KBS

Sememe Prediction for BabelNet Synsets using Multilingual and Multimodal Information (2022.findings-acl)

Challenge:	Existing benchmarks fail to reflect robustness challenges and fairly evaluate models.
Approach:	They propose to ground language models to knowledge bases to investigate distribution shifts in language and linguistic aspects of distribution shift.
Outcome:	The proposed method fails to evaluate language models in large and small datasets . the proposed model fails to cope with unseen schemas and language variations .

Copied to clipboard

Fanchao Qi, Chuancheng Lv, Zhiyuan Liu, Xiaojun Meng, Maosong Sun, Hai-Tao Zheng

Multimodality

Challenge:	Existing sememe KBs only cover a few languages, which hinders the wide utilization of sememes.
Approach:	They propose to build a multilingual sememe KB based on a dictionary called BabelNet . they use multilingual synonyms, multilingual glosses and images to encode sememes .
Outcome:	The proposed model outperforms previous methods in terms of MAP and F1 scores.

Open Relation Extraction: Relational Knowledge Transfer from Supervised Data to Unsupervised Data (D19-1)

Copied to clipboard

Ruidong Wu, Yuan Yao, Xu Han, Ruobing Xie, Zhiyuan Liu, Fen Lin, Leyu Lin, Maosong Sun

Retrieval, Re-ranking and Multi-task Learning for Knowledge-Base Question Answering (2021.eacl-main)

Challenge:	Existing methods to extract relational facts from open domain corpora are time-consuming and human-intensive.
Approach:	They propose a framework to learn similarity metrics of relations from labeled data . they propose to transfer relational knowledge to identify novel relations in unlabeled data.
Outcome:	Experiments on two real-world datasets show that the proposed framework improves compared with state-of-the-art methods.

Copied to clipboard

Zhiguo Wang, Patrick Ng, Ramesh Nallapati, Bing Xiang

X-WikiRE: A Large, Multilingual Resource for Relation Extraction as Machine Comprehension (D19-61)

Challenge:	Existing work on question answering over knowledge bases limited the search space to a subset of KBs . a retrieval-and-rerank framework is used to access KB and rerank retrieved candidates with more powerful neural networks.
Approach:	They propose to share a BERT encoder across all three sub-tasks and define task-specific layers on top of the shared layer.
Outcome:	The proposed method improves accuracy and accuracy on the SimpleQuestions dataset and the FreebaseQA dataset.

Copied to clipboard

Mostafa Abdou, Cezar Sas, Rahul Aralikatte, Isabelle Augenstein, Anders Søgaard

Multilinguality

Challenge:	Existing knowledge bases are heavily biased towards English, but Wikipedias cover very different topics in different languages.
Approach:	They propose a multilingual dataset that frams relation extraction as a machine reading problem.
Outcome:	The proposed model can be used to transfer models cross-lingually and improves knowledge base completion across languages.

Knowledge Base Question Answering through Recursive Hypergraphs (2021.eacl-main)

Copied to clipboard

Naganand Yadati, Dayanidhi R S, Vaishnavi S, Indira K M, Srinidhi G

Plug-and-Play Adaptation for Continuously-updated QA (2022.findings-acl)

Challenge:	Existing methods for Knowledge Base Question Answering (KBQA) do not explicitly incorporate the recursive relational group structure in the given knowledge base.
Approach:	They propose a method to model KBs through recursive hypergraphs using hypergraph data.
Outcome:	The proposed method is based on recursive hypergraphs and has been released on multiple benchmarks.

Copied to clipboard

Kyungjae Lee, Wookje Han, Seung-won Hwang, Hwaran Lee, Joonsuk Park, Sang-Woo Lee

AutoKB: Automated Creation of Structured Knowledge Bases for Domain-Specific Support (2025.naacl-industry)

Challenge:	Existing tasks to assess LMs’ efficacy as KBs do not adequately consider multiple large-scale updates.
Approach:	They propose a task where multiple large-scale updates are made to language models and plug-in modules are used to handle the updates.
Outcome:	The proposed method outperforms existing methods on zsRE QA and NQ datasets and is 4x more effective in terms of updates/forgets ratio compared to a fine-tuning baseline.

Copied to clipboard

Rishav Sahay, Arihant Jain, Purav Aggarwal, Anoop Saladi

Multi-Relational Question Answering from Narratives: Machine Reading and Reasoning in Simulated Worlds (P18-1)

Challenge:	Effective customer support requires domain-specific solutions tailored to users’ issues.
Approach:	They propose an automated pipeline for building a domain-specific KB with a hierarchical tree structure that maps user issues to precise and domain-compliant solutions.
Outcome:	Experiments in troubleshooting and medical domains show that the proposed pipeline outperforms LLMs and unstructured knowledge bases and is 75 times more cost-effective than manual methods.

Copied to clipboard

Igor Labutov, Bishan Yang, Anusha Prakash, Amos Azaria

Question Answering

Challenge:	Question Answering (QA) has primarily focused on knowledge bases or free text as a source of knowledge.
Approach:	They propose a task of multi-relational QA over personal narrative using text worlds . they generate and release a lightweight Python-based framework for easily generating additional worlds and narrative .
Outcome:	The proposed framework combines elements of structured QA over knowledge bases and unstructured QA . it generates and analyzes five diverse datasets with dynamic narrative . the framework is lightweight and easy to use .

