The first workshop on personalized generative ai@ cikm 2023: Personalization meets large language models
The First Workshop on Personalized Generative AI1 aims to be a cornerstone event
fostering innovation and collaboration in the dynamic field of personalized AI. Leveraging …
fostering innovation and collaboration in the dynamic field of personalized AI. Leveraging …
Graph Meets LLM: A Novel Approach to Collaborative Filtering for Robust Conversational Understanding
Conversational AI systems such as Alexa need to understand defective queries to ensure
robust conversational understanding and reduce user friction. These defective queries often …
robust conversational understanding and reduce user friction. These defective queries often …
Kg-eco: Knowledge graph enhanced entity correction for query rewriting
Query Rewriting (QR) plays a critical role in large-scale dialogue systems for reducing
frictions. When there is an entity error, it imposes extra challenges for a dialogue system to …
frictions. When there is an entity error, it imposes extra challenges for a dialogue system to …
CURATRON: Complete and Robust Preference Data for Rigorous Alignment of Large Language Models
NU Naresh, T Tulabandhula - … of the Fifth Workshop on Data …, 2024 - aclanthology.org
This paper addresses the challenges of aligning large language models (LLMs) with human
values via preference learning (PL), focusing on incomplete and corrupted data in …
values via preference learning (PL), focusing on incomplete and corrupted data in …
CL-QR: Cross-lingual enhanced query reformulation for multi-lingual conversational AI agents
The growing popularity of conversational AI agents such as Alexa, Google Assistant, and Siri
rely on accurate spoken language comprehension. The query reformulation (QR) method …
rely on accurate spoken language comprehension. The query reformulation (QR) method …
Personalized dense retrieval on global index for voice-enabled conversational systems
Voice-controlled AI dialogue systems are susceptible to noise from phonetic variations and
failure to resolve ambiguous entities. Typically, personalized entity resolution (ER) and/or …
failure to resolve ambiguous entities. Typically, personalized entity resolution (ER) and/or …