9 papers
PolyAlign: Conditional Human-Distribution Alignment
L. D. M. S. Sai Teja, Ufaq Khan, Sathira Silva +2
Post-training methods such as supervised fine-tuning (SFT) and preference optimization typically align language models toward a single global assistant behavior. While effective fo…
Bridging Scale Discrepancies in Robotic Control via Language-Based Action Representations
Yuchi Zhang, Churui Sun, Shiqi Liang +4
Recent end-to-end robotic manipulation research increasingly adopts architectures inspired by large language models to enable robust manipulation. However, a critical challenge ari…
Unstructured Text Enhanced Open-domain Dialogue System: A Systematic Survey
Longxuan Ma, Mingda Li, Weinan Zhang +2
Incorporating external knowledge into dialogue generation has been proven to benefit the performance of an open-domain Dialogue System (DS), such as generating informative or styli…
A Static and Dynamic Attention Framework for Multi Turn Dialogue Generation
Wei-Nan Zhang, Yiming Cui, Kaiyan Zhang +4
Recently, research on open domain dialogue systems have attracted extensive interests of academic and industrial researchers. The goal of an open domain dialogue system is to imita…
Visualizing attention zones in machine reading comprehension models
Yiming Cui, Wei-Nan Zhang, Ting Liu
The attention mechanism plays an important role in the machine reading comprehension (MRC) model. Here, we describe a pipeline for building an MRC model with a pretrained language…
Multilingual Multi-Aspect Explainability Analyses on Machine Reading Comprehension Models
Yiming Cui, Wei-Nan Zhang, Wanxiang Che +3
Achieving human-level performance on some of the Machine Reading Comprehension (MRC) datasets is no longer challenging with the help of powerful Pre-trained Language Models (PLMs).…