AirConcierge: Generating Task-Oriented Dialogue via Efficient Large-Scale Knowledge Retrieval (2020.findings-emnlp)

Copied to clipboard

Chieh-Yang Chen, Pei-Hsin Wang, Shih-Chieh Chang, Da-Cheng Juan, Wei Wei, Jia-Yu Pan

Relational World Knowledge Representation in Contextual Language Models: A Review (2021.emnlp-main)

Challenge:	Existing neural task-oriented dialogue systems cannot be encoded by memory networks, such as memory networks.
Approach:	They propose an end-to-end trainable text-to SQL guided framework to learn a neural agent that interacts with KBs using the generated SQL queries.
Outcome:	The proposed method significantly improves on the AirDialogue dataset, which contains the conversations of customers booking flight tickets from the agent.

Copied to clipboard

Tara Safavi, Danai Koutra

ReGen: Reinforcement Learning for Text and Knowledge Base Generation using Pretrained Language Models (2021.emnlp-main)

Challenge:	Existing knowledge bases are organized according to manual schemas that limit their expressiveness and require significant human engineering and maintenance.
Approach:	They propose to organize knowledge representation strategies in LMs by the level of KB supervision provided . they propose to highlight notable models, evaluation tasks, and findings .
Outcome:	The proposed model can internalize and express relational knowledge in more flexible forms.

Copied to clipboard

Pierre Dognin, Inkit Padhi, Igor Melnyk, Payel Das

Augmenting Pre-trained Language Models with QA-Memory for Open-Domain Question Answering (2023.eacl-main)

Challenge:	Existing approaches to generate relevant Knowledge Bases from text and graph data are gaining popularity.
Approach:	They propose a bidirectional generation of text and graph leveraging Reinforcement Learning.
Outcome:	The proposed system improves on WebNLG+ 2020 and TekGen datasets.

Copied to clipboard

Wenhu Chen, Pat Verga, Michiel de Jong, John Wieting, William W. Cohen

Language Models over Large-Scale Knowledge Base: on Capacity, Flexibility and Reasoning for New Facts (2025.coling-main)

Challenge:	Existing methods for open-domain question-answering use an open book approach . a recent alternative is to retrieve from a collection of previously-generated question-annwer pairs .
Approach:	They propose a new QA system that augments a text-to-text model with a large memory of question-answer pairs and a task for the latent step of question retrieval.
Outcome:	The proposed system outperforms closed-book QA and can answer multi-hop questions.

Copied to clipboard

Qiyuan He, Yizhong Wang, Jianfei Yu, Wenya Wang

ChatKBQA: A Generate-then-Retrieve Framework for Knowledge Base Question Answering with Fine-tuned Large Language Models (2024.findings-acl)

Challenge:	Existing studies on LMs lack systematic studies on their structured reasoning capabilities over the infused knowledge.
Approach:	They investigate how LMs of different sizes can store world knowledge of different frequencies in a large-scale KB after training on the abundant world knowledge triplets.
Outcome:	The proposed models can store and respond to natural language queries with flexibility and reasoning abilities, but they need to be enhanced to fully realize their potential.

Copied to clipboard

Haoran Luo, Haihong E, Zichen Tang, Shiyao Peng, Yikai Guo, Wentai Zhang, Chenghao Ma, Guanting Dong, Meina Song, Wei Lin, Yifan Zhu, Anh Tuan Luu

ArT: All-round Thinker for Unsupervised Commonsense Question Answering (2022.coling-1)

Challenge:	Existing KBQA methods address inefficient knowledge retrieval and semantic parsing errors.
Approach:	They propose a generatethen-retrieve KBQA framework that generates logical form and replaces entities and relations with an unsupervised retrieval method to improve both generation and retrieval more directly.
Outcome:	Experimental results show that ChatKBQA achieves new state-of-the-art performance on standard KBQA datasets, WebQSP, and CWQ.

Copied to clipboard

Jiawei Wang, Hai Zhao

Cross-lingual Knowledge Projection Using Machine Translation and Target-side Knowledge Base Completion (C18-1)

Challenge:	Existing work on commonsense QA requires labeled training data for its success . existing work relies on large-scale in-domain or out-of-domain labeles or fails to generate knowledge of high quality in a general way.
Approach:	They propose an approach to commonsense question-answering (QA) that takes association during knowledge generation.
Outcome:	The proposed model outperforms existing models on commonsense QA benchmarks.

Copied to clipboard

Naoki Otani, Hirokazu Kiyomaru, Daisuke Kawahara, Sadao Kurohashi

Multilinguality

Challenge:	Existing efforts to build commonsense knowledge bases are expensive and lack quantity and quality between languages.
Approach:	They propose to project English commonsense knowledge into Japanese and Chinese with high precision.
Outcome:	The proposed method achieves top-10 accuracy on the crowdsourced English–Japanese benchmark and 18,747 facts of accurate Japanese commonsense within a very short period.

A Systematic Investigation of KB-Text Embedding Alignment at Scale (2021.acl-long)

Copied to clipboard

Vardaan Pahuja, Yu Gu, Wenhu Chen, Mehdi Bahrami, Lei Liu, Wei-Peng Chen, Yu Su

Can Language Models Serve as Temporal Knowledge Bases? (2022.findings-emnlp)

Challenge:	Knowledge bases (KBs) and text often contain complementary knowledge.
Approach:	They propose a framework for aligning KB and text embeddings for joint reasoning . they also evaluate alignment methods to infuse textual information into KB embeddables .
Outcome:	The proposed framework can be used to predict link prediction on emerging entities and events using textual information.

