cd /news/large-language-models/interpretable-column-annotation-with… · home topics large-language-models article
[ARTICLE · art-78060] src=arxiv.org ↗ pub= topic=large-language-models verified=true sentiment=↑ positive

Interpretable Column Annotation with LLM-Symbolized Decision Process Materialization

Researchers propose SymCA, an LLM-empowered interpretable column annotation framework that materializes column annotation as a global-to-local symbolic decision process, outperforming the strongest baselines by an average of 6.42% in Micro-F1 and 11.03% in Macro-F1. The framework consists of global skeleton induction using LLMs to generate hypernym-inspired tree-structured semantic skeletons and local substrate evolution that trains interpretable random forest classifiers.

read1 min views1 publishedJul 29, 2026

arXiv:2607.25228v1 Announce Type: new Abstract: Column annotation (CA), including column type annotation (CTA) and column property annotation (CPA), aims to identify the meanings of table columns and the semantic relationships among them. Recent CA methods usually use various neural models to learn column representations and directly map them to label categories, thereby (1) sacrificing model interpretability and adaptivity, and (2) overlooking rich label semantics and ultimately limiting accuracy. To address these limitations, we propose SymCA, an LLM-empowered interpretable CA framework that materializes column annotation as a global-to-local symbolic decision process. SymCA consists of two components: (1) global skeleton induction, which constructs a semantic skeleton over the label space, and (2) local substrate evolution, which evolves predictive substrates within the skeleton. Specifically, to exploit label semantics while preserving an interpretable decision process, the global skeleton induction module leverages LLMs to generate candidate hypernym-inspired tree-structured semantic skeletons and employs a Minimum Bayes Risk (MBR)-based consensus strategy to select a robust skeleton against generation variance. Since different internal nodes require different evidence to distinguish among their child nodes, the local substrate evolution module materializes each internal node as an executable and evolvable predictive substrate. Over multiple evolution rounds, each substrate trains an interpretable random forest classifier with the current operator set, leverages the LLM to propose node-specific operator modifications, and uses an exploration-exploitation strategy to prioritize promising substrates. Extensive experiments demonstrate that SymCA is accurate, robust, and interpretable, outperforming the strongest baselines by an average of 6.42% in Micro-F1 and 11.03% in Macro-F1.

── more in #large-language-models 4 stories · sorted by recency
── more on @symca 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
Live at https://your-agent.zahid.host
Get free account → Pricing
from €0/mo · no card required
LIVE [news/interpretable-column…] indexed:0 read:1min 2026-07-29 ·