Table understanding capability of Large Language Models (LLMs) has been extensively studied through the task of question-answering (QA) over tables. Typically, only a small part of the whole table is relevant to derive the answer for a given question. The irrelevant parts act as noise and are distracting information, resulting in sub-optimal performance due to the vulnerability of LLMs to noise. To mitigate this, we propose CABINET (Content RelevAnce-Based NoIse ReductioN for TablE QuesTion-Answering) - a framework to enable LLMs to focus on relevant tabular data by suppressing extraneous information. CABINET comprises an Unsupervised Relevance Scorer (URS), trained differentially with the QA LLM, that weighs the table content based on its relevance to the input question before feeding it to the question-answering LLM (QA LLM). To further aid the relevance scorer, CABINET employs a weakly supervised module that generates a parsing statement describing the criteria of rows and columns relevant to the question and highlights the content of corresponding table cells. CABINET significantly outperforms various tabular LLM baselines, as well as GPT3-based in-context learning methods, is more robust to noise, maintains outperformance on tables of varying sizes, and establishes new SoTA performance on WikiTQ, FeTaQA, and WikiSQL datasets. We release our code and datasets at https://github.com/Sohanpatnaik106/CABINET_QA.

翻译：大型语言模型（LLMs）的表格理解能力已通过表格问答（QA）任务得到广泛研究。通常，整个表格中仅有小部分内容与推导给定问题的答案相关，而无关部分作为噪声与干扰信息存在，由于LLMs对噪声的敏感性，导致性能次优。为解决这一问题，我们提出CABINET（基于内容相关性的表格问答噪声抑制框架）——通过抑制冗余信息使LLMs聚焦于相关表格数据。该框架包含一个无监督相关性评分器（URS），该评分器与问答LLM联合差分训练，在将表格内容输入问答LLM前，基于其与输入问题的相关性进行加权。为进一步辅助相关性评分器，CABINET采用弱监督模块生成解析语句，描述与问题相关的行列筛选标准，并高亮对应表格单元格的内容。CABINET显著超越各类表格LLM基线方法及基于GPT3的上下文学习方法，对噪声具有更强鲁棒性，在不同规模表格上保持优异性能，并在WikiTQ、FeTaQA和WikiSQL数据集上创下最新最先进水平（SoTA）。我们已在https://github.com/Sohanpatnaik106/CABINET_QA 开源代码与数据集。