Predicting information pathways across online communities

Y **, YC Lee, K Sharma, M Ye, K Sikka… - Proceedings of the 29th …, 2023‏ - dl.acm.org
The problem of community-level information pathway prediction (CLIPP) aims at predicting
the transmission trajectory of content across online communities. A successful solution to …

Complex query answering on eventuality knowledge graph with implicit logical constraints

J Bai, X Liu, W Wang, C Luo… - Advances in Neural …, 2023‏ - proceedings.neurips.cc
Querying knowledge graphs (KGs) using deep learning approaches can naturally leverage
the reasoning and generalization ability to learn to infer better answers. Traditional neural …

BRAINTEASER: Lateral Thinking Puzzles for Large Language Model

Y Jiang, F Ilievski, K Ma - arxiv preprint arxiv:2310.05057, 2023‏ - arxiv.org
The success of language models has inspired the NLP community to attend to tasks that
require implicit and complex reasoning, relying on human-like commonsense mechanisms …

Acquiring and modeling abstract commonsense knowledge via conceptualization

M He, T Fang, W Wang, Y Song - Artificial Intelligence, 2024‏ - Elsevier
Conceptualization, or viewing entities and situations as instances of abstract concepts in
mind and making inferences based on that, is a vital component in human intelligence for …

Intentionqa: A benchmark for evaluating purchase intention comprehension abilities of language models in e-commerce

W Ding, W Wang, SHD Kwok, M Liu, T Fang… - arxiv preprint arxiv …, 2024‏ - arxiv.org
Enhancing Language Models'(LMs) ability to understand purchase intentions in E-
commerce scenarios is crucial for their effective assistance in various downstream tasks …

Knowcomp at semeval-2023 task 7: Fine-tuning pre-trained language models for clinical trial entailment identification

W Wang, B Xu, T Fang, L Zhang… - Proceedings of the 17th …, 2023‏ - aclanthology.org
In this paper, we present our system for the textual entailment identification task as a subtask
of the SemEval-2023 Task 7: Multi-evidence Natural Language Inference for Clinical Trial …

MARS: Benchmarking the metaphysical reasoning abilities of language models with a multi-task evaluation dataset

W Wang, Y Song - arxiv preprint arxiv:2406.02106, 2024‏ - arxiv.org
To enable Large Language Models (LLMs) to function as conscious agents with
generalizable reasoning capabilities, it is crucial that they possess the reasoning ability to …

KnowComp at DialAM-2024: Fine-tuning Pre-trained Language Models for Dialogical Argument Mining with Inference Anchoring Theory

Y Wu, Y Zhou, B Xu, W Wang… - Proceedings of the 11th …, 2024‏ - aclanthology.org
In this paper, we present our framework for DialAM-2024 TaskA: Identification of
Propositional Relations and TaskB: Identification of Illocutionary Relations. The goal of task …

Miko: Multimodal Intention Knowledge Distillation from Large Language Models for Social-Media Commonsense Discovery

F Lu, W Wang, Y Luo, Z Zhu, Q Sun, B Xu… - Proceedings of the …, 2024‏ - dl.acm.org
Social media has become ubiquitous for connecting with others, staying updated with news,
expressing opinions, and finding entertainment. However, understanding the intention …

Gold: A global and local-aware denoising framework for commonsense knowledge graph noise detection

Z Deng, W Wang, Z Wang, X Liu, Y Song - arxiv preprint arxiv:2310.12011, 2023‏ - arxiv.org
Commonsense Knowledge Graphs (CSKGs) are crucial for commonsense reasoning, yet
constructing them through human annotations can be costly. As a result, various automatic …