REVIEW 6 cited by
Interpretable LLM-based Table Question Answering
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
Interpretability in Table Question Answering (Table QA) is critical, especially in high-stakes domains like finance and healthcare. While recent Table QA approaches based on Large Language Models (LLMs) achieve high accuracy, they often produce ambiguous explanations of how answers are derived. We propose Plan-of-SQLs (POS), a new Table QA method that makes the model's decision-making process interpretable. POS decomposes a question into a sequence of atomic steps, each directly translated into an executable SQL command on the table, thereby ensuring that every intermediate result is transparent. Through extensive experiments, we show that: First, POS generates the highest-quality explanations among compared methods, which markedly improves the users' ability to simulate and verify the model's decisions. Second, when evaluated on standard Table QA benchmarks (TabFact, WikiTQ, and FeTaQA), POS achieves QA accuracy that is competitive to existing methods, while also offering greater efficiency-requiring significantly fewer LLM calls and table database queries (up to 25x fewer)-and more robust performance on large-sized tables. Finally, we observe high agreement (up to 90.59% in forward simulation) between LLMs and human users when making decisions based on the same explanations, suggesting that LLMs could serve as an effective proxy for humans in evaluating Table QA explanations.
Forward citations
Cited by 6 Pith papers
-
AraTable: Benchmarking LLMs' Reasoning and Understanding of Arabic Tabular Data
AraTable is the first Arabic tabular QA benchmark; its experiments show LLMs are much weaker at reasoning over Arabic tables than at direct lookup.
-
Table Understanding and (Multimodal) LLMs: A Cross-Domain Case Study on Scientific vs. Non-Scientific Data
A new benchmark, TableEval, with 3017 tables in five formats, shows LLMs are robust to table representation but perform worse on scientific tables, with the caveat that the domain gap is confounded by task difficulty.
-
ExpliCIT-QA: Explainable Code-Based Image Table Question Answering
ExpliCIT-QA turns table-image question answering into a traceable sequence of table extraction, natural-language reasoning, code generation, execution, and explanation.
-
What to Keep and What to Drop: Adaptive Table Filtering Framework
ATF prunes table columns and rows with LLM scoring plus retrieval, cutting cells by about 70% and improving out-of-domain TableQA accuracy, while hurting in-domain QA and fact verification.
-
Beyond Natural Language Plans: Structure-Aware Planning for Query-Focused Table Summarization
SPaGe uses structured TaSoF plans and graph-parallel SQL execution to improve query-focused table summarization, outperforming most prior models on FeTaQA, QTSumm, and QFMTS datasets.
-
LLM Inference Enhanced by External Knowledge: A Survey
A survey of methods that enhance LLM inference by integrating external structured knowledge from tables and knowledge graphs.
Discussion (0). Sign in to comment.