作者位次 #6/11ACL 2026Poster· Natural Language Processing
Rethinking Table Pruning in T able QA : From Sequential Revisions to Gold Trajectory-Supervised Parallel Search
Yu Guo · Shenghao Ye · Shuangwu Chen · Zijian Wen · Tao Zhang · Bai Qirui · Dong Jin · Yunpeng Hou · Huasen He · Jianyang · Xiaobin Tan
摘要
Table Question Answering (TableQA) benefits significantly from table pruning, which extracts compact sub-tables by eliminating redundant cells to streamline downstream reasoning. However, existing pruning methods typically rely on sequential revisions driven by unreliable critique signals, often...