# Complex Reasoning over Logical Queries on Commonsense Knowledge Graphs

arXiv: https://arxiv.org/abs/2403.07398 · HTML: https://mlsanity.com/paper/2403.07398/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning.
- Builds on 10 of its 63 references that are in the map.
- First posted on arXiv 12 Mar 2024.

## Placed in

- LLM reasoning / [Reasoning benchmarks and evaluation](https://mlsanity.com/lr/reasoning-benchmarks-and-evaluation/)

## Builds on (most cited first, 10 of 10)

- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Scaling Instruction-Finetuned Language Models](https://mlsanity.com/paper/2210.11416/) (2022)
- [MEDITRON-70B: Scaling Medical Pretraining for Large Language Models](https://mlsanity.com/paper/2311.16079/) (2023)
- [Leveraging Large Language Models for Multiple Choice Question Answering](https://mlsanity.com/paper/2210.12353/) (2022)
- [KG-Agent: An Efficient Autonomous Agent Framework for Complex Reasoning over Knowledge Graph](https://mlsanity.com/paper/2402.11163/) (2024)
- [UnifiedQA-v2: Stronger Generalization via Broader Cross-Format Training](https://mlsanity.com/paper/2202.12359/) (2022)
- [Complex Query Answering on Eventuality Knowledge Graph with Implicit Logical Constraints](https://mlsanity.com/paper/2305.19068/) (2023)
- [Knowledge Crosswords: Geometric Knowledge Reasoning with Large Language Models](https://mlsanity.com/paper/2310.01290/) (2023)
- [Multi-hop Commonsense Knowledge Injection Framework for Zero-Shot Commonsense Question Answering](https://mlsanity.com/paper/2305.05936/) (2023)
- [VCD: A Dataset for Visual Commonsense Discovery in Images](https://mlsanity.com/paper/2402.17213/) (2024)

## Built on by (most cited first, 8 of 8)

- [Heterogeneous Swarms: Jointly Optimizing Model Roles and Weights for Multi-LLM Systems](https://mlsanity.com/paper/2502.04510/) (2025)
- [Varying Shades of Wrong: Aligning LLMs with Wrong Answers Only](https://mlsanity.com/paper/2410.11055/) (2024)
- [SPARTA ALIGNMENT: Collectively Aligning Multiple Language Models through Combat](https://mlsanity.com/paper/2506.04721/) (2025)
- [Enhancing Transformers for Generalizable First-Order Logical Entailment](https://mlsanity.com/paper/2501.00759/) (2025)
- [On the Role of Entity and Event Level Conceptualization in Generalizable Reasoning: A Survey of Tasks, Methods, Applications, and Future Directions](https://mlsanity.com/paper/2406.10885/) (2024)
- [BioPIE: A Biomedical Protocol Information Extraction Dataset for Experiment Understanding](https://mlsanity.com/paper/2601.04524/) (2026)
- [LOGICAL-COMMONSENSEQA: A Benchmark for Logical Commonsense Reasoning](https://mlsanity.com/paper/2601.16504/) (2026)
- [NEST: Narrative Event Structures in Time for Long Video Understanding](https://mlsanity.com/paper/2606.19706/) (2026)

## Abstract (arXiv)

Event commonsense reasoning requires the ability to reason about the relationship between events, as well as infer implicit context underlying that relationship. However, data scarcity makes it challenging for language models to learn to generate commonsense inferences for contexts and questions involving interactions between complex events. To address this demand, we present COM2 (COMplex COMmonsense), a new dataset created by sampling multi-hop logical queries (e.g., the joint effect or cause of both event A and B, or the effect of the effect of event C) from an existing commonsense knowledge graph (CSKG), and verbalizing them using handcrafted rules and large language models into multiple-choice and text generation questions. Our experiments show that language models trained on COM2 exhibit significant improvements in complex reasoning ability, resulting in enhanced zero-shot performance in both in-domain and out-of-domain tasks for question answering and generative commonsense reasoning, without expensive human annotations. Code and data are available at https://github.com/tqfang/complex-commonsense-reasoning.