HELIOS: Harmonizing Early Fusion, Late Fusion, and LLM Reasoning for Multi-Granular Table-Text Retrieval
Sungho Park, Joohyung Yun, Jongwuk Lee, Wook-Shin Han
摘要
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 multihop 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. Love Me Like You Used To (song) Love Me Like You Used To is a song written by Paul Davis and Bobby Emmons, and recorded by American country music artist Johnny Cash.
问问这篇 Paper
智能体会读完全文。
Lune 把这篇 Paper 索引到了每一个公式,引用它的顶会 Paper 也一样。你提问,回答直接引用原文。
引用它的顶会 Paper3
- Table Question Answering in the Era of Large Language Models: A Comprehensive Survey of Tasks, Methods, and EvaluationWei Zhou, Bolei Ma, Annemarie Friedrich, Mohsen MesgarACL 2026 · 被引用 3 次
- SPARTA: Scalable and Principled Benchmark of Tree-Structured Multi-hop QA over Text and TablesSungho Park, Jueun Kim, Wook-Shin HanICLR 2026 · 被引用 2 次
- LILaC: Late Interacting in Layered Component Graph for Open-domain Multimodal Multihop RetrievalJoohyung Yun, Doyup Lee, Wook-Shin HanEMNLP 2025
它引用的顶会 Paper10
- Self-Consistency Improves Chain of Thought Reasoning in Language ModelsXuezhi Wang, Jason Wei, Dale Schuurmans, Quoc V. Le 等ICLR 2023 · 被引用 681 次
- Chain-of-Table: Evolving Tables in the Reasoning Chain for Table UnderstandingZilong Wang, Hao Zhang, Chun-Liang Li, Julian Martin Eisenschlos 等ICLR 2024 · 被引用 244 次
- Answering Complex Open-Domain Questions with Multi-Hop Dense RetrievalWenhan Xiong, Xiang Lorraine Li, Srini Iyer, Jingfei Du 等ICLR 2021 · 被引用 232 次
- MultiModalQA: complex question answering over text, tables and imagesAlon Talmor, Ori Yoran, Amnon Catav, Dan Lahav 等ICLR 2021 · 被引用 229 次
- Open Question Answering over Tables and TextWenhu Chen, Ming-Wei Chang, Eva Schlinger, William Yang Wang 等ICLR 2021 · 被引用 76 次
相关 Paper
- TableRAG: A Retrieval Augmented Generation Framework for Heterogeneous Document ReasoningXiaohan Yu, Pu Jian, Chong ChenEMNLP 2025 · 被引用 4 次
- Is Table Retrieval a Solved Problem? Exploring Join-Aware Multi-Table RetrievalPeter Baile Chen, Yi Zhang, Dan RothACL 2024 · 被引用 4 次
- REaR : Retrieve, Expand and Refine for Effective Multitable RetrievalRishita Agarwal, Himanshu Singhal, Peter Baile Chen, Manan Roy Choudhury 等ACL 2026 · 被引用 2 次
- Dual Reader-Parser on Hybrid Textual and Tabular Evidence for Open Domain Question AnsweringAlexander Hanbo Li, Patrick Ng, Peng Xu, Henghui Zhu 等ACL 2021
- RINK: Reader-Inherited Evidence Reranker for Table-and-Text Open Domain Question AnsweringEunhwan Park, Sung-Min Lee, Daeryong Seo, Seonhoon Kim 等AAAI 2023 · 被引用 4 次
