Textual graph question answering (GraphQA) and graph-based retrieval-augmented generation (GraphRAG) have gained increasing attention as a way to ground large language models (LLMs) on structured knowledge.
Two Key Gaps
Despite extensive efforts, existing methods still face two key gaps.
- The first is an architectural gap: existing methods typically fine-tune an LLM-based generator, but do not also make the retriever itself a learnable LLM for graph evidence selection within one end-to-end retrieve-then-generate pipeline.
- The second is a retrieval-supervision gap: existing retrievers rarely use gold answer signals to supervise evidence selection.
As a result, they may fail to recall evidence nodes required for reasoning, resulting in insufficient coverage of the gold answer set; meanwhile, naive attempts to boost recall often introduce excessive irrelevant information that compromises compactness and overwhelms the LLM.
TaLenT: Proposed Framework
To address these gaps, we propose TaLenT, an LLM-based end-to-end retriever-generator framework for textual GraphQA.
To bridge the architectural gap, TaLenT pairs a learnable LLM-based retriever for evidence selection with a fine-tuned LLM-based generator within one unified retrieve-then-generate pipeline.
To bridge the retrieval-supervision gap, we leverage gold answer signals as retriever supervision.
Supervision via Node Stratification and Weighted Pseudo-Label Loss
Specifically, we stratify graph nodes into gold answers, answer-related nodes, and irrelevant noise.
We then adopt a weighted pseudo-label loss to prioritize gold answers and preserve answer-related nodes for coverage, while discarding irrelevant noise for compactness.
Experimental Results
Experimental results across three GraphQA datasets demonstrate that TaLenT consistently improves downstream performance.