Copied to clipboard

Ruilin Zhao, Feng Zhao, Guandong Xu, Sixiao Zhang, Hai Jin

GraphDialog: Integrating Graph Knowledge into End-to-End Task-Oriented Dialogue Systems (2020.emnlp-main)

Challenge:	Existing studies have only considered language models as knowledge bases in a static setting . memorizing conflicting information is still challenging for LMs and hinders memorization of other unrelated one-to-one relationships.
Approach:	They propose two requirements for treating language models as temporal knowledge bases . they propose a dataset which is aimed at probing temporally-scoped knowledge .
Outcome:	The proposed model can store conflicting information and use stored knowledge for temporal knowledge queries.

Copied to clipboard

Shiquan Yang, Rui Zhang, Sarah Erfani

Language Models as Knowledge Bases: On Entity Representations, Storage Capacity, and Paraphrased Queries (2021.eacl-main)

Challenge:	End-to-end task-oriented dialogue systems aim to generate system responses directly from plain text inputs.
Approach:	They propose a recurrent cell architecture which exploits the structural information in dialogue history . they propose recursive cell architecture to allow representation learning on graphs .
Outcome:	The proposed model improves on two different datasets on task-oriented dialogues.

Copied to clipboard

Benjamin Heinzerling, Kentaro Inui

RESIDE: Improving Distantly-Supervised Neural Relation Extraction using Side Information (D18-1)

Challenge:	Pretrained language models have been suggested as an alternative or complement to structured knowledge bases . however, this paradigm has only been considered in a very limited setting .
Approach:	They propose a paradigm that allows LMs to store a large number of entities . they propose LM-as-KB paradigm which allows querying stored facts .
Outcome:	The proposed paradigm allows handling 21k entities whose name is found in common LM vocabularies . the proposed paradigm has only been considered in a very limited setting .

Copied to clipboard

Shikhar Vashishth, Rishabh Joshi, Sai Suman Prayaga, Chiranjib Bhattacharyya, Partha Talukdar

Knowledgeable Prompt-tuning: Incorporating Knowledge into Prompt Verbalizer for Text Classification (2022.acl-long)

Challenge:	Distantly-supervised Relation Extraction (RE) methods ignore readily available side information.
Approach:	They propose a distantly-supervised neural relation extraction method which uses additional side information from KBs to train an extractor.
Outcome:	The proposed method improves performance even when limited side information is available.

Copied to clipboard

Shengding Hu, Ning Ding, Huadong Wang, Zhiyuan Liu, Jingang Wang, Juanzi Li, Wei Wu, Maosong Sun

A Pretraining Numerical Reasoning Model for Ordinal Constrained Question Answering on Knowledge Base (2021.findings-emnlp)

Challenge:	Recent studies suggest that pre-trained language models have gained rich knowledge during pre-training.
Approach:	They propose to tune pre-trained language models with task-specific prompts to improve and stabilize prompttuning.
Outcome:	Extensive experiments on zero and few-shot text classification tasks show that prompt-tuning improves and stabilizes prompttun-ing.

Copied to clipboard

Yu Feng, Jing Zhang, Gaole He, Wayne Xin Zhao, Lemao Liu, Quan Liu, Cuiping Li, Hong Chen

KB-Plugin: A Plug-and-play Framework for Large Language Models to Induce Programs over Low-resourced Knowledge Bases (2024.emnlp-main)

Challenge:	Existing knowledge bases (KBs) can explicitly facilitate the QA process.
Approach:	They propose a numerical reasoning model pretraining NumGNN and NumTransformer, guided by explicit self-supervision signals, to enhance numerical reasoning ability for IR-based KBQA models.
Outcome:	Extensive experiments on two KBQA benchmarks confirm the effectiveness of the proposed model.

Copied to clipboard

Jiajie Zhang, Shulin Cao, Linmei Hu, Ling Feng, Lei Hou, Juanzi Li

STACKFEED: Structured Textual Actor-Critic Knowledge base editing with FEEDback (2025.emnlp-industry)

Challenge:	Program induction (PI) is a promising paradigm for using knowledge bases (KBs) to help large language models answer complex knowledge-intensive questions.
Approach:	They propose a plug-and-play framework that enables large language models to induce programs over any low-resourced KB.
Outcome:	Experiments show that KB-Plugin outperforms SoTA low-resourced PI methods with 25x smaller backbone LLM on large-scale and domain-specific KBs and even approaches the performance of supervised methods.

Copied to clipboard

Shashank Kirtania, Naman Gupta, Priyanshu Gupta, Sumit Gulwani, Arun Iyer, Suresh Parthasarathy Iyengar, Arjun Radhakrishna, Sriram K. Rajamani, Gustavo Soares

Visual Named Entity Linking: A New Dataset and A Baseline (2022.findings-emnlp)

Challenge:	Large Language Models (LLMs) often generate incorrect or outdated information, especially in low-resource settings or when dealing with private data.
Approach:	They propose a framework that iteratively refines the knowledge base based on expert feedback . they define a ReACT actor agent on each document to perform structured edits .
Outcome:	The proposed framework improves the quality and performance of the RAG system on low-resource programming problems, modified Python packages, and factual question-answering tasks.

Copied to clipboard

Wen Sun, Yixing Fan, Jiafeng Guo, Ruqing Zhang, Xueqi Cheng

Visual Data in NLP

Challenge:	Existing tasks in Visual Entity Linking (VEL) rely on textual data to complement multi-modal linking or only link objects with general entities.
Approach:	They propose a task to link regions of images with corresponding entities in Knowledge Bases . they propose three sub-tasks, based on a human-annotated visual person dataset .
Outcome:	The proposed task is based on a human-annotated visual person linking dataset . the proposed sub-tasks are validated on the WIKIPerson dataset based upon the proposed methods .

