H-STAR: LLM-driven Hybrid SQL-Text Adaptive Reasoning on Tables
- URL: http://arxiv.org/abs/2407.05952v1
- Date: Sat, 29 Jun 2024 21:24:19 GMT
- Title: H-STAR: LLM-driven Hybrid SQL-Text Adaptive Reasoning on Tables
- Authors: Nikhil Abhyankar, Vivek Gupta, Dan Roth, Chandan K. Reddy,
- Abstract summary: Tabular reasoning involves interpreting unstructured queries against structured tables.
Textual reasoning excels in semantic interpretation, but falls short in mathematical reasoning.
We introduce a novel algorithm H-STAR, comprising table extraction and adaptive reasoning.
- Score: 56.73919743039263
- License: http://creativecommons.org/licenses/by-sa/4.0/
- Abstract: Tabular reasoning involves interpreting unstructured queries against structured tables, requiring a synthesis of textual understanding and symbolic reasoning. Existing methods rely on either of the approaches and are constrained by their respective limitations. Textual reasoning excels in semantic interpretation unlike symbolic reasoning (SQL logic), but falls short in mathematical reasoning where SQL excels. In this paper, we introduce a novel algorithm H-STAR, comprising table extraction and adaptive reasoning, integrating both symbolic and semantic (text-based) approaches. To enhance evidence extraction, H-STAR employs a multi-view approach, incorporating step-by-step row and column retrieval. It also adapts reasoning strategies based on question types, utilizing symbolic reasoning for quantitative and logical tasks, and semantic reasoning for direct lookup and complex lexical queries. Our extensive experiments demonstrate that H-STAR significantly outperforms state-of-the-art methods across three tabular question-answering (QA) and fact-verification datasets, underscoring its effectiveness and efficiency.
Related papers
- Chain-of-Table: Evolving Tables in the Reasoning Chain for Table
Understanding [79.9461269253121]
We propose the Chain-of-Table framework, where tabular data is explicitly used in the reasoning chain as a proxy for intermediate thoughts.
Chain-of-Table achieves new state-of-the-art performance on WikiTQ, FeTaQA, and TabFact benchmarks.
arXiv Detail & Related papers (2024-01-09T07:46:26Z) - Rethinking Tabular Data Understanding with Large Language Models [39.38132513255292]
This study investigates the robustness of Large Language Models (LLMs) to structural perturbations in tables.
We show that structural variance of tables presenting the same content reveals a notable performance decline, particularly in symbolic reasoning tasks.
We conclude that the aggregation of textual and symbolic reasoning pathways, bolstered by a mix self-consistency mechanism, resulted in achieving SOTA performance, with an accuracy of 73.6% on WIKITABLEQUESTIONS.
arXiv Detail & Related papers (2023-12-27T19:58:52Z) - Modeling Hierarchical Reasoning Chains by Linking Discourse Units and
Key Phrases for Reading Comprehension [80.99865844249106]
We propose a holistic graph network (HGN) which deals with context at both discourse level and word level, as the basis for logical reasoning.
Specifically, node-level and type-level relations, which can be interpreted as bridges in the reasoning process, are modeled by a hierarchical interaction mechanism.
arXiv Detail & Related papers (2023-06-21T07:34:27Z) - Query Structure Modeling for Inductive Logical Reasoning Over Knowledge
Graphs [67.043747188954]
We propose a structure-modeled textual encoding framework for inductive logical reasoning over KGs.
It encodes linearized query structures and entities using pre-trained language models to find answers.
We conduct experiments on two inductive logical reasoning datasets and three transductive datasets.
arXiv Detail & Related papers (2023-05-23T01:25:29Z) - Large Language Models are Versatile Decomposers: Decompose Evidence and
Questions for Table-based Reasoning [45.013230888670435]
We exploit large language models (LLMs) as decomposers for effective table-based reasoning.
We decompose huge evidence (a huge table) into sub-evidence (a small table) to mitigate the interference of useless information.
We propose a "parsing-execution-filling" strategy to alleviate the dilemma of the chain of thought.
arXiv Detail & Related papers (2023-01-31T17:51:45Z) - Suggesting Relevant Questions for a Query Using Statistical Natural
Language Processing Technique [0.0]
Suggesting similar questions for a user query has many applications ranging from reducing search time of users on e-commerce websites, training of employees in companies to holistic learning for students.
The use of Natural Language Processing techniques for suggesting similar questions is prevalent over the existing architecture.
arXiv Detail & Related papers (2022-04-26T04:30:16Z) - Reasoning over Hybrid Chain for Table-and-Text Open Domain QA [69.8436986668218]
We propose a ChAin-centric Reasoning and Pre-training framework (CARP)
CARP utilizes hybrid chain to model the explicit intermediate reasoning process across table and text for question answering.
We also propose a novel chain-centric pre-training method, to enhance the pre-trained model in identifying the cross-modality reasoning process.
arXiv Detail & Related papers (2022-01-15T16:11:55Z) - Logic-Driven Context Extension and Data Augmentation for Logical
Reasoning of Text [65.24325614642223]
We propose to understand logical symbols and expressions in the text to arrive at the answer.
Based on such logical information, we put forward a context extension framework and a data augmentation algorithm.
Our method achieves the state-of-the-art performance, and both logic-driven context extension framework and data augmentation algorithm can help improve the accuracy.
arXiv Detail & Related papers (2021-05-08T10:09:36Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.