CORG: Generating Answers from Complex, Interrelated Contexts
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866910923897176064 |
|---|---|
| author | Lee, Hyunji Dernoncourt, Franck Bui, Trung Yoon, Seunghyun |
| author_facet | Lee, Hyunji Dernoncourt, Franck Bui, Trung Yoon, Seunghyun |
| contents | In a real-world corpus, knowledge frequently recurs across documents but often contains inconsistencies due to ambiguous naming, outdated information, or errors, leading to complex interrelationships between contexts. Previous research has shown that language models struggle with these complexities, typically focusing on single factors in isolation. We classify these relationships into four types: distracting, ambiguous, counterfactual, and duplicated. Our analysis reveals that no single approach effectively addresses all these interrelationships simultaneously. Therefore, we introduce Context Organizer (CORG), a framework that organizes multiple contexts into independently processed groups. This design allows the model to efficiently find all relevant answers while ensuring disambiguation. CORG consists of three key components: a graph constructor, a reranker, and an aggregator. Our results demonstrate that CORG balances performance and efficiency effectively, outperforming existing grouping methods and achieving comparable results to more computationally intensive, single-context approaches. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_00023 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | CORG: Generating Answers from Complex, Interrelated Contexts Lee, Hyunji Dernoncourt, Franck Bui, Trung Yoon, Seunghyun Computation and Language Artificial Intelligence In a real-world corpus, knowledge frequently recurs across documents but often contains inconsistencies due to ambiguous naming, outdated information, or errors, leading to complex interrelationships between contexts. Previous research has shown that language models struggle with these complexities, typically focusing on single factors in isolation. We classify these relationships into four types: distracting, ambiguous, counterfactual, and duplicated. Our analysis reveals that no single approach effectively addresses all these interrelationships simultaneously. Therefore, we introduce Context Organizer (CORG), a framework that organizes multiple contexts into independently processed groups. This design allows the model to efficiently find all relevant answers while ensuring disambiguation. CORG consists of three key components: a graph constructor, a reranker, and an aggregator. Our results demonstrate that CORG balances performance and efficiency effectively, outperforming existing grouping methods and achieving comparable results to more computationally intensive, single-context approaches. |
| title | CORG: Generating Answers from Complex, Interrelated Contexts |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2505.00023 |