Cross-Lingual Question Answering over Knowledge Base as Reading Comprehension (2023.findings-eacl)

Copied to clipboard

Chen Zhang, Yuxuan Lai, Yansong Feng, Xingyu Shen, Haowei Du, Dongyan Zhao

Evaluating Step-by-Step Reasoning through Symbolic Verification (2024.findings-naacl)

Challenge:	Existing high-quality xMRC datasets can be further utilized to fine-tune our model.
Approach:	They propose a cross-lingual question answering over knowledge base approach that converts KB subgraphs into passages to narrow the gap between KB schemas and questions.
Outcome:	The proposed approach outperforms baselines and achieves strong few-shot and zero-shot performance on two xKBQA datasets in 12 languages.

Copied to clipboard

YiFan Zhang, Hanlin Zhang, Li Li, Eric Xing

Knowledge Prompting in Pre-trained Language Model for Natural Language Understanding (2022.emnlp-main)

Challenge:	Pre-trained language models (LMs) have shown remarkable reasoning performance using explanations or chain-of-thoughts (CoT)) for in-context learning.
Approach:	They propose to use symbolic examples to iteratively reason over symbolic examples and to recover Prolog’s backward chaining algorithm to iterate over KBs.
Outcome:	The proposed model performs better on length generalization benchmarks than CoT on explanations and chain-of-thoughts (CoT) tasks.

Copied to clipboard

Jianing Wang, Wenkang Huang, Minghui Qiu, Qiuhui Shi, Hongbin Wang, Xiang Li, Ming Gao

Language Model Analysis for Ontology Subsumption Inference (2023.findings-acl)

Challenge:	Existing knowledge-enhanced pre-trained language models (PLMs) introduce redundant factual knowledge from knowledge bases and require complex modules.
Approach:	They propose a knowledge prompting-based PLM framework that incorporates factual knowledge into PLMs.
Outcome:	The proposed framework can be flexibly combined with existing mainstream PLMs.

Copied to clipboard

Yuan He, Jiaoyan Chen, Ernesto Jimenez-Ruiz, Hang Dong, Ian Horrocks

Enhancing Pre-Trained Language Representations with Rich Knowledge for Machine Reading Comprehension (P19-1)

Challenge:	Existing studies focus on simple, triple-based, relational KBs but omit more sophisticated, logic-based conceptualised KB.
Approach:	They propose to use ontology subsumption axioms to probe LMs' knowledge of ontologies by probing datasets from atomic and complex concepts.
Outcome:	The proposed methods encode less background knowledge of Subsumption Inference (SI) than traditional Natural Language Inference but can improve on SI significantly when a small number of samples are given.

Copied to clipboard

An Yang, Quan Wang, Jing Liu, Kai Liu, Yajuan Lyu, Hua Wu, Qiaoqiao She, Sujian Li

Modelling Long-distance Node Relations for KBQA with Global Dynamic Graph (2020.coling-main)

Challenge:	Recent results show pre-trained language models (LMs) can improve machine reading comprehension (MRC) Experimental results indicate that KT-NET offers significant and consistent improvements over BERT .
Approach:	They propose a method that leverages external knowledge bases to improve machine reading comprehension (MRC) KT-NET employs an attention mechanism to select desired knowledge from KBs and fuses selected knowledge with BERT to enable context- and knowledge-aware predictions.
Outcome:	The proposed model outperforms baseline models on ReCoRD and SQuAD1.1 benchmarks and ranks 1st on the ReCoDR and SQUAD1.1 leaderboards.

Copied to clipboard

Xu Wang, Shuai Zhao, Jiale Han, Bo Cheng, Hao Yang, Jianchang Ao, Zhenzi Li

Structured Data in NLP

Challenge:	Existing studies rely on deep graph neural networks (GNNs) to capture rich structural information, but they lack the structural information needed for QA.
Approach:	They propose a framework which captures structural information from KBs and models long-distance node relations from two perspectives.
Outcome:	The proposed framework models long-distance node relations from two perspectives . it is based on two widely used multi-hop KBQA datasets .

Leveraging Frequent Query Substructures to Generate Formal Queries for Complex Question Answering (D19-1)

Copied to clipboard

Jiwei Ding, Wei Hu, Qixin Xu, Yuzhong Qu

Fact Discovery from Knowledge Base via Facet Decomposition (N19-1)

Challenge:	Existing approaches build universal paraphrasing or ranking models for whole questions . current approaches build a universal ranking model for the whole questions, which fails for complex, long-tail questions.
Approach:	They propose a new query generation approach based on frequent query substructures which helps rank existing query structures or build new query structures.
Outcome:	The proposed approach significantly outperforms existing models on two benchmark datasets.

Copied to clipboard

Zihao Fu, Yankai Lin, Zhiyuan Liu, Wai Lam

Bidirectional Attentive Memory Networks for Question Answering over Knowledge Bases (N19-1)

Challenge:	Recent years have witnessed the emergence and growth of many large-scale knowledge bases (KBs) however, there are some issues unsettled towards enriching the KBs.
Approach:	They propose a framework that decomposes the discovery problem into several facet components and an auto-encoder component to estimate some facets of the fact.
Outcome:	The proposed framework achieves promising results on a benchmark dataset.

