significantly advanced various natural language processing tasks, but deploying them remains computationally expensive. Knowledge distillation (KD) is a promising solution, enabling the …

Knowledge Distillation

Enhancing Knowledge Distillation for LLMs with Response-Priming Prompting

2024-12-18 · Vijay Goyal, Mustafa Khan, Aprameya Tirupati, Harveer Saini 외

Large language models (LLMs) have demonstrated remarkable performance across a wide range of natural language processing (NLP) tasks. However, these models are often difficult to deploy due to significant computational r…

GSM8KKnowledge DistillationTransfer Learning

Improving generalizability of distilled self-supervised speech processing models under distorted settings

2022-10-14 · Kuan-Po Huang, Yu-Kuan Fu, Tsu-Yuan Hsu, Fabian Ritter Gutierrez 외

Self-supervised learned (SSL) speech pre-trained models perform well across various speech processing tasks. Distilled versions of SSL models have been developed to match the needs of on-device speech applications. Thoug…

Knowledge Distillation

DistilQwen2.5: Industrial Practices of Training Distilled Open Lightweight Language Models

2025-04-21 · Chengyu Wang, Junbing Yan, Yuanhao Yue, Jun Huang

Enhancing computational efficiency and reducing deployment costs for large language models (LLMs) have become critical challenges in various resource-constrained scenarios. In this work, we present DistilQwen2.5, a famil…

Computational EfficiencyInstruction Following