Bridging Context Gaps: Leveraging Coreference Resolution for Long Contextual Understanding
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866913992514994176 |
|---|---|
| author | Liu, Yanming Peng, Xinyue Cao, Jiannan Shen, Yanxin Du, Tianyu Cheng, Sheng Wang, Xun Yin, Jianwei Zhang, Xuhong |
| author_facet | Liu, Yanming Peng, Xinyue Cao, Jiannan Shen, Yanxin Du, Tianyu Cheng, Sheng Wang, Xun Yin, Jianwei Zhang, Xuhong |
| contents | Large language models (LLMs) have shown remarkable capabilities in natural language processing; however, they still face difficulties when tasked with understanding lengthy contexts and executing effective question answering. These challenges often arise due to the complexity and ambiguity present in longer texts. To enhance the performance of LLMs in such scenarios, we introduce the Long Question Coreference Adaptation (LQCA) method. This innovative framework focuses on coreference resolution tailored to long contexts, allowing the model to identify and manage references effectively. The LQCA method encompasses four key steps: resolving coreferences within sub-documents, computing the distances between mentions, defining a representative mention for coreference, and answering questions through mention replacement. By processing information systematically, the framework provides easier-to-handle partitions for LLMs, promoting better understanding. Experimental evaluations on a range of LLMs and datasets have yielded positive results, with a notable improvements on OpenAI-o1-mini and GPT-4o models, highlighting the effectiveness of leveraging coreference resolution to bridge context gaps in question answering. Our code is public at https://github.com/OceannTwT/LQCA. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_01671 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Bridging Context Gaps: Leveraging Coreference Resolution for Long Contextual Understanding Liu, Yanming Peng, Xinyue Cao, Jiannan Shen, Yanxin Du, Tianyu Cheng, Sheng Wang, Xun Yin, Jianwei Zhang, Xuhong Computation and Language Artificial Intelligence Large language models (LLMs) have shown remarkable capabilities in natural language processing; however, they still face difficulties when tasked with understanding lengthy contexts and executing effective question answering. These challenges often arise due to the complexity and ambiguity present in longer texts. To enhance the performance of LLMs in such scenarios, we introduce the Long Question Coreference Adaptation (LQCA) method. This innovative framework focuses on coreference resolution tailored to long contexts, allowing the model to identify and manage references effectively. The LQCA method encompasses four key steps: resolving coreferences within sub-documents, computing the distances between mentions, defining a representative mention for coreference, and answering questions through mention replacement. By processing information systematically, the framework provides easier-to-handle partitions for LLMs, promoting better understanding. Experimental evaluations on a range of LLMs and datasets have yielded positive results, with a notable improvements on OpenAI-o1-mini and GPT-4o models, highlighting the effectiveness of leveraging coreference resolution to bridge context gaps in question answering. Our code is public at https://github.com/OceannTwT/LQCA. |
| title | Bridging Context Gaps: Leveraging Coreference Resolution for Long Contextual Understanding |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2410.01671 |