paper-with-me

Papers

LenAtten: An Effective Length Controlling Unit For Text Summarization

2021-06-01 · Findings (ACL) 2021 8 · Zhongyi Yu, Zhenghao Wu, Hao Zheng, Zhe XuanYuan, Jefferson Fong, Weifeng Su

Fixed length summarization aims at generating summaries with a preset number of words or characters. Most recent researches incorporate length information with word embeddings as the input to the recurrent decoding unit, causing a compromise between length controllability and summary quality. In this work, we present an effective length controlling unit Length Attention (LenAtten) to break this trade-off. Experimental results show that LenAtten not only brings improvements in length controllability and ROGUE scores but also has great generalization ability. In the task of generating a summary with the target length, our model is 732 times better than the best-performing length controllable summarizer in length controllability on the CNN/Daily Mail dataset.

📄 PDF Abstract BibTeX arXiv:2106.00316

Code (1)

X-AISIG/LenAtten 공식 구현 pytorch

Tasks

Text SummarizationWord Embeddings

Similar Papers 제목 키워드 기반

Length Representations in Large Language Models

2025-07-27 · Sangjun Moon, Dasom Choi, Jingun Kwon, Hidetaka Kamigaito 외 arxiv

Large language models (LLMs) have shown remarkable capabilities across various tasks, that are learned from massive amounts of text-based data. Although LLMs can control output sequence length, particularly in instructio…

Controlling Summarization Length Through EOS Token Weighting

2025-06-05 · Zeno Belligoli, Emmanouil Stergiadis, Eran Fainman, Ilya Gusev

Controlling the length of generated text can be crucial in various text-generation tasks, including summarization. Existing methods often require complex model alterations, limiting compatibility with pre-trained models.…

DecoderText Generation

Controlling Output Length in Neural Encoder-Decoders

2016-09-30 · EMNLP 2016 11 · Yuta Kikuchi, Graham Neubig, Ryohei Sasano, Hiroya Takamura 외

Neural encoder-decoder models have shown great success in many sequence generation tasks. However, previous work has not investigated situations in which we would like to control the length of encoder-decoder outputs. Th…

DecoderText Summarization

We Can't Understand AI Using our Existing Vocabulary

2025-02-11 · John Hewitt, Robert Geirhos, Been Kim

This position paper argues that, in order to understand AI, we cannot rely on our existing vocabulary of human words. Instead, we should strive to develop neologisms: new words that represent precise human concepts that …

Diversity

Can LLMs Track Their Output Length? A Dynamic Feedback Mechanism for Precise Length Regulation

2026-01-05 · Meiman Xiao, Ante Wang, Qingguo Hu, Zhongjian Miao 외 arxiv

Precisely controlling the length of generated text is a common requirement in real-world applications. However, despite significant advancements in following human instructions, Large Language Models (LLMs) still struggl…