Back to search

Virginia Tech

A Schema-aware Harness for Tabular Reasoning with Language Models

Abstract

dc:description.abstract

Language Models (LMs) are increasingly deployed as interactive data exploration assistants, enabling users to pose natural language questions over structured datasets without requiring query language expertise. Yet as these systems grow more capable, a critical gap emerges: while LMs can generate fluent, confident responses, their reasoning over structured tabular data remains brittle when schema-level signals (field semantics, aggregation rules, relational structure) are absent or inconsistently surfaced. This brittleness is especially consequential in multi-step reasoning pipelines, where a schema error at one stage can propagate silently into downstream outputs. We address this challenge in the context of Recursive Language Model (RLM) systems, where a root-model decomposes complex queries and delegates linguistically irreducible sub-tasks to sub-models. Using IPEDS, a large-scale higher education dataset that exceeds context window limits and requires programmatic data access, we investigate whether schema-aware harnesses improve reasoning reliability. Specifically, we introduce structured schema signals at the point of use and propagate them into sub-model calls, targeting failure modes where models default to assumption over verification. We systematically evaluate three levels of schema richness across three tiers of query complexity. Our results show that incorporating schema-aware signals significantly improves reasoning reliability, with schema propagation emerging as a stronger driver of performance than increased recursion depth. These findings highlight the importance of explicitly surfacing and maintaining structured context in LM-based reasoning systems over tabular data.

Degree

thesis:*
Name thesis:degree_name
Master of Science
Level thesis:degree_level
masters
Discipline thesis:degree_discipline
Computer Science & Applications
Department dc:contributor.department
Computer Science and#38; Applications
Grantor dc:publisher
Virginia Tech
Year dc:date.issued
2026

Author and committee

dc:creator, dc:contributor.*
Author dc:creator
  • Son, Eunice
Chair dc:contributor.committeechair
  • Ramakrishnan, Narendran
Committee members dc:contributor.committeemember
  • Garg, Vaibhav
  • Lu, Chang Tien

Subjects

dc:subject × 5

Rights

dc:rights
Statement dc:rights
  • In Copyright
Language dc:language.iso
en

Identifiers

dc:identifier.*
Dc Identifier Other
vt_gsexam:46698

Chain of custody

source
Harvested from
Virginia Tech
Base URL
vtechworks.lib.vt.edu/oai/request
Last updated
2026-11-18
Source record
OAI-PMH GetRecord
citation

Son, Eunice. A Schema-aware Harness for Tabular Reasoning with Language Models. masters thesis, Virginia Tech, 2026. https://hdl.handle.net/10919/143544