7 papers
Are Akpans Trick or Treat: Unveiling Helpful Biases in Assistant Systems
Jiao Sun, Yu Hou, Jiin Kim +1
Information-seeking AI assistant systems aim to answer users' queries about knowledge in a timely manner. However, both the human-perceived helpfulness of information-seeking assis…
Learning Action Conditions from Instructional Manuals for Instruction Understanding
Te-Lin Wu, Caiqi Zhang, Qingyuan Hu +2
The ability to infer pre- and postconditions of an action is vital for comprehending complex instructions, and is essential for applications such as autonomous instruction-guided a…
Open-Domain Text Evaluation via Contrastive Distribution Methods
Sidi Lu, Hongyi Liu, Asli Celikyilmaz +2
Recent advancements in open-domain text generation, driven by the power of large pre-trained language models (LLMs), have demonstrated remarkable performance. However, assessing th…
DiNADO: Norm-Disentangled Neurally-Decomposed Oracles for Controlling Language Models
Sidi Lu, Wenbo Zhao, Chenyang Tao +4
NeurAlly-Decomposed Oracle (NADO) is a powerful approach for controllable generation with large language models. It is designed to avoid catastrophic forgetting while achieving gua…
RLCD: Reinforcement Learning from Contrastive Distillation for Language Model Alignment
Kevin Yang, Dan Klein, Asli Celikyilmaz +2
We propose Reinforcement Learning from Contrastive Distillation (RLCD), a method for aligning language models to follow principles expressed in natural language (e.g., to be more h…
STAR: Boosting Low-Resource Information Extraction by Structure-to-Text Data Generation with Large Language Models
Mingyu Derek Ma, Xiaoxuan Wang, Po-Nien Kung +3
Information extraction tasks such as event extraction require an in-depth understanding of the output structure and sub-task dependencies. They heavily rely on task-specific traini…