Copied to clipboard

Yu Chen, Lingfei Wu, Mohammed J. Zaki

Question Answering

Challenge:	Existing methods for knowledge base question answering ignore subtle inter-relationships between the question and the KB.
Approach:	They propose to model the two-way flow of interactions between questions and KBs using a bidirectional attentive memory network.
Outcome:	The proposed method outperforms existing methods on the WebQuestions benchmark and offers better interpretability compared to baselines.

Connecting Language and Knowledge with Heterogeneous Representations for Neural Relation Extraction (N19-1)

Copied to clipboard

Peng Xu, Denilson Barbosa

Multi-Multi-View Learning: Multilingual and Multi-Representation Entity Typing (D18-1)

Challenge:	Knowledge Bases (KBs) require constant updating to reflect changes to the world they represent.
Approach:	They propose a framework that unifies learning of RE and KBE models . the framework is based on a relation extraction task that uses a KB relation to a phrase .
Outcome:	The proposed framework unifies learning of RE and KBE models, leading to significant improvements over the state-of-the-art RE framework.

Copied to clipboard

Yadollah Yaghoobzadeh, Hinrich Schütze

Prix-LM: Pretraining for Multilingual Knowledge Base Construction (2022.acl-long)

Challenge:	Accurate and complete knowledge bases (KBs) are paramount in NLP.
Approach:	They employ multiview learning for increasing the accuracy and coverage of entity type information in KBs by taking high- and low-resource languages from Wikipedia.
Outcome:	The proposed learning improves the accuracy and coverage of knowledge bases (KBs) by combining language and representation.

Copied to clipboard

Wenxuan Zhou, Fangyu Liu, Ivan Vulić, Nigel Collier, Muhao Chen

Unsupervised Commonsense Question Answering with Self-Talk (2020.emnlp-main)

Challenge:	Existing methods to build and enrich multilingual knowledge bases have not been successful . knowledge expressed in different languages may be complementary and unequally distributed .
Approach:	They propose a model that integrates useful multilingual and KB-based factual knowledge into a single model.
Outcome:	The proposed model can provide richer combined knowledge than monolingual KBs.

Copied to clipboard

Vered Shwartz, Peter West, Ronan Le Bras, Chandra Bhagavatula, Yejin Choi

MLMLM: Link Prediction with Mean Likelihood Masked Language Model (2021.findings-acl)

Challenge:	Current systems rely on pre-trained language models or external knowledge bases to incorporate additional relevant knowledge.
Approach:	They propose an unsupervised framework based on self-talk to improve commonsense performance by asking language models to ask information seeking questions.
Outcome:	Empirical results show that the proposed framework improves on four out of six commonsense benchmarks and competes with models that obtain knowledge from external KBs.

Copied to clipboard

Louis Clouatre, Philippe Trempe, Amal Zouaq, Sarath Chandar

Can Language Models be Biomedical Knowledge Bases? (2021.emnlp-main)

Challenge:	Knowledge Bases (KBs) are easy to query, verifiable, and interpretable. however, they scale with man-hours and high-quality data.
Approach:	They propose to commit the knowledge embedded in MLMs to a KB, making it interpretable . they propose to use a mean likelihood Masked Language Model to compare the likelihood of generating different entities to perform link prediction in a tractable manner.
Outcome:	The proposed approach compares the likelihood of generating different entities to perform link prediction in a tractable manner.

Copied to clipboard

Mujeen Sung, Jinhyuk Lee, Sean Yi, Minji Jeon, Sungdong Kim, Jaewoo Kang

ChemNER: Fine-Grained Chemistry Named Entity Recognition with Ontology-Guided Distant Supervision (2021.emnlp-main)

Challenge:	Existing studies have focused on probing LMs in the general domain but little attention has been given to whether they can be used as domain knowledge bases.
Approach:	They propose to use 49K biomedical factual knowledge triples to probe LMs for biomedically . they find that biomedic LM can achieve up to 18.51% Acc@5 on retrieving biomedcial knowledge.
Outcome:	The proposed biomedical factual knowledge probing benchmark achieves 18.51% Acc@5 on biomedically-relevant knowledge retrieval.

Copied to clipboard

Xuan Wang, Vivian Hu, Xiangchen Song, Shweta Garg, Jinfeng Xiao, Jiawei Han

Evaluating the Knowledge Base Completion Potential of GPT (2023.findings-emnlp)

Challenge:	Named entity recognition (NER) is a fundamental step in scientific literature analysis to build AI-driven systems for molecular discovery, synthetic strategy designing, and manufacturing.
Approach:	They propose an ontology-guided method for fine-grained named entity recognition (NER) it leverages the chemistry type ontologies to generate distant labels with flexible KB-matching .
Outcome:	The proposed method significantly outperforms the state-of-the-art methods with a .25 absolute F1 improvement.

Copied to clipboard

Blerta Veseli, Simon Razniewski, Jan-Christoph Kalo, Gerhard Weikum

Probabilistic Case-based Reasoning for Open-World Knowledge Graph Completion (2020.findings-emnlp)

Challenge:	Language models (LMs) have been proposed for unsupervised knowledge base completion (KBC) however, their ability to do this at scale and with high accuracy remains an open question.
Approach:	They propose to use language models to complete a large public KB, Wikidata, with 90% precision.
Outcome:	The proposed models can extend Wikidata by 27M facts at 90% precision.

