Papers by Aaron Halfaker
Logical Transformers: Infusing Logical Structures into Pre-Trained Language Models (2023.findings-acl)
Copied to clipboard
Borui Wang, Qiuyuan Huang, Budhaditya Deb, Aaron Halfaker, Liqun Shao, Daniel McDuff, Ahmed Hassan Awadallah, Dragomir Radev, Jianfeng Gao
| Challenge: | Existing pre-trained language models that ignore the logical structures underlying natural language text often lack the ability to capture and encode key logical information in the input sequences. |
| Approach: | They propose to construct logic-aware input embeddings for transformer language models through logic detection, logic mapping and hierarchical logical projections and then develop a new modeling paradigm that can upgrade existing transformer language model into logical transformers to boost their performance. |
| Outcome: | The proposed model can achieve superior performance on four important and challenging tasks. |
On Improving Summarization Factual Consistency from Natural Language Feedback (2023.acl-long)
Copied to clipboard
| Challenge: | Recent work shows that language generation models can make errors on fine-grained qualities such as factual consistency. |
| Approach: | They propose to use natural language feedback to improve generation quality and user preference alignment. |
| Outcome: | The proposed model can provide factual consistency in human-edited summaries and further insights into summarization factual consistentness. |