PAMI-GPT: knowledge-grounded LLMs for reliable pattern mining workflow generation

ExReg: Using Automated Example Generation to Guide Candidate Disambiguation and Validation in Regular Expression Construction

ExReg, a human-in-the-loop workflow that automatically generates discriminative examples using SMT-based constraint solving, highlights how automated example generation guided by formal methods and mutations can improve the reliability, efficiency, and trustworthiness of LLM-assisted regex pattern generation.

SymbolLKG: Towards Verifiable Logical Reasoning via Logical Knowledge Graph and Symbolic Solvers

A Neuro-Symbolic architecture that integrates a Logical Knowledge Graph (LKG) with dynamic solver routing, and introduces an ontology-based LKG that treats logical rules and constraints as first-class topological nodes, enabling explicit modeling of dependencies extracted from text.

Automatic Chain of Concepts: Conceptual Prompting for LLMs by Constructing Concept Trees

Overall, AutoCoC contributes a reproducible and scalable alternative to expert-authored concept hierarchies by automatically deriving domain-specific prompt structures from documentation, making concept-based prompting more practical for structured knowledge generation.

Optimizing sample selection for large language model-based entity matching using AssistEM

AssistEM, a framework for efficient LLM adaptation to EM via principled data selection, demonstrates that selective fine-tuning not only accelerates adaptation but also improves training efficiency (requiring fewer GPU hours), enabling open-source LLMs to rival–and in some cases outperform–closed-source models.

Deterministic Validation for Reliable LLM-Based Causal Knowledge Extraction

Large Language Models produce stochastic outputs that undermine reproducibility in knowledge extraction. We present a deterministic post-processing framework with 14 explicit validation predicates that transforms unreliable LLM output into consistent, validated causal triplets. Evaluated on four benchmarks spanning 2,1...

Prompt Template-Driven Large Model SQL Generation