Copied to clipboard

Rajarshi Das, Ameya Godbole, Nicholas Monath, Manzil Zaheer, Andrew McCallum

Multimodality

Challenge:	Existing methods for learning non-parametric representations of entities and relations are based on tensor factorization or sophisticated neural approaches.
Approach:	They propose a case-based reasoning system that retrieves ‘cases’ that are similar to the given problem and then stores them in its parameters.
Outcome:	The proposed model outperforms state-of-the-art methods on several benchmark datasets and is non-parametric and grows dynamically as new entities and relations arrive in the KB.

Middleware for LLMs: Tools Are Instrumental for Language Agents in Complex Environments (2024.emnlp-main)

Copied to clipboard

Yu Gu, Yiheng Shu, Hao Yu, Xiao Liu, Yuxiao Dong, Jie Tang, Jayanth Srinivasa, Hugo Latapie, Yu Su

Open Hierarchical Relation Extraction (2021.naacl-main)

Challenge:	Large language models (LLMs) are generalist agents capable of operating within complex environments.
Approach:	They propose a class of tools that can serve as a middleware layer shielding LLMs from environmental complexity.
Outcome:	The proposed tool can shield the LLM from environmental complexity in two representative complex environments.

Copied to clipboard

Kai Zhang, Yuan Yao, Ruobing Xie, Xu Han, Zhiyuan Liu, Fen Lin, Leyu Lin, Maosong Sun

Open Domain Question Answering Using Early Fusion of Knowledge Bases and Text (D18-1)

Challenge:	Existing OpenRE methods cast different relation types in isolation without considering their hierarchical dependency.
Approach:	They propose a framework to establish bidirectional connections between OpenRE and relation hierarchies by integrating hierarchy information into relation representations.
Outcome:	The proposed framework outperforms state-of-the-art models on relation clustering and hierarchy expansion.

Copied to clipboard

Haitian Sun, Bhuwan Dhingra, Manzil Zaheer, Kathryn Mazaitis, Ruslan Salakhutdinov, William Cohen

NegatER: Unsupervised Discovery of Negatives in Commonsense Knowledge Bases (2021.emnlp-main)

Challenge:	Specialized neural models have been developed for extracting answers from text alone or Knowledge Bases (KBs) alone.
Approach:	They propose a novel model for extracting answers from a question-specific subgraph containing text and KB entities and relations.
Outcome:	The proposed model outperforms existing methods in a combination of a KB and entity-linked text in QA over a large text corpus.

Copied to clipboard

Tara Safavi, Jing Zhu, Danai Koutra

COMET: Commonsense Transformers for Automatic Knowledge Graph Construction (P19-1)

Challenge:	Recent advances in knowledge base construction techniques focus on the acquisition of positive (true) KB statements, but negative (false) statements are important for discriminative reasoning.
Approach:	They propose a framework that ranks potential negatives in commonsense KBs using a contextual language model.
Outcome:	The proposed framework ranks negatives in commonsense KBs using a language model . it yields positives that are more grammatical, coherent, and informative .

Copied to clipboard

Antoine Bosselut, Hannah Rashkin, Maarten Sap, Chaitanya Malaviya, Asli Celikyilmaz, Yejin Choi

Knowledge Base Embedding By Cooperative Knowledge Distillation (2020.coling-main)

Challenge:	Existing studies on commonsense knowledge base construction only store loosely structured open-text descriptions of knowledge.
Approach:	They propose a commonsense knowledge base construction model that generates rich commonsensense descriptions in natural language.
Outcome:	The proposed models can generate rich and diverse commonsense descriptions in natural language.

Copied to clipboard

Raphaël Sourty, Jose G. Moreno, François-Paul Servant, Lynda Tamine-Lechani

IntKB: A Verifiable Interactive Framework for Knowledge Base Completion (2020.coling-main)

Challenge:	Knowledge bases are increasingly exploited as gold standard data sources for various knowledge-driven NLP tasks.
Approach:	They propose a method to perform knowledge base representation learning by mutually and jointly distilling knowledge within a dynamic teacher-student setting.
Outcome:	The proposed approach outperforms two baselines, traditional and sequential, on two standard datasets showing that it is possible to distill knowledge between KBs.

Copied to clipboard

Bernhard Kratzwald, Guo Kunpeng, Stefan Feuerriegel, Dennis Diefenbach

Program Transfer for Answering Complex Questions over Knowledge Bases (2022.acl-long)

Challenge:	Knowledge bases (KBs) present databases that store information about entities and relations among them.
Approach:	They propose a question-based interactive framework for KB completion from text . their framework generates facts that are aligned with text snippets and is immediately verifiable by humans .
Outcome:	The proposed framework achieves a hit@1 ratio of 29.7% for initial unseen relations, and gradually improves to 46.2%.

Copied to clipboard

Shulin Cao, Jiaxin Shi, Zijun Yao, Xin Lv, Jifan Yu, Lei Hou, Juanzi Li, Zhiyuan Liu, Jinghui Xiao

Rule-KBQA: Rule-Guided Reasoning for Complex Knowledge Base Question Answering with Large Language Models (2025.coling-main)

Challenge:	Program induction for complex questions over knowledge bases relies on a large number of parallel question-program pairs for the given KB, but the gold program annotations are usually lacking, making learning difficult.
Approach:	They propose an approach to leverage program annotations on rich KBs as external supervision signals to aid program induction for low-resourced KB.
Outcome:	The proposed approach outperforms SOTA methods on ComplexWebQuestions and WebQuestionSP.

