paper-with-me

홈 › Papers

Never Lost in the Middle: Mastering Long-Context Question Answering with Position-Agnostic Decompositional Training

2023-11-15 · Junqing He, Kunhao Pan, Xiaoqun Dong, Zhuoyang Song, Yibo Liu, Qianguo Sun, Yuxin Liang, Hao Wang, Enming Zhang, Jiaxing Zhang

While large language models (LLMs) are equipped with longer text input capabilities than before, they are struggling to seek correct information in long contexts. The "lost in the middle" problem challenges most LLMs, referring to the dramatic decline in accuracy when correct information is located in the middle. To overcome this crucial issue, this paper proposes to enhance the information searching and reflection ability of LLMs in long contexts via specially designed tasks called Attention Strengthening Multi-doc QA (ASM QA). Following these tasks, our model excels in focusing more precisely on the desired information. Experimental results show substantial improvement in Multi-doc QA and other benchmarks, superior to state-of-the-art models by 13.7% absolute gain in shuffled settings, by 21.5% in passage retrieval task. We release our model, Ziya-Reader to promote related research in the community.

📄 PDF Abstract BibTeX arXiv:2311.09198

Code (2)

hejunqing/never-lost-in-the-middle 공식 구현 pytorch
qihoo360/360zhinao pytorch

Tasks

Passage RetrievalPositionQuestion AnsweringRetrieval

Similar Papers 제목 키워드 기반

An Efficient Recipe for Long Context Extension via Middle-Focused Positional Encoding

2024-06-11 · Tong Wu, Yanpeng Zhao, Zilong Zheng

Recently, many methods have been developed to extend the context length of pre-trained large language models (LLMs), but they often require fine-tuning at the target length ($\gg4K$) and struggle to effectively utilize i…

4k

Retrieval Quality at Context Limit

2025-11-08 · Max McKinnon arxiv

The ability of large language models (LLMs) to recall and retrieve information from long contexts is critical for many real-world applications. Prior work (Liu et al., 2023) reported that LLMs suffer significant drops in…

Layer-Specific Scaling of Positional Encodings for Superior Long-Context Modeling

2025-03-06 · Zhenghua Wang, Yiran Ding, Changze Lv, Zhibo Xu 외

Although large language models (LLMs) have achieved significant progress in handling long-context inputs, they still suffer from the ``lost-in-the-middle'' problem, where crucial information in the middle of the context …

Found in the Middle: Calibrating Positional Attention Bias Improves Long Context Utilization

2024-06-23 · Cheng-Yu Hsieh, Yung-Sung Chuang, Chun-Liang Li, Zifeng Wang 외

Large language models (LLMs), even when specifically trained to process long input contexts, struggle to capture relevant information located in the middle of their input. This phenomenon has been known as the lost-in-th…

RAGRetrieval-augmented Generation

GUI-PRA: Process Reward Agent for GUI Tasks

2025-09-27 · Tao Xiong, Xavier Hu, Yurun Chen, Yuhang Liu 외 arxiv

Graphical User Interface (GUI) Agents powered by Multimodal Large Language Models (MLLMs) show significant potential for automating tasks. However, they often struggle with long-horizon tasks, leading to frequent failure…