Year: 2026
Type: preprint
Abstract: We introduce GRAB, a constructor-encoder-bridge pipeline for table question answering. Our method lifts relational data into an heterogeneous graph, encodes it via message passing, and transfers the signals to an LLM through a small set of query-conditioned latent tokens. This provides the LLM with a compact, task-relevant structural representation together with the flattened text. Crucially, the LLM remains strictly frozen to preserve its general reasoning capabilities; we train only the lightweight graph encoder and latent bridge (91M parameters), allowing the entire pipeline to be trained efficiently. Our pipeline significantly improves performance on relational Question Answering, with the largest gains in demanding multi-table settings, offering an efficient, principled way to connect relational deep learning with LLMs.
Source: arXiv (Cornell University)
Language: English
Topic: Topic Modeling
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
Awards: G4510828401, 3IA Côte d'Azur 2030
OpenAlex ID: W7166653183
Cites:
Cited by:
Related to: