44 citations · 71 across the 15 of their papers we have counts for
12 papers · 1 filter
Mitigating Context Interference for Reliable and Efficient Search Agents
Boyang Xue, Bin Wu, Shuofei Qiao +8
Recent research empowers Large Language Models (LLMs) as multi-turn search agents to iteratively retrieve and generate outputs until complex tasks are solved. However, the contexts…
Instruction Tuning With Loss Over Instructions
Zhengyan Shi, Adam X. Yang, Bin Wu +3
Instruction tuning plays a crucial role in shaping the outputs of language models (LMs) to desired styles. In this work, we propose a simple yet effective method, Instruction Model…
Lexical Entrainment for Conversational Systems
Zhengxiang Shi, Procheta Sen, Aldo Lipani
Conversational agents have become ubiquitous in assisting with daily tasks, and are expected to possess human-like features. One such feature is lexical entrainment (LE), a phenome…
DePT: Decomposed Prompt Tuning for Parameter-Efficient Fine-tuning
Zhengxiang Shi, Aldo Lipani
Prompt tuning (PT), where a small amount of trainable soft (continuous) prompt vectors is affixed to the input of language models (LM), has shown promising results across various t…
Rethink the Effectiveness of Text Data Augmentation: An Empirical Analysis
Zhengxiang Shi, Aldo Lipani
In recent years, language models (LMs) have made remarkable progress in advancing the field of natural language processing (NLP). However, the impact of data augmentation (DA) tech…
Towards Asking Clarification Questions for Information Seeking on Task-Oriented Dialogues
Yue Feng, Hossein A. Rahmani, Aldo Lipani +1
Task-oriented dialogue systems aim at providing users with task-specific services. Users of such systems often do not know all the information about the task they are trying to acc…
When and What to Ask Through World States and Text Instructions: IGLU NLP Challenge Solution
Zhengxiang Shi, Jerome Ramos, To Eun Kim +3
In collaborative tasks, effective communication is crucial for achieving joint goals. One such task is collaborative building where builders must communicate with each other to con…
Don't Stop Pretraining? Make Prompt-based Fine-tuning Powerful Learner
Zhengxiang Shi, Aldo Lipani
Language models (LMs) trained on vast quantities of unlabelled data have greatly advanced the field of natural language processing (NLP). In this study, we re-visit the widely acce…
Attention-based Ingredient Phrase Parser
Zhengxiang Shi, Pin Ni, Meihui Wang +2
As virtual personal assistants have now penetrated the consumer market, with products such as Siri and Alexa, the research community has produced several works on task-oriented dia…
Learning to Execute Actions or Ask Clarification Questions
Zhengxiang Shi, Yue Feng, Aldo Lipani
Collaborative tasks are ubiquitous activities where a form of communication is required in order to reach a joint goal. Collaborative building is one of such tasks. We wish to deve…
StepGame: A New Benchmark for Robust Multi-Hop Spatial Reasoning in Texts
Zhengxiang Shi, Qiang Zhang, Aldo Lipani
Inferring spatial relations in natural language is a crucial ability an intelligent system should possess. The bAbI dataset tries to capture tasks relevant to this domain (task 17…
Dynamic Schema Graph Fusion Network for Multi-Domain Dialogue State Tracking
Yue Feng, Aldo Lipani, Fanghua Ye +2
Dialogue State Tracking (DST) aims to keep track of users' intentions during the course of a conversation. In DST, modelling the relations among domains and slots is still an under…