Papers by Mubashara Akhtar
Multimodal Automated Fact-Checking: A Survey (2023.findings-emnlp)
Copied to clipboard
Mubashara Akhtar, Michael Schlichtkrull, Zhijiang Guo, Oana Cocarascu, Elena Simperl, Andreas Vlachos
| Challenge: | Existing studies on automated fact-checking focus on text, but they focus on a single modality, text . multimodal misinformation is perceived as more credible by humans and spreads faster than text-only counterparts. |
| Approach: | They propose a framework for automated fact-checking that includes subtasks unique to multimodal misinformation. |
| Outcome: | The proposed framework includes subtasks unique to multimodal misinformation. |
Exploring the Numerical Reasoning Capabilities of Language Models: A Comprehensive Analysis on Tabular Data (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Recent benchmarks have assessed language models' numerical abilities . limitations include tokenization and representation of numbers in text, hallucination, and a lack of numerical commonsense knowledge. |
| Approach: | They propose a hierarchical taxonomy for numerical reasoning skills that includes representation, number sense, manipulation, and complex reasoning. |
| Outcome: | The proposed model outperforms other models on the tabular Natural Language Inference task. |
Reading and Reasoning over Chart Images for Evidence-based Automated Fact-Checking (2023.findings-eacl)
Copied to clipboard
| Challenge: | Existing studies on detecting manipulated or fake images focus on identifying manipulated and false images. |
| Approach: | They propose a novel task, chart-based fact-checking, to validate textual, structural and visual information of charts to determine the veracity of textual claims. |
| Outcome: | The proposed model outperforms existing models in vision-language tests with 63.8% accuracy. |
ChartCheck: Explainable Fact-Checking over Real-World Chart Images (2024.findings-acl)
Copied to clipboard
| Challenge: | Data visualizations are often used to summarize and communicate key information, but they can also be misused to spread misinformation and promote agendas. |
| Approach: | They propose a dataset for explainable fact-checking against real-world charts that uses vision-language and chart-to-table models to evaluate the validity of the dataset. |
| Outcome: | The proposed model is based on vision-language and chart-to-table models and proposes a baseline to the community. |
PubHealthTab: A Public Health Table-based Dataset for Evidence-based Fact Checking (2022.findings-naacl)
Copied to clipboard
| Challenge: | Fact-checking is the task of establishing the veracity of factual information, commonly performed manually by journalists. |
| Approach: | They propose a table fact-checking dataset based on real world public health claims and noisy evidence tables from sources similar to those used by fact checkers. |
| Outcome: | The proposed dataset achieves an overall F1 score of 0.73 . |
Ev2R: Evaluating Evidence Retrieval in Automated Fact-Checking (2026.tacl-1)
Copied to clipboard
| Challenge: | Current methods for automated fact-checking rely on relying on other evaluation metrics and closed knowledge sources. |
| Approach: | They propose a method which combines evidence evaluation with verdict-level proxy scoring. |
| Outcome: | The proposed method outperforms existing methods in accuracy and robustness against human ratings and adversarial tests. |
Efficient Test-Time Scaling of Multi-Step Reasoning by Probing Internal States of Large Language Models (2026.acl-long)
Copied to clipboard
Jingwei Ni, Ekaterina Fadeeva, Tianyi Wu, Mubashara Akhtar, Jiaheng Zhang, Elliott Ash, Markus Leippold, Timothy Baldwin, See-Kiong Ng, Artem Shelmanov, Mrinmaya Sachan
| Challenge: | Existing verification approaches, such as Process Reward Models, are computationally expensive and limited to specific domains. |
| Approach: | They propose a transformer-based probe that uses internal states of frozen LLMs to estimate credibility of reasoning steps during generation. |
| Outcome: | The proposed probes match or exceed PRMs that are up to 810 larger. |