Semantic text matching for long-form documents
Semantic text matching is one of the most important research problems in many domains,
including, but not limited to, information retrieval, question answering, and recommendation …
including, but not limited to, information retrieval, question answering, and recommendation …
Comparing retrieval-augmentation and parameter-efficient fine-tuning for privacy-preserving personalization of large language models
Privacy-preserving methods for personalizing large language models (LLMs) are relatively
under-explored. There are two schools of thought on this topic:(1) generating personalized …
under-explored. There are two schools of thought on this topic:(1) generating personalized …
EmailSum: Abstractive email thread summarization
Recent years have brought about an interest in the challenging task of summarizing
conversation threads (meetings, online discussions, etc.). Such summaries help analysis of …
conversation threads (meetings, online discussions, etc.). Such summaries help analysis of …
Longlamp: A benchmark for personalized long-form text generation
I Kumar, S Viswanathan, S Yerra, A Salemi… - arxiv preprint arxiv …, 2024 - arxiv.org
Long-text generation is seemingly ubiquitous in real-world applications of large language
models such as generating an email or writing a review. Despite the fundamental …
models such as generating an email or writing a review. Despite the fundamental …
Automated evaluation of personalized text generation using large language models
Personalized text generation presents a specialized mechanism for delivering content that is
specific to a user's personal context. While the research progress in this area has been …
specific to a user's personal context. While the research progress in this area has been …
Membership inference on word embedding and beyond
In the text processing context, most ML models are built on word embeddings. These
embeddings are themselves trained on some datasets, potentially containing sensitive data …
embeddings are themselves trained on some datasets, potentially containing sensitive data …
Context-aware intent identification in email conversations
Email continues to be one of the most important means of online communication. People
spend a significant amount of time sending, reading, searching and responding to email in …
spend a significant amount of time sending, reading, searching and responding to email in …
Privacy regularization: Joint privacy-utility optimization in language models
Neural language models are known to have a high capacity for memorization of training
samples. This may have serious privacy implications when training models on user content …
samples. This may have serious privacy implications when training models on user content …
Learning with weak supervision for email intent detection
Email remains one of the most frequently used means of online communication. People
spend significant amount of time every day on emails to exchange information, manage …
spend significant amount of time every day on emails to exchange information, manage …
Searching the enterprise
U Kruschwitz, C Hull - Foundations and Trends® in …, 2017 - nowpublishers.com
Search has become ubiquitous but that does not mean that search has been solved.
Enterprise search, which is broadly speaking the use of information retrieval technology to …
Enterprise search, which is broadly speaking the use of information retrieval technology to …