Copied to clipboard

Zhiqiang Zhang, Liqiang Wen, Wen Zhao

Interactive-KBQA: Multi-Turn Interactions for Knowledge Base Question Answering with Large Language Models (2024.acl-long)

Challenge:	Existing methods for knowledge base question answering lack grammaticality, faithfulness, and controllability due to hallucinations in the reasoning process.
Approach:	They propose a framework that employs learned rules to guide the generation of logical forms.
Outcome:	The proposed method achieves competitive results on standard KBQA datasets.

Copied to clipboard

Guanming Xiong, Junwei Bao, Wen Zhao

KaeDe: Progressive Generation of Logical Forms via Knowledge-Aware Question Decomposition for Improved KBQA (2025.findings-emnlp)

Challenge:	Knowledge base question answering (KBQA) is a challenging task, particularly in parsing intricate questions into executable logical forms.
Approach:	They propose a framework to generate logical forms through direct interaction with knowledge bases (KBs) by annotating a dataset with step-wise reasoning processes.
Outcome:	The proposed framework achieves competitive results on the WebQuestionsSP, ComplexWebQuestIONS, KQA Pro, and MetaQA datasets with a minimal number of examples (shots). Importantly, the proposed model supports manual intervention, allowing for the iterative refinement of LLM outputs.

Copied to clipboard

Ranran Bu, Jian Cao, Jianqi Gao, Shiyou Qian, Hongming Cai

Conversational Multi-Hop Reasoning with Neural Commonsense Knowledge and Symbolic Logic Rules (2021.emnlp-main)

Challenge:	Existing methods for answering natural language questions are difficult to generate . lack of a logical form for complex graphs can negatively impact overall performance .
Approach:	They propose a generate-then-retrieve method that converts questions into structured LF queries . they propose to combine knowledge-aware question decomposition and progressive LF generation .
Outcome:	The proposed method achieves state-of-the-art (SOTA) performance on WebQuestionSP and ComplexWebQuestions benchmarks.

Copied to clipboard

Forough Arabshahi, Jennifer Lee, Antoine Bosselut, Yejin Choi, Tom Mitchell

Revisiting Unsupervised Relation Extraction (2020.acl-main)

Challenge:	Currently, conversational agents lack commonsense reasoning, preventing them from engaging in rich conversations with humans.
Approach:	They propose a commonsense reasoning system that uncovers unstated presumptions from user commands satisfying a general template of if-(state), then-(action), because-(goal) They propose to use a transformer-based generative commons sense knowledge base as its source of background knowledge to extract multi-hop reasoning chains from the neural KB.
Outcome:	The proposed model achieves a 35% higher success rate than existing methods with human users.

Copied to clipboard

Thy Thy Tran, Phong Le, Sophia Ananiadou

Cross-Lingual Knowledge Projection and Knowledge Enhancement for Zero-Shot Question Answering in Low-Resource Languages (2025.coling-main)

Challenge:	Unsupervised relation extraction (URE) extracts relations between named entities from raw text without manually-labelled data and existing knowledge bases (KBs).
Approach:	They compare unsupervised relation extraction methods to generative and discriminative approaches . they conclude that entity types provide a strong inductive bias for URE .
Outcome:	The proposed method outperforms generative and discriminative approaches on two popular datasets.

Copied to clipboard

Sello Ralethe, Jan Buys

DualTKB: A Dual Learning Bridge between Text and Knowledge Base (2020.emnlp-main)

Challenge:	Knowledge bases (KBs) in low-resource languages are often incomplete, restricting the ability to do zero-shot question answering using multilingual language models.
Approach:	They propose a novel cross-lingual mapping technique which improves word alignments extracted from parallel English-LRL text by combining lexical alignment, named entity recognition, and semantic alignment.
Outcome:	The proposed approach improves zero-shot question answering accuracy by up to 17% compared to baselines without KB access.

Copied to clipboard

Pierre Dognin, Igor Melnyk, Inkit Padhi, Cicero Nogueira dos Santos, Payel Das

Augmenting Reasoning Capabilities of LLMs with Graph Structures in Knowledge Base Question Answering (2024.findings-emnlp)

Challenge:	Existing methods for KB construction and sentence generation are lacking in the field of knowledge transfer.
Approach:	They propose a dual learning approach for unsupervised text to path and path to text transfers in Commonsense Knowledge Bases.
Outcome:	The proposed method compares favorably to existing baselines and is a viable step towards a more advanced system for automatic KB construction/expansion and reverse operation of sentence generation from KBs.

Copied to clipboard

Yuhang Tian, Dandan Song, Zhijing Wu, Changzhi Zhou, Hao Wang, Jun Yang, Jing Xu, Ruanmin Cao, HaoYu Wang

Knowing When Not to Answer: Lightweight KB-Aligned OOD Detection for Safe RAG (2026.acl-long)

Challenge:	Recent work uses Large Language Models (LLMs) for semantic parsing to address Knowledge Base Question Answering tasks.
Approach:	They propose a framework that augments reasoning capabilities of LLMs with Graph Structures in Knowledge Base Question Answering to retrieve question-related graph structures.
Outcome:	The proposed framework outperforms existing methods on GrailQA and WebQSP under the few-shot setting.

Copied to clipboard

Ilias Triantafyllopoulos, Renyi Qu, Salvatore Giorgi, Brenda Curtis, Lyle Ungar, João Sedoc

Responsible & Trustworthy NLP

Challenge:	Retrieval-Augmented Generation (RAG) systems are increasingly deployed in high-stakes domains where safety depends on how a system answers . out-of-domain (OOD) queries can impair performance and safety .
Approach:	They propose to use lightweight, KB-aligned OOD detection as an always-on gate for RAG systems.
Outcome:	The proposed method scores queries in a compact subspace selected either by explained-variance retention (EVR) or by a separability-driven -test ranking.

