2 citations · 9 across the 13 of their papers we have counts for
8 papers · 1 filter
DialGuide: Aligning Dialogue Model Behavior with Developer Guidelines
Prakhar Gupta, Yang Liu, Di Jin +6
Dialogue models are able to generate coherent and fluent responses, but they can still be challenging to control and may produce non-engaging, unsafe results. This unpredictability…
Inducer-tuning: Connecting Prefix-tuning and Adapter-tuning
Yifan Chen, Devamanyu Hazarika, Mahdi Namazifar +3
Prefix-tuning, or more generally continuous prompt tuning, has become an essential paradigm of parameter-efficient transfer learning. Using a large pre-trained language model (PLM)…
Improving Bot Response Contradiction Detection via Utterance Rewriting
Di Jin, Sijia Liu, Yang Liu +1
Though chatbots based on large neural models can often produce fluent responses in open domain conversations, one salient error type is contradiction or inconsistency with the prec…
Enhanced Knowledge Selection for Grounded Dialogues via Document Semantic Graphs
Sha Li, Mahdi Namazifar, Di Jin +4
Providing conversation models with background knowledge has been shown to make open-domain dialogues more informative and engaging. Existing models treat knowledge selection as a s…
Calibrate and Debias Layer-wise Sampling for Graph Convolutional Networks
Yifan Chen, Tianning Xu, Dilek Hakkani-Tur +3
Multiple sampling-based methods have been developed for approximating and accelerating node embedding aggregation in graph convolutional networks (GCNs) training. Among them, a lay…
On the Limits of Evaluating Embodied Agent Model Generalization Using Validation Sets
Hyounghun Kim, Aishwarya Padmakumar, Di Jin +2
Natural language guided embodied task completion is a challenging problem since it requires understanding natural language instructions, aligning them with egocentric visual observ…
Empowering parameter-efficient transfer learning by recognizing the kernel structure in self-attention
Yifan Chen, Devamanyu Hazarika, Mahdi Namazifar +3
The massive amount of trainable parameters in the pre-trained language models (PLMs) makes them hard to be deployed to multiple downstream tasks. To address this issue, parameter-e…
Towards Textual Out-of-Domain Detection without In-Domain Labels
Di Jin, Shuyang Gao, Seokhwan Kim +2
In many real-world settings, machine learning models need to identify user inputs that are out-of-domain (OOD) so as to avoid performing wrong actions. This work focuses on a chall…