Parameter-Efficient Retriever-Reader for Trustworthy Table-Text Question Answering Toward Agentic Edge Intelligence
- Jian Lyu,
- Jingfeng Xue,
- ,
- Junbao Chen,
- Zeyang Liu,
- Tianqing Zhu
- Beijing Institute of Technology,
- ,
- City University of Macau
Research Output:
Contribution to journal
Article
Research
Peer-reviewOpen access
Abstract
<p>Resource-constrained edge intelligence increasingly requires lightweight and trustworthy access to heterogeneous knowledge, where decisions often involve reasoning over structured tables and associated text. In this paper, trustworthiness is operationalized as robustness under weak supervision, imperfect evidence selection, and noisy hybrid contexts. Table-text Hybrid Question Answering (HQA) is representative of this need, yet existing methods often face a trade-off between specialization-driven systems with high engineering cost and generalization-driven LLM pipelines that are flexible but may lag behind the strongest specialized systems. We propose RRS, a parameter-efficient retriever-reader framework that formulates HQA as two dialog-style tasks, row retrieval and answer generation, handled by a shared pretrained language model with task-specific low-rank adapters. RRS combines modular decomposition, noise-robust training against weak-supervision errors, and a natural-language interface without specialized feature engineering. Sharing over 99.8% of backbone parameters, it introduces no more than 0.2% task-specific trainable parameters. With modest-scale public models of 7B and 4B parameters, RRS achieves 71.9%/79.6% and 71.6%/79.2% EM/F1 on the HybridQA official blind test, surpassing the previous best result of 67.9%/75.5%. These results demonstrate a lightweight and noise-robust table-text reasoning approach that is well suited to resource-constrained deployment and provides a useful building block for agentic edge intelligence.</p>
Research Output Information
Output type
Research Output:
Contribution to journal
Article
Research
Peer-reviewOriginal language
EnglishPages from-to (Number of pages)
Pages 11301-11318 (18 pages)Journal (Volume, Issue Number)
IEEE Transactions on Network Science and Engineering (Volume 13)Publication milestones
- Published - 2026
Publication status
Published - 2026
Publication IDs
- Scopus: 105048598862
Documents and links
Publication metrics
PlumX, opens in new tab
Captures
4
