paper-with-me

홈 › Papers

Lost-in-the-Middle in Long-Text Generation: Synthetic Dataset, Evaluation Framework, and Mitigation

2025-03-10 · Junhao Zhang, Richong Zhang, Fanshuang Kong, Ziyang Miao, Yanhan Ye, Yaowei Zheng

Existing long-text generation methods primarily concentrate on producing lengthy texts from short inputs, neglecting the long-input and long-output tasks. Such tasks have numerous practical applications while lacking available benchmarks. Moreover, as the input grows in length, existing methods inevitably encounter the "lost-in-the-middle" phenomenon. In this paper, we first introduce a Long Input and Output Benchmark (LongInOutBench), including a synthetic dataset and a comprehensive evaluation framework, addressing the challenge of the missing benchmark. We then develop the Retrieval-Augmented Long-Text Writer (RAL-Writer), which retrieves and restates important yet overlooked content, mitigating the "lost-in-the-middle" issue by constructing explicit prompts. We finally employ the proposed LongInOutBench to evaluate our RAL-Writer against comparable baselines, and the results demonstrate the effectiveness of our approach. Our code has been released at https://github.com/OnlyAR/RAL-Writer.

📄 PDF Abstract BibTeX arXiv:2503.06868

Code (1)

onlyar/ral-writer 공식 구현

Tasks

Text Generation

Similar Papers 제목 키워드 기반

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

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 …

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 외

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, re…

Passage RetrievalPositionQuestion AnsweringRetrieval

A MapReduce Approach to Effectively Utilize Long Context Information in Retrieval Augmented Language Models

2024-12-17 · Gongbo Zhang, Zihan Xu, Qiao Jin, Fangyi Chen 외

While holding great promise for improving and facilitating healthcare, large language models (LLMs) struggle to produce up-to-date responses on evolving topics due to outdated knowledge or hallucination. Retrieval-augmen…

HallucinationRAGRetrievalRetrieval-augmented Generation