GRAB improves multi-table QA performance by encoding relational data as graphs and bridging structural signals to frozen LLMs through latent tokens.
LLM M ap R educe: Simplified Long-Sequence Processing using Large Language Models
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Latent Bridges for Multi-Table Question Answering
GRAB improves multi-table QA performance by encoding relational data as graphs and bridging structural signals to frozen LLMs through latent tokens.