Can large language models infer causation from correlation?

Z Jin, J Liu, Z Lyu, S Poff, M Sachan, R Mihalcea… - arXiv preprint arXiv …, 2023 - arxiv.org
Causal inference is one of the hallmarks of human intelligence. While the field of CausalNLP
has attracted much interest in the recent years, existing causal inference datasets in NLP …

Large language models for propaganda span annotation

M Hasanain, F Ahmad, F Alam - arXiv preprint arXiv:2311.09812, 2023 - arxiv.org
The use of propagandistic techniques in online content has increased in recent years aiming
to manipulate online audiences. Fine-grained propaganda detection and extraction of …

Argument-based detection and classification of fallacies in political debates

P Goffredo, M Espinoza, S Villata… - Proceedings of the 2023 …, 2023 - hal.science
Fallacies are arguments that employ faulty reasoning. Given their persuasive and seemingly
valid nature, fallacious arguments are often used in political debates. Employing these …

Modeling appropriate language in argumentation

T Ziegenbein, S Syed, F Lange, M Potthast… - arXiv preprint arXiv …, 2023 - arxiv.org
Online discussion moderators must make ad-hoc decisions about whether the contributions
of discussion participants are appropriate or should be removed to maintain civility. Existing …

Discourse structures guided fine-grained propaganda identification

Y Lei, R Huang - arXiv preprint arXiv:2310.18544, 2023 - arxiv.org
Propaganda is a form of deceptive narratives that instigate or mislead the public, usually
with a political purpose. In this paper, we aim to identify propaganda in political news at two …

Human-in-the-loop evaluation for early misinformation detection: A case study of COVID-19 treatments

E Mendes, Y Chen, W Xu, A Ritter - arXiv preprint arXiv:2212.09683, 2022 - arxiv.org
We present a human-in-the-loop evaluation framework for fact-checking novel
misinformation claims and identifying social media messages that support them. Our …

Detecting argumentative fallacies in the wild: Problems and limitations of large language models

R Ruiz-Dolz, J Lawrence - Proceedings of the 10th …, 2023 - discovery.dundee.ac.uk
Previous work on the automatic identification of fallacies in natural language text has
typically approached the problem in constrained experimental setups that make it difficult to …

Hierarchical machine learning models can identify stimuli of climate change misinformation on social media

C Rojas, F Algra-Maschio, M Andrejevic… - … Earth & Environment, 2024 - nature.com
Misinformation about climate change poses a substantial threat to societal well-being,
prompting the urgent need for effective mitigation strategies. However, the rapid proliferation …

Grounding fallacies misrepresenting scientific publications in evidence

M Glockner, Y Hou, P Nakov, I Gurevych - arXiv preprint arXiv:2408.12812, 2024 - arxiv.org
Health-related misinformation claims often falsely cite a credible biomedical publication as
evidence, which superficially appears to support the false claim. The publication does not …

Vi-AbSQA: multi-task prompt instruction tuning model for Vietnamese aspect-based sentiment quadruple analysis

TV Dang, D Hao, N Nguyen - ACM Transactions on Asian and Low …, 2024 - dl.acm.org
Aspect-based sentiment analysis (ABSA) has recently received considerable attention within
the Natural Language Processing (NLP) community, especially for complex tasks like triplet …