Reward models (RMs) are crucial in aligning large language models (LLMs)...
Although dominant in natural language processing, transformer-based mode...
Traditional multitask learning methods basically can only exploit common...
With increasing privacy concerns on data, recent studies have made
signi...
Aspect Sentiment Triplet Extraction (ASTE) aims to extract the spans of
...
In this technical report, we introduce Effidit (Efficient and Intelligen...
People perceive the world with multiple senses (e.g., through hearing so...
Chinese BERT models achieve remarkable progress in dealing with grammati...
We present a Chinese BERT model dubbed MarkBERT that uses word informati...
This paper presents a Pathways approach to handle many tasks at once. Ou...
Whole word masking (WWM), which masks all subwords corresponding to a wo...
While GPT has become the de-facto method for text generation tasks, its
...
Multi-source unsupervised domain adaptation (MS-UDA) for sentiment analy...