Plausible extractive rationalization through semi-supervised entailment signal

WJ Yeo, R Satapathy, E Cambria - arxiv preprint arxiv:2402.08479, 2024 - arxiv.org
The increasing use of complex and opaque black box models requires the adoption of
interpretable measures, one such option is extractive rationalizing models, which serve as a …

Selflre: Self-refining representation learning for low-resource relation extraction

X Hu, J Chen, S Meng, L Wen, PS Yu - Proceedings of the 46th …, 2023 - dl.acm.org
Low-resource relation extraction (LRE) aims to extract potential relations from limited
labeled corpus to handle the problem of scarcity of human annotations. Previous works …

Unveiling the power of language models in chemical research question answering

X Chen, T Wang, T Guo, K Guo, J Zhou, H Li… - Communications …, 2025 - nature.com
While the abilities of language models are thoroughly evaluated in areas like general
domains and biomedicine, academic chemistry remains less explored. Chemical QA tools …

Make Your Decision Convincing! A Unified Two-Stage Framework: Self-Attribution and Decision-Making

Y Du, S Zhao, H Wang, Y Chen, R Bai, Z Qiang… - arxiv preprint arxiv …, 2023 - arxiv.org
Explaining black-box model behavior with natural language has achieved impressive results
in various NLP tasks. Recent research has explored the utilization of subsequences from the …

LOG: A Local-to-Global Optimization Approach for Retrieval-based Explainable Multi-Hop Question Answering

H Xu, Y Zhao, J Zhang, Z Wang… - Proceedings of the 31st …, 2025 - aclanthology.org
Multi-hop question answering (MHQA) aims to utilize multi-source intensive documents
retrieved to derive the answer. However, it is very challenging to model the importance of …

Experiment Design for Hypotheses About How NLP Models Work

S Serrano - 2024 - search.proquest.com
In the last few years, Natural Language Processing models have come a long way.
However, for all the work that continues to report performance improvements, we still see …