Similarity-weighted Construction of Contextualized Commonsense Knowledge Graphs for Knowledge-intense Argumentation Tasks

Challenge:	Arguments often do not make explicit how a conclusion follows from its premises . we present a method for constructing Contextualized Commonsense Knowledge Graphs (CCKGs) that is efficient and high-quality .
Approach:	They propose an unsupervised method for constructing Contextualized Commonsense Knowledge Graphs (CCKGs) they use triplet similarities to extract contextually relevant knowledge paths .
Outcome:	The proposed method outperforms baselines and a GPT-3 based system in a knowledge-intense argumentation task.

Similar Papers

Overview

Challenge

Approach

Outcome

ComFact: A Benchmark for Linking Contextual Commonsense Knowledge (2022.findings-emnlp)

Copied to clipboard

Silin Gao, Jena D. Hwang, Saya Kanno, Hiromi Wakaki, Yuki Mitsufuji, Antoine Bosselut

Natural Language Interfaces

Challenge:	Existing methods to retrieve facts from commonsense knowledge graphs are imprecise, requiring heuristics that ignore contexts and ambiguity . a novel benchmark, ComFact, contains 293k in-context relevance annotations for commonsensense triplets .
Approach:	They propose a task of commonsense fact linking where models are given contexts and trained to identify situationally-relevant commonsensical knowledge from KGs.
Outcome:	The proposed benchmark shows that heuristic fact linking approaches are imprecise . however, the models still significantly underperform humans in the commonsense augmentation task .

Fusing Context Into Knowledge Graph for Commonsense Question Answering (2021.findings-acl)

Copied to clipboard

Yichong Xu, Chenguang Zhu, Ruochen Xu, Yang Liu, Michael Zeng, Xuedong Huang

Semantic Text Processing

Challenge:	Existing methods to combine language modeling and knowledge graphs (KG) lack the context to provide a more precise understanding of the concepts.
Approach:	They propose to use external entity descriptions to provide contextual information for commonsense question answering models.
Outcome:	The proposed model achieves state-of-the-art among non-generative models in OpenBookQA and is the first of its kind in the field.

Structured Self-Supervised Pretraining for Commonsense Knowledge Graph Completion (2021.tacl-1)

Copied to clipboard

Jiayuan Huang, Yangkai Du, Shuting Tao, Kun Xu, Pengtao Xie

Semantic Text Processing

Challenge:	Existing approaches focus on generating concepts that have direct and obvious relationships with existing concepts and lack an ability to generate unobvious concepts.
Approach:	They propose a general graph-to-paths pretraining framework that leverages high-order structures in CKGs to capture high-level relationships between concepts.
Outcome:	The proposed framework can capture high-order relationships between concepts in four special cases: long path, path-to-path, router, and graph-node-path.

Connecting the Dots: A Knowledgeable Path Generator for Commonsense Question Answering (2020.findings-emnlp)

Copied to clipboard

Peifeng Wang, Nanyun Peng, Filip Ilievski, Pedro Szekely, Xiang Ren

Reasoning

Challenge:	Existing QA systems do not have commonsense knowledge or cannot reason with it.
Approach:	They propose to augment a general commonsense QA framework with a knowledgeable path generator by extrapolating existing paths from a KG with 'state-of-the-art' language model.
Outcome:	The generated paths are interpretable, novel, and relevant to the task.

On the Consistency of Commonsense in Large Language Models (2025.findings-acl)

Copied to clipboard

Guozheng Li, Peng Wang, Wenjun Ke, Zijie Xu, Jiajun Liu, Ziyu Shang

Language Models

Challenge:	Existing evaluations of commonsense for large language models focus on downstream knowledge tasks, failing to probe whether LLMs truly understand and utilize knowledge or merely memorize it.
Approach:	They propose to automatically construct a large benchmark named CoCo which measures LLMs’ knowledge memorization, comprehension, and application and examines the consistency between these tasks.
Outcome:	The proposed benchmark systematically assesses LLMs’ knowledge memorization, comprehension, and application and examines the consistency between these tasks.

KE-GCL: Knowledge Enhanced Graph Contrastive Learning for Commonsense Question Answering (2022.findings-emnlp)

Copied to clipboard

Lihui Zhang, Ruifan Li

Semantic Text Processing

Challenge:	Existing models for commonsense question answering lack effective representations of knowledge graphs.
Approach:	They propose a Knowledge Enhanced Graph Contrastive Learning model by incorporating contextual descriptions into QA pairs and adopting a graph contrastive learning scheme.
Outcome:	The proposed model outperforms existing methods consistently on two benchmark datasets.

ExplaGraphs: An Explanation Graph Generation Task for Structured Commonsense Reasoning (2021.emnlp-main)

Copied to clipboard

Swarnadeep Saha, Prateek Yadav, Lisa Bauer, Mohit Bansal

Reasoning

Challenge:	Current commonsense-reasoning tasks are discriminative in nature, where a model answers a multiple-choice question for a certain context.
Approach:	They propose a generative task that generates a commonsense-augmented graph for stance prediction by using a create-verify-and-refine graph collection framework.
Outcome:	The proposed model is able to generate a graph that serves as non-trivial, complete, and unambiguous explanation for the predicted stance.

Employing Argumentation Knowledge Graphs for Neural Argument Generation (2021.acl-long)

Copied to clipboard

Khalid Al Khatib, Lukas Trautner, Henning Wachsmuth, Yufang Hou, Benno Stein

Structured Data in NLP

Challenge:	Existing methods for generating arguments use end-to-end knowledge graphs or are controlled with respect to the argument's topic, aspects, or stance.
Approach:	They construct and populate three knowledge graphs and encode them into debate portals and relevant paragraphs from Wikipedia.
Outcome:	The proposed model produces arguments with superior quality than those generated without knowledge.

Retrieval and Reasoning on KGs: Integrate Knowledge Graphs into Large Language Models for Complex Question Answering (2024.findings-emnlp)

Copied to clipboard

Yixin Ji, Kaixin Wu, Juntao Li, Wei Chen, Mingjie Zhong, Xu Jia, Min Zhang

Semantic Text Processing

Challenge:	Large Language Models (LLMs) have performed impressively in various NLP tasks, but their inherent hallucination phenomena severely challenge their credibility in complex reasoning.
Approach:	They propose to integrate explainable Knowledge Graphs (KGs) with LLMs to alleviate hallucinations . they construct subgraphs to enhance the retrieval capabilities of KGs via CoT reasoning.
Outcome:	Extensive experiments on two KGQA datasets show that the proposed model achieves convincing performance compared to strong baselines.

SocraticKG: Knowledge Graph Construction via QA-Driven Fact Extraction (2026.findings-acl)

Copied to clipboard

Sanghyeok Choi, Woosang Jeon, Kyuseok Yang, Taehyeong Kim

Structured Data in NLP

Challenge:	Existing approaches to construct knowledge graphs struggle with factual coverage and information loss.
Approach:	They propose an automated KG construction method that introduces question-answer pairs as a structured intermediate representation to unfold document-level semantics prior to triple extraction.
Outcome:	The proposed method achieves superior factual retention while maintaining high structural cohesion even as extracted knowledge volume substantially expands.