8 papers
ContextWeaver: Selective and Dependency-Structured Memory Construction for LLM Agents
Yating Wu, Yuhao Zhang, Sayan Ghosh +4
Large language model (LLM) agents often struggle in long-context interactions. As the history grows, sliding windows and prompt compression may drop earlier information that later…
Multimodal QUD: Inquisitive Questions from Scientific Figures
Yating Wu, William Rudman, Venkata S Govindarajan +2
Discourse comprehension in complex documents often involves continuously posing and resolving Questions Under Discussion (QUDs). While QUD frameworks have so far focused on text, s…
QUDsim: Quantifying Discourse Similarities in LLM-Generated Text
Ramya Namuduri, Yating Wu, Anshun Asher Zheng +3
As large language models become increasingly capable at various writing tasks, their weakness at generating unique and creative content becomes a major liability. Although LLMs hav…
Which questions should I answer? Salience Prediction of Inquisitive Questions
Yating Wu, Ritika Mangla, Alexandros G. Dimakis +2
Inquisitive questions -- open-ended, curiosity-driven questions people ask as they read -- are an integral part of discourse processing (Kehler and Rohde, 2017; Onea, 2016) and com…
QUDEVAL: The Evaluation of Questions Under Discussion Discourse Parsing
Yating Wu, Ritika Mangla, Greg Durrett +1
Questions Under Discussion (QUD) is a versatile linguistic framework in which discourse progresses as continuously asking questions and answering them. Automatic parsing of a disco…
Elaborative Simplification as Implicit Questions Under Discussion
Yating Wu, William Sheffield, Kyle Mahowald +1
Automated text simplification, a technique useful for making text more accessible to people such as children and emergent bilinguals, is often thought of as a monolingual translati…
Discourse Analysis via Questions and Answers: Parsing Dependency Structures of Questions Under Discussion
Wei-Jen Ko, Yating Wu, Cutter Dalton +3
Automatic discourse processing is bottlenecked by data: current discourse formalisms pose highly demanding annotation tasks involving large taxonomies of discourse relations, makin…
longhorns at DADC 2022: How many linguists does it take to fool a Question Answering model? A systematic approach to adversarial attacks
Venelin Kovatchev, Trina Chatterjee, Venkata S Govindarajan +9
Developing methods to adversarially challenge NLP systems is a promising avenue for improving both model performance and interpretability. Here, we describe the approach of the tea…