Dynamic Chunking and Selection for Reading Comprehension of Ultra-Long Context in Large Language Models
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915319737483264 |
|---|---|
| author | Sheng, Boheng Yao, Jiacheng Zhang, Meicong He, Guoxiu |
| author_facet | Sheng, Boheng Yao, Jiacheng Zhang, Meicong He, Guoxiu |
| contents | Large language models (LLMs) often struggle to accurately read and comprehend extremely long texts. Current methods for improvement typically rely on splitting long contexts into fixed-length chunks. However, fixed truncation risks separating semantically relevant content, leading to ambiguity and compromising accurate understanding. To overcome this limitation, we propose a straightforward approach for dynamically separating and selecting chunks of long context, facilitating a more streamlined input for LLMs. In particular, we compute semantic similarities between adjacent sentences, using lower similarities to adaptively divide long contexts into variable-length chunks. We further train a question-aware classifier to select sensitive chunks that are critical for answering specific questions. Experimental results on both single-hop and multi-hop question-answering benchmarks show that the proposed approach consistently outperforms strong baselines. Notably, it maintains robustness across a wide range of input lengths, handling sequences of up to 256k tokens. Our datasets and code are available at the following link: https://github.com/ECNU-Text-Computing/DCS |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_00773 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Dynamic Chunking and Selection for Reading Comprehension of Ultra-Long Context in Large Language Models Sheng, Boheng Yao, Jiacheng Zhang, Meicong He, Guoxiu Computation and Language Large language models (LLMs) often struggle to accurately read and comprehend extremely long texts. Current methods for improvement typically rely on splitting long contexts into fixed-length chunks. However, fixed truncation risks separating semantically relevant content, leading to ambiguity and compromising accurate understanding. To overcome this limitation, we propose a straightforward approach for dynamically separating and selecting chunks of long context, facilitating a more streamlined input for LLMs. In particular, we compute semantic similarities between adjacent sentences, using lower similarities to adaptively divide long contexts into variable-length chunks. We further train a question-aware classifier to select sensitive chunks that are critical for answering specific questions. Experimental results on both single-hop and multi-hop question-answering benchmarks show that the proposed approach consistently outperforms strong baselines. Notably, it maintains robustness across a wide range of input lengths, handling sequences of up to 256k tokens. Our datasets and code are available at the following link: https://github.com/ECNU-Text-Computing/DCS |
| title | Dynamic Chunking and Selection for Reading Comprehension of Ultra-Long Context in Large Language Models |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2506.00773 |