Salvato in:
Dettagli Bibliografici
Autori principali: Wang, Cunxiang, Ning, Ruoxi, Pan, Boqi, Wu, Tonghui, Guo, Qipeng, Deng, Cheng, Bao, Guangsheng, Hu, Xiangkun, Zhang, Zheng, Wang, Qian, Zhang, Yue
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:https://arxiv.org/abs/2403.12766
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866909589176320000
author Wang, Cunxiang
Ning, Ruoxi
Pan, Boqi
Wu, Tonghui
Guo, Qipeng
Deng, Cheng
Bao, Guangsheng
Hu, Xiangkun
Zhang, Zheng
Wang, Qian
Zhang, Yue
author_facet Wang, Cunxiang
Ning, Ruoxi
Pan, Boqi
Wu, Tonghui
Guo, Qipeng
Deng, Cheng
Bao, Guangsheng
Hu, Xiangkun
Zhang, Zheng
Wang, Qian
Zhang, Yue
contents Recent advancements in Large Language Models (LLMs) have pushed the boundaries of natural language processing, especially in long-context understanding. However, the evaluation of these models' long-context abilities remains a challenge due to the limitations of current benchmarks. To address this gap, we introduce NovelQA, a benchmark tailored for evaluating LLMs with complex, extended narratives. Constructed from English novels, NovelQA offers a unique blend of complexity, length, and narrative coherence, making it an ideal tool for assessing deep textual understanding in LLMs. This paper details the design and construction of NovelQA, focusing on its comprehensive manual annotation process and the variety of question types aimed at evaluating nuanced comprehension. Our evaluation of long-context LLMs on NovelQA reveals significant insights into their strengths and weaknesses. Notably, the models struggle with multi-hop reasoning, detail-oriented questions, and handling extremely long inputs, with average lengths exceeding 200,000 tokens. Results highlight the need for substantial advancements in LLMs to enhance their long-context comprehension and contribute effectively to computational literary analysis.
format Preprint
id arxiv_https___arxiv_org_abs_2403_12766
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle NovelQA: Benchmarking Question Answering on Documents Exceeding 200K Tokens
Wang, Cunxiang
Ning, Ruoxi
Pan, Boqi
Wu, Tonghui
Guo, Qipeng
Deng, Cheng
Bao, Guangsheng
Hu, Xiangkun
Zhang, Zheng
Wang, Qian
Zhang, Yue
Computation and Language
Recent advancements in Large Language Models (LLMs) have pushed the boundaries of natural language processing, especially in long-context understanding. However, the evaluation of these models' long-context abilities remains a challenge due to the limitations of current benchmarks. To address this gap, we introduce NovelQA, a benchmark tailored for evaluating LLMs with complex, extended narratives. Constructed from English novels, NovelQA offers a unique blend of complexity, length, and narrative coherence, making it an ideal tool for assessing deep textual understanding in LLMs. This paper details the design and construction of NovelQA, focusing on its comprehensive manual annotation process and the variety of question types aimed at evaluating nuanced comprehension. Our evaluation of long-context LLMs on NovelQA reveals significant insights into their strengths and weaknesses. Notably, the models struggle with multi-hop reasoning, detail-oriented questions, and handling extremely long inputs, with average lengths exceeding 200,000 tokens. Results highlight the need for substantial advancements in LLMs to enhance their long-context comprehension and contribute effectively to computational literary analysis.
title NovelQA: Benchmarking Question Answering on Documents Exceeding 200K Tokens
topic Computation and Language
url https://arxiv.org/abs/2403.12766