Multi-view Content-aware Indexing for Long Document Retrieval

no code implementations • 23 Apr 2024 • Kuicai Dong, Derrick Goh Xin Deik, Yi Quan Lee, Hao Zhang, Xiangyang Li, Cong Zhang, Yong liu

As they do not consider content structures, the resultant chunks can exclude vital information or include irrelevant content.

Chunking Question Answering +1

Aligning Crowd Feedback via Distributional Preference Reward Modeling

no code implementations • 15 Feb 2024 • Dexun Li, Cong Zhang, Kuicai Dong, Derrick Goh Xin Deik, Ruiming Tang, Yong liu

In this paper, we introduce the Distributional Preference Reward Model (DPRM), a simple yet effective framework to align large language models with a diverse set of human preferences.

Automatic Unit Test Data Generation and Actor-Critic Reinforcement Learning for Code Synthesis

1 code implementation • 20 Oct 2023 • Philip John Gorinski, Matthieu Zimmer, Gerasimos Lampouras, Derrick Goh Xin Deik, Ignacio Iacobacci

The advent of large pre-trained language models in the domain of Code Synthesis has shown remarkable performance on various benchmarks, treating the problem of Code Generation in a fashion similar to Natural Language Generation, trained with a Language Modelling (LM) objective.

Code Generation Language Modelling +2