In this work, we propose optimizing the usage costs of LLMs by estimating their output quality (without actually invoking the LLMs), and then solving an optimization routine for the LLM selection to either keep costs under a budget, or minimize the costs, in a quality and latency aware manner.
Our architecture is based on two parts: a the first part contains an image captioning model that takes in an image that the brand wants to post online and gives a plain English caption; b the second part takes in the generated caption along with the target brand personality and outputs a catchy personality-aligned social media caption.
We address the task of evidence retrieval for long document question answering, which involves locating relevant paragraphs within a document to answer a question.
First, our attention segregation loss reduces the cross-attention overlap between attention maps of different concepts in the text prompt, thereby reducing the confusion/conflict among various concepts and the eventual capture of all concepts in the generated output.
We propose KGT5-context, a simple sequence-to-sequence model for link prediction (LP) in knowledge graphs (KG).
Ranked #1 on Link Prediction on Wikidata5M
Recent years have witnessed much interest in temporal reasoning over knowledge graphs (KG) for complex question answering (QA), but there remains a substantial gap in human capabilities.
These methods have recently been applied to KG link prediction and question answering over incomplete KGs (KGQA).
Ranked #5 on Link Prediction on Wikidata5M
Temporal Knowledge Graphs (Temporal KGs) extend regular Knowledge Graphs by providing temporal scopes (start and end times) on each edge in the KG.
Ranked #5 on Question Answering on CronQuestions
In a separate line of research, KG embedding methods have been proposed to reduce KG sparsity by performing missing link prediction.