DKAF: KB Arbitration for Learning Task-Oriented Dialog Systems with Dialog-KB Inconsistencies (2023.findings-acl)

Copied to clipboard

Vishal Saley, Rocktim Das, Dinesh Raghu, null Mausam

Knowing False Negatives: An Adversarial Training Method for Distantly Supervised Relation Extraction (2021.emnlp-main)

Challenge:	Existing approaches for learning task-oriented dialog agents assume the KB snapshot is current during training.
Approach:	They propose a dialog-KB arbitration framework which predicts the contemporary KB snapshot for each train dialog.
Outcome:	The proposed model performs better on two publicly available dialog datasets than baselines on both datasets.

Copied to clipboard

Kailong Hao, Botao Yu, Wei Hu

Robustness in NLP

Challenge:	Existing methods for relation extraction ignore the incompleteness of existing knowledge bases . current methods are too weak and cause noises when training and testing are not based on training data.
Approach:	They propose a method to automatically align unstructured text with relation instances in a knowledge base . they use heuristics to leverage the memory mechanism of deep neural networks to find out possible FN samples .
Outcome:	Experiments on two wildly-used benchmark datasets show the effectiveness of the proposed method.

Extractive Medical Entity Disambiguation with Memory Mechanism and Memorized Entity Information (2024.findings-emnlp)

Copied to clipboard

Guobiao Zhang, Xueping Peng, Tao Shen, Guodong Long, Jiasheng Si, Libo Qin, Wenpeng Lu

Challenge:	Existing methods focus on local optimal while ignoring sole-mention disambiguation boosted by richer context from other mentions’ disambiguating processes.
Approach:	They propose an approach to extracting medical entity disambiguation using memory mechanism and memorized entity information (M3E) they use a memory mechanism module that performs memory caching, retrieval, fusion and cross-network residual to aid the disambiguations of remaining mentions.
Outcome:	The proposed method outperforms state-of-the-art methods on two benchmark datasets.

Injecting Domain Knowledge in Language Models for Task-oriented Dialogue Systems (2022.emnlp-main)

Copied to clipboard

Denis Emelin, Daniele Bonadiman, Sawsan Alqahtani, Yi Zhang, Saab Mansour

Real World Conversational Entity Linking Requires More Than Zero-Shots (2024.findings-acl)

Challenge:	Pre-trained language models lack domain-specific knowledge that does not naturally occur in pre-training data.
Approach:	They propose to inject domain-specific knowledge prior to fine-tuning on TOD tasks by using adapters that can be easily integrated with PLMs.
Outcome:	The proposed methods show that they can inject domain-specific knowledge prior to fine-tuning on TOD tasks.

Copied to clipboard

Mohanna Hoveyda, Arjen Vries, Faegheh Hasibi, Maarten Rijke

Know-Adapter: Towards Knowledge-Aware Parameter-Efficient Transfer Learning for Few-shot Named Entity Recognition (2024.lrec-main)

Challenge:	Entity linking (EL) in conversations is a key component of many downstream tasks such as semantic search.
Approach:	They propose to use Fandom and Wikipedia to evaluate EL models' ability to generalize to a new unfamiliar KB without prior training.
Outcome:	The proposed evaluation framework and dataset are tailored to facilitate the study.

Copied to clipboard

Binling Nie, Yiming Shao, Yigang Wang

Medical Entity Disambiguation with Medical Mention Relation and Fine-grained Entity Knowledge (2024.lrec-main)

Challenge:	Named entity recognition (NER) is a fundamental task in natural language processing.
Approach:	They propose a knowledgeable adapter to incorporate structure and semantic knowledge of knowledge graphs into PLMs for few-shot NER.
Outcome:	The proposed adapter improves the quality of retrieved information by adding explicit knowledge from external sources to PEFTs.

Copied to clipboard

Wenpeng Lu, Guobiao Zhang, Xueping Peng, Hongjiao Guan, Shoujin Wang

Challenge:	Existing methods for medical entity disambiguation (MED) fail to fully utilize the knowledge within medical knowledge bases (KBs) Existing models overlook essential interactions between medical mentions and candidate entities, resulting in knowledge- and interaction-inefficient modeling and suboptimal disambiguations performance.
Approach:	They propose to combine a mention relation fusion module and an entity knowledge fusion modules to map medical mentions to corresponding entities in a knowledge base (KB)
Outcome:	The proposed method outperforms state-of-the-art MED models on two publicly available real-world datasets.

Generating then Refining for Reliable Knowledge Base Question Answering (2026.acl-long)

Copied to clipboard

Jianqi Gao, Hang Yu, Jian Cao, Ranran Bu, Jinghua Tang, Nengjun Zhu, Yonggang Zhang

Joint Knowledge Base Completion and Question Answering by Combining Large Language Models and Small Language Models (2026.acl-long)

Challenge:	Existing knowledge base question answering methods generate LFs that are non-executable due to semantic hallucination issue of large language models.
Approach:	They propose a "generate-verify-refine" framework for reliable LF generation . they propose ARI-KBQA to generate query paths based on hop-by-hop reasoning .
Outcome:	The proposed framework significantly improves model performance with a reduced search space . ARI-KBQA can generate LFs that are non-executable due to semantic hallucination issue .

Copied to clipboard

Yinan Liu, Dongying Lin, Sigang Luo, Xiaochun Yang, Bin Wang