Irwin Deng
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Irwin Deng has a total of 5 co-authors. Here are the top co-authors by number of shared publications:
- Dan Roth
University of Pennsylvania
2 shared publications - Kushagra Dixit
University of Pennsylvania
1 shared publication - Kushagra Dixit
University of Utah
1 shared publication Vivek Gupta
University of Pennsylvania
1 shared publication- Vivek Gupta
Arizona State University
1 shared publication
Latest Publications
- Open Access
- 1 January 2025
- Published by Association for Computational Linguistics (ACL)
- p. 4936-4955
Enhancing Temporal Understanding in LLMs for Semi-structured Tables
Irwin Deng, Kushagra Dixit, Dan Roth, Vivek Gupta. Findings of the Association for Computational Linguistics: NAACL 2025. 2025.
- 1 January 2025
- Published by Association for Computational Linguistics (ACL)
- p. 4936-4955
Open AccessEnhancing Temporal Understanding in LLMs for Semi-structured Tables
Irwin Deng, Kushagra Dixit, Dan Roth, Vivek Gupta. Findings of the Association for Computational Linguistics: NAACL 2025. 2025.
- Open Access
Enhancing Temporal Understanding in LLMs for Semi-structured Tables
Temporal reasoning over tabular data presents substantial challenges for large language models (LLMs), as evidenced by recent research. In this study, we conduct a comprehensive analysis of temporal datasets to pinpoint the specific limitations of LLMs. Our investigation leads to enhancements in TempTabQA, a dataset specifically designed for tabular temporal question answering. We provide critical insights for improving LLM performance in temporal reasoning tasks with tabular data. Furthermore, we introduce a novel approach, C.L.E.A.R to strengthen LLM capabilities in this domain. Our findings demonstrate that our method significantly improves evidence-based reasoning across various models. Additionally, our experimental results reveal that indirect supervision with auxiliary data substantially boosts model performance in these tasks. This work contributes to a deeper understanding of LLMs' temporal reasoning abilities over tabular data and promotes advancements in their application across diverse fields.
Open AccessEnhancing Temporal Understanding in LLMs for Semi-structured Tables
Temporal reasoning over tabular data presents substantial challenges for large language models (LLMs), as evidenced by recent research. In this study, we conduct a comprehensive analysis of temporal datasets to pinpoint the specific limitations of LLMs. Our investigation leads to enhancements in TempTabQA, a dataset specifically designed for tabular temporal question answering. We provide critical insights for improving LLM performance in temporal reasoning tasks with tabular data. Furthermore, we introduce a novel approach, C.L.E.A.R to strengthen LLM capabilities in this domain. Our findings demonstrate that our method significantly improves evidence-based reasoning across various models. Additionally, our experimental results reveal that indirect supervision with auxiliary data substantially boosts model performance in these tasks. This work contributes to a deeper understanding of LLMs' temporal reasoning abilities over tabular data and promotes advancements in their application across diverse fields.