Papers with cross-referencing
FourCorners: Grounded Thai Legal Research over a Temporal Knowledge Graph (2026.acl-demo)
Copied to clipboard
Pawitsapak Akarajaradwong, Thitiwat Nopparatbundit, Treephop Saeteng, Kasidit Phoncharoen, Sarana Nutanong, Chompakorn Chaksangchaichot
| Challenge: | a new platform addresses five pain points in legal research in Thailand . the tools available to legal practitioners are fragmented and lack a unified tool for cross-referencing, version tracking or structural navigation. |
| Approach: | They propose a platform that addresses five practitioner pain points through three modules built on a temporal legal knowledge graph covering 552K nodes and 6.3M edges. |
| Outcome: | The proposed platform addresses five practitioner pain points through three modules built on a temporal legal knowledge graph covering 552K nodes and 6.3M edges. |
Cross-referencing Using Fine-grained Topic Modeling (N19-1)
Copied to clipboard
| Challenge: | Cross-referencing is a useful study aid for facilitating comprehension of a text, but it requires extensive thematic knowledge and a focused search through the corpus to find such useful connections. |
| Approach: | They propose a system for producing candidate cross-references which can be easily verified by human annotators. |
| Outcome: | a new system can produce cross-references that can be easily verified by human annotators . the system uses fine-grained topic modeling to identify verse pairs which are topically related . |
NitiBench: Benchmarking LLM Frameworks on Thai Legal Question Answering Capabilities (2025.emnlp-main)
Copied to clipboard
Pawitsapak Akarajaradwong, Pirat Pothavorn, Chompakorn Chaksangchaichot, Panuthep Tasawong, Thitiwat Nopparatbundit, Keerakiat Pratai, Sarana Nutanong
| Challenge: | Large language models (LLMs) show promise in legal question answering (QA), yet Thai legal QA systems face challenges due to limited data and complex legal structures. |
| Approach: | They propose a benchmark which uses Thai financial laws and tax rulings to evaluate Thai legal QA systems. |
| Outcome: | The proposed benchmark compared retrieval-augmented generation and long-context LLM approaches across three key dimensions and found that they improve over naive methods. |