Papers by Chenxiao Dou

2 papers
To Answer or Not To Answer? Improving Machine Reading Comprehension Model with Span-based Contrastive Learning (2022.findings-naacl)

Copied to clipboard

Challenge: Existing models fail to recognize answerable questions due to subtle literal changes . MRC models are forced to perceive crucial semantic changes from slight literal differences.
Approach: They propose a span-based method of Contrastive Learning which explicitly contrasts answerable questions with their answerable counterparts at the answer span level.
Outcome: The proposed method improves baselines significantly and is an effective way to utilize generated questions.
Lost in the Context: Insufficient and Distracted Attention to Contexts in Preference Modeling (2025.acl-long)

Copied to clipboard

Challenge: Existing reward models concatenate contexts and responses, but they often ignore crucial segments of the context that are important for evaluating the response quality.
Approach: They propose a reward model that evaluates the response quality based on a given context and assigns a rewards reward.
Outcome: The proposed framework significantly improves preference modeling by increasing attention to relevant information within the context and achieves better generalizability.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations