2 citations · 6 across the 12 of their papers we have counts for
6 papers · 1 filter
Capability-aware Prompt Reformulation Learning for Text-to-Image Generation
Jingtao Zhan, Qingyao Ai, Yiqun Liu +2
Text-to-image generation systems have emerged as revolutionary tools in the realm of artistic creation, offering unprecedented ease in transforming textual prompts into visual art.…
DELTA: Pre-train a Discriminative Encoder for Legal Case Retrieval via Structural Word Alignment
Haitao Li, Qingyao Ai, Xinyan Han +5
Recent research demonstrates the effectiveness of using pre-trained language models for legal case retrieval. Most of the existing works focus on improving the representation abili…
BLADE: Enhancing Black-box Large Language Models with Small Domain-Specific Models
Haitao Li, Qingyao Ai, Jia Chen +5
Large Language Models (LLMs) like ChatGPT and GPT-4 are versatile and capable of addressing a diverse range of tasks. However, general LLMs, which are developed on open-domain data…
Scaling Laws For Dense Retrieval
Yan Fang, Jingtao Zhan, Qingyao Ai +4
Scaling up neural models has yielded significant advancements in a wide array of tasks, particularly in language generation. Previous studies have found that the performance of neu…
Generalizing Reward Modeling for Out-of-Distribution Preference Learning
Chen Jia
Preference learning (PL) with large language models (LLMs) aims to align the LLMs' generations with human preferences. Previous work on reinforcement learning from human feedback (…
Wikiformer: Pre-training with Structured Information of Wikipedia for Ad-hoc Retrieval
Weihang Su, Qingyao Ai, Xiangsheng Li +4
With the development of deep learning and natural language processing techniques, pre-trained language models have been widely used to solve information retrieval (IR) problems. Be…