3 papers
cs.CL2026
Context Poisoning as Extreme-Value Attention Interference in Long-Context Language Models
Meysam Ghaffari, Nina Fatehi, Bhaskar Sen +2
Large language models can process increasingly long prompts, yet their ability to locate and use decisive evidence may degrade as irrelevant or confusable context is added. We form…
cs.CL2022
CPTAM: Constituency Parse Tree Aggregation Method
Adithya Kulkarni, Nasim Sabetpour, Alexey Markin +2
Diverse Natural Language Processing tasks employ constituency parsing to understand the syntactic structure of a sentence according to a phrase structure grammar. Many state-of-the…
cs.HC2021
Truth Discovery in Sequence Labels from Crowds
Nasim Sabetpour, Adithya Kulkarni, Sihong Xie +1
Annotation quality and quantity positively affect the learning performance of sequence labeling, a vital task in Natural Language Processing. Hiring domain experts to annotate a co…