HELIOS: Harmonizing Early Fusion, Late Fusion, and LLM Reasoning for Multi-Granular Table-Text Retrieval

TL;DR

HELIOS is proposed, which combines the strengths of both early and late fusion in table-text retrieval, and outperforms state-of-the-art models with a significant improvement up to 42.6\% and 39.9\% in recall and nDCG, respectively, on the OTT-QA benchmark.

Abstract

Table-text retrieval aims to retrieve relevant tables and text to support open-domain question answering. Existing studies use either early or late fusion, but face limitations. Early fusion pre-aligns a table row with its associated passages, forming "stars," which often include irrelevant contexts and miss query-dependent relationships. Late fusion retrieves individual nodes, dynamically aligning them, but it risks missing relevant contexts. Both approaches also struggle with advanced reasoning tasks, such as column-wise aggregation and multi-hop reasoning. To address these issues, we propose HELIOS, which combines the strengths of both approaches. First, the edge-based bipartite subgraph retrieval identifies finer-grained edges between table segments and passages, effectively avoiding the inclusion of irrelevant contexts. Then, the query-relevant node expansion identifies the most promising nodes, dynamically retrieving relevant edges to grow the bipartite subgraph, minimizing the risk of missing important contexts. Lastly, the star-based LLM refinement performs logical inference at the star graph level rather than the bipartite subgraph, supporting advanced reasoning tasks. Experimental results show that HELIOS outperforms state-of-the-art models with a significant improvement up to 42.6\% and 39.9\% in recall and nDCG, respectively, on the OTT-QA benchmark.

Figures (8)

• Figure 2: Overview of HELIOS: The initial graph $G_{init}$ is early-fused to generate a graph $G_d$. Each node and edge of $G_d$ are embedded. (1) The edges of $G_d$ are retrieved using the query $q$, then integrated into a candidate bipartite subgraph $G_c$. (2) The most query-relevant nodes in $G_c$ are identified as seed nodes. New nodes from $G_{init}$ are expanded from the seed nodes, forming an expanded graph $G_l$. (3) LLM performs aggregation over restored tables to identify new relevant table rows, and then eliminates irrelevant passages.
• Figure 3: The overall procedure of query-relevant node expansion. The beam width $b$ is set as 2 in this example. The purple-colored nodes indicate the selected seed nodes.
• Figure 4: End-to-end QA accuracy comparison across different readers for dev set of OTT-QA
• Figure 5: High-level schematic workflow of HELIOS.
• Figure 6: The overall process of star-based LLM refinement for queries classified as aggregation queries. Table segment nodes of the same color (black, orange) indicate segments that belong to the same original table.