1 code implementation • 1 Feb 2024 • Weijie Xu, Zicheng Huang, Wenxiang Hu, Xi Fang, Rajesh Kumar Cherukuri, Naumaan Nayyar, Lorenzo Malandri, Srinivasan H. Sengamedu
The data generation pipeline is transferable and can be easily adapted for labeled conversation data generation in other domains.
no code implementations • 28 Oct 2023 • Yixin Wan, Fanyou Wu, Weijie Xu, Srinivasan H. Sengamedu
We explore the correlation between the level of hallucination in model responses and two types of sequence-level certainty: probabilistic certainty and semantic certainty.
1 code implementation • 3 Jul 2023 • Weijie Xu, Xiaoyu Jiang, Srinivasan H. Sengamedu, Francis Iannacci, Jinjin Zhao
Recently, Neural Topic Models (NTM), inspired by variational autoencoders, have attracted a lot of research interest; however, these methods have limited applications in the real world due to the challenge of incorporating human knowledge.
Ranked #1 on Topic Models on 20NewsGroups
no code implementations • 10 Sep 2022 • Neela Sawant, Srinivasan H. Sengamedu
This is a zero-shot evaluation as none of the policies occur in the training set.
no code implementations • 29 Sep 2021 • Thanh V Nguyen, Srinivasan H. Sengamedu
We evaluate GRAPHIX on the Patches in The Wild Java benchmark, using both abstract and concrete code.
no code implementations • 11 Apr 2018 • Anil R. Yelundur, Srinivasan H. Sengamedu, Bamdev Mishra
In addition, we use Polya-Gamma data augmentation for the semi-supervised Bayesian tensor decomposition.