Autonomous agents empowered by Large Language Models (LLMs) have undergo...
Personalized recommendation relies on user historical behaviors to provi...
Despite the advancements of open-source large language models (LLMs) and...
This work examines the presence of modularity in pre-trained Transformer...
Recently, large language models (LLMs) (e.g. GPT-4) have demonstrated
im...
Continual pre-training is the paradigm where pre-trained language models...
In the past decades, recommender systems have attracted much attention i...
Long-form question answering (LFQA) aims at answering complex, open-ende...
Recently, a series of pioneer studies have shown the potency of pre-trai...
Cross-domain recommendation (CDR) aims to leverage the users' behaviors ...
Recently, causal inference has attracted increasing attention from
resea...
Recently, Graph Neural Networks (GNNs) achieve remarkable success in
Rec...
Large-scale commonsense knowledge bases empower a broad range of AI
appl...
In this work, we revisit the Transformer-based pre-trained language mode...
The click behavior is the most widely-used user positive feedback in
rec...
Contrastive learning (CL) has shown its power in recommendation. However...
Conversational recommender systems (CRS) aim to capture user's current
i...
Recent works have shown promising results of prompt tuning in stimulatin...
Pre-training models have shown their power in sequential recommendation....
Recommendation fairness has attracted great attention recently. In real-...
Conversational recommender systems (CRS) aim to provide highquality
reco...
Multi-behavior recommendation (MBR) aims to jointly consider multiple
be...
Cross-domain recommendation (CDR) aims to provide better recommendation
...
Semantically connecting users and items is a fundamental problem for the...
Cold-start problem is still a very challenging problem in recommender
sy...
Search and recommendation are the two most common approaches used by peo...
In recommender systems and advertising platforms, marketers always want ...
Recently, embedding techniques have achieved impressive success in
recom...
Cold-start problems are enormous challenges in practical recommender sys...
Existing sequential recommendation methods rely on large amounts of trai...
Recently, real-world recommendation systems need to deal with millions o...
Distant supervision (DS) has been widely used to generate auto-labeled d...
Recommender systems aim to provide item recommendations for users, and a...
Knowledge graph (KG) entity typing aims at inferring possible missing en...
Question answering (QA) aims to understand user questions and find
appro...
Knowledge graphs typically undergo open-ended growth of new relations. T...
Knowledge representation learning (KRL) aims to represent entities and
r...
Most language modeling methods rely on large-scale data to statistically...
Sememes are minimum semantic units of concepts in human languages, such ...
Knowledge graphs (KGs) can provide significant relational information an...
Emoji is an essential component in dialogues which has been broadly util...
Entity images could provide significant visual information for knowledge...