REVIEW 8 cited by
Open Question Answering over Tables and Text
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
Open Question Answering over Tables and Text
read the original abstract
In open question answering (QA), the answer to a question is produced by retrieving and then analyzing documents that might contain answers to the question. Most open QA systems have considered only retrieving information from unstructured text. Here we consider for the first time open QA over both tabular and textual data and present a new large-scale dataset Open Table-and-Text Question Answering (OTT-QA) to evaluate performance on this task. Most questions in OTT-QA require multi-hop inference across tabular data and unstructured text, and the evidence required to answer a question can be distributed in different ways over these two types of input, making evidence retrieval challenging -- our baseline model using an iterative retriever and BERT-based reader achieves an exact match score less than 10%. We then propose two novel techniques to address the challenge of retrieving and aggregating evidence for OTT-QA. The first technique is to use "early fusion" to group multiple highly relevant tabular and textual units into a fused block, which provides more context for the retriever to search for. The second technique is to use a cross-block reader to model the cross-dependency between multiple retrieved evidence with global-local sparse attention. Combining these two techniques improves the score significantly, to above 27%.
Forward citations
Cited by 8 Pith papers
-
TabEmbed: Benchmarking and Learning Generalist Embeddings for Tabular Understanding
TabEmbed is the first generalist embedding model for tabular data that unifies classification and retrieval in one space via contrastive learning and outperforms text embedding models on the new TabBench benchmark.
-
TableVision: A Large-Scale Benchmark for Spatially Grounded Reasoning over Complex Hierarchical Tables
TableVision benchmark shows explicit spatial grounding recovers MLLM reasoning on hierarchical tables, delivering 12.3% accuracy improvement through a decoupled perception-reasoning framework.
-
HETERQA: Benchmarking Record Retrieval over Multiple Heterogeneous Sources
HETERQA builds 857 answer-driven multi-source Yelp record-retrieval questions and finds hybrid and agentic methods still far from saturating Recall@10 and MRR@10.
-
LakeQA: An Exploratory QA Benchmark over a Million-Scale Data Lake
Introduces LakeQA, a new expert-annotated benchmark for search-centric multi-hop QA over a million-scale heterogeneous data lake, showing low performance (18.37% exact match) on frontier LLMs like GPT-5.2.
-
PIPER: Content-Based Table Search via profiling and LLM-Generated Pseudoqueries
PIPER retrieves and ranks tabular datasets by profiling their content and using LLM-generated queries for dense vector search, outperforming metadata baselines and TableQA methods in low-metadata settings.
-
Stepwise Reasoning Enhancement for LLMs via External Subgraph Generation
SGR framework generates query-relevant subgraphs from knowledge graphs via schema-guided retrieval to guide LLM stepwise reasoning, reporting accuracy gains on QA benchmarks.
-
SGR: A Stepwise Reasoning Framework for LLMs with External Subgraph Generation
SGR enhances LLM reasoning accuracy by generating external subgraphs from knowledge bases and guiding progressive inference over them, yielding consistent gains over baselines on benchmarks.
-
RaguTeam at SemEval-2026 Task 8: Meno and Friends in a Judge-Orchestrated LLM Ensemble for Faithful Multi-Turn Response Generation
A heterogeneous ensemble of seven LLMs plus a judge model won first place in SemEval-2026 Task 8 on faithful multi-turn response generation by selecting optimal candidates from diverse outputs.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.