# Constrained Entity Selection under Partial Knowledge for LLM-Based Knowledge Graph QA

arXiv: https://arxiv.org/abs/2608.24824 · HTML: https://mlsanity.com/paper/2608.24824/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 4 of its 13 references that are in the map.
- First posted on arXiv 25 Aug 2026.

## Builds on (most cited first, 4 of 4)

- [Knowledge Graphs](https://mlsanity.com/paper/2003.02320/) (2020)
- [On the Planning Abilities of Large Language Models : A Critical Investigation](https://mlsanity.com/paper/2305.15771/) (2023)
- [Large Language Models Meet Knowledge Graphs for Question Answering: Synthesis and Opportunities](https://mlsanity.com/paper/2505.20099/) (2025)
- [Decoding on Graphs: Faithful and Sound Reasoning on Knowledge Graphs through Generation of Well-Formed Chains](https://mlsanity.com/paper/2410.18415/) (2024)

## Abstract (arXiv)

Large language models are increasingly used for knowledge graph question answering (KGQA), but can fail to correctly ground answers in the underlying graph. Current approaches to LLM-based KGQA either rely on full semantic parsing into executable queries such as SPARQL, which is brittle in practice due to complex schemas or incompleteness of real-world KGs, or on LLM-reasoning and answer generation over KGs, which can be more robust but lacks formal guarantees. In this work, we study a complementary setting in which candidate answers are generated by an LLM-based system and subsequently verified using lightweight symbolic constraints derived from the question. We introduce Constrained Entity Selection under Partial Knowledge (CES-PK), a problem formulation that focuses on eliminating invalid answers and providing symbolic support for valid ones without requiring construction of executable logical forms. To account for incomplete KGs, we employ a three-valued constraint semantics (satisfied, violated, unknown) that avoids incorrect rejections under open-world assumptions. To demonstrate the effects of our method, we instantiate this framework over the Hetionet biomedical knowledge graph and evaluate the impact of type, relation, and exclusion constraints. Experiments show that precision improves by filtering invalid candidates, while recall is preserved due to retaining candidates whose constraints are not explicitly violated. Satisfied constraints provide additional positive symbolic evidence to rank remaining candidates.