paper-with-me

홈 › Papers

SELF: Self-Extend the Context Length With Logistic Growth Function

2025-05-22 · Phat Thanh Dang, Saahil Thoppay, Wang Yang, Qifan Wang, Vipin Chaudhary, Xiaotian Han

Large language models suffer issues when operated on long contexts that are larger than their training context length due to the standard position encoding for tokens in the attention layer. Tokens a long distance apart will rarely have an effect on each other and long prompts yield unexpected results. To solve this problem, we propose SELF (Self-Extend the Context Length With Logistic Growth Function): a solution of grouping consecutive tokens at varying group sizes using a logistic capacity equation combined with a constant group size at smaller relative distances. Our model had an increase in performance of up to 12% compared to the LongLM extension method in LEval (specifically on the Qwen model). On summarization related tasks in LongBench, our model performed up to 6.4% better than LongLM (specifically on the Llama-2-7b model). On reading comprehension tasks from LEval, our model performed up to 5.4% better than the LongLM. Our code is available at https://github.com/alexeipc/SELF-LLM.

📄 PDF Abstract BibTeX arXiv:2505.17296

Code (1)

alexeipc/self-llm 공식 구현 pytorch

Tasks

Reading Comprehension

Methods 이 논문이 사용한 방법론

Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Attention 설명 없음

Similar Papers 제목 키워드 기반

LLM Maybe LongLM: Self-Extend LLM Context Window Without Tuning

2024-01-02 · Hongye Jin, Xiaotian Han, Jingfeng Yang, Zhimeng Jiang 외

It is well known that LLMs cannot generalize well to long contexts whose lengths are larger than the training sequence length. This poses challenges when employing LLMs for processing long input sequences during inferenc…

InAttention: Linear Context Scaling for Transformers

2024-10-09 · Joseph Eisner

VRAM requirements for transformer models scale quadratically with context length due to the self-attention mechanism. In this paper we modify the decoder-only transformer, replacing self-attention with InAttention, which…

BenchmarkingDecoder

CoCA: Fusing Position Embedding with Collinear Constrained Attention in Transformers for Long Context Window Extending

2023-09-15 · Shiyi Zhu, Jing Ye, Wei Jiang, Siqiao Xue 외

Self-attention and position embedding are two key modules in transformer-based Large Language Models (LLMs). However, the potential relationship between them is far from well studied, especially for long context window e…

2kPosition

Unlocking Context Constraints of LLMs: Enhancing Context Efficiency of LLMs with Self-Information-Based Content Filtering

2023-04-24 · Yucheng Li

Large language models (LLMs) have received significant attention by achieving remarkable performance across various tasks. However, their fixed context length poses challenges when processing long documents or maintainin…

ArticlesQuestion Answering

Language Models can Self-Lengthen to Generate Long Texts

2024-10-31 · Shanghaoran Quan, Tianyi Tang, Bowen Yu, An Yang 외

Recent advancements in Large Language Models (LLMs) have significantly enhanced their ability to process long contexts, yet a notable gap remains in generating long, aligned outputs. This limitation stems from a training…

Text Generation