164 citations · 488 across the 38 of their papers we have counts for
22 papers · 1 filter
Unifying Language Agent Algorithms with Graph-based Orchestration Engine for Reproducible Agent Research
Qianqian Zhang, Jiajia Liao, Heting Ying +9
Language agents powered by large language models (LLMs) have demonstrated remarkable capabilities in understanding, reasoning, and executing complex tasks. However, developing robu…
The Self-Improvement Paradox: Can Language Models Bootstrap Reasoning Capabilities without External Scaffolding?
Yutao Sun, Mingshuai Chen, Tiancheng Zhao +3
Self-improving large language models (LLMs) -- i.e., to improve the performance of an LLM by fine-tuning it with synthetic data generated by itself -- is a promising way to advance…
Preserving Knowledge in Large Language Model with Model-Agnostic Self-Decompression
Zilun Zhang, Yutao Sun, Tiancheng Zhao +4
Humans can retain old knowledge while learning new information, but Large Language Models (LLMs) often suffer from catastrophic forgetting when post-pretrained or supervised fine-t…
SF-QA: Simple and Fair Evaluation Library for Open-domain Question Answering
Xiaopeng Lu, Kyusong Lee, Tiancheng Zhao
Although open-domain question answering (QA) draws great attention in recent years, it requires large amounts of resources for building the full system and is often difficult to re…
SPARTA: Efficient Open-Domain Question Answering via Sparse Transformer Matching Retrieval
Tiancheng Zhao, Xiaopeng Lu, Kyusong Lee
We introduce SPARTA, a novel neural retrieval method that shows great promise in performance, generalization, and interpretability for open-domain question answering. Unlike many n…
Report from the NSF Future Directions Workshop, Toward User-Oriented Agents: Research Directions and Challenges
Maxine Eskenazi, Tiancheng Zhao
This USER Workshop was convened with the goal of defining future research directions for the burgeoning intelligent agent research community and to communicate them to the National…
Talk to Papers: Bringing Neural Question Answering to Academic Search
Tianchang Zhao, Kyusong Lee
We introduce Talk to Papers, which exploits the recent open-domain question answering (QA) techniques to improve the current experience of academic search. It's designed to enable…
"None of the Above":Measure Uncertainty in Dialog Response Retrieval
Yulan Feng, Shikib Mehri, Maxine Eskenazi +1
This paper discusses the importance of uncovering uncertainty in end-to-end dialog tasks, and presents our experimental results on uncertainty classification on the Ubuntu Dialog C…
Investigating Evaluation of Open-Domain Dialogue Systems With Human Generated Multiple References
Prakhar Gupta, Shikib Mehri, Tiancheng Zhao +3
The aim of this paper is to mitigate the shortcomings of automatic evaluation of open-domain dialog systems through multi-reference evaluation. Existing metrics have been shown to…
Pretraining Methods for Dialog Context Representation Learning
Shikib Mehri, Evgeniia Razumovskaia, Tiancheng Zhao +1
This paper examines various unsupervised pretraining objectives for learning dialog context representations. Two novel methods of pretraining dialog context encoders are proposed,…
Target-Guided Open-Domain Conversation
Jianheng Tang, Tiancheng Zhao, Chenyan Xiong +3
Many real-world open-domain conversation applications have specific goals to achieve during open-ended chats, such as recommendation, psychotherapy, education, etc. We study the pr…
Unsupervised Dialog Structure Learning
Weiyan Shi, Tiancheng Zhao, Zhou Yu
Learning a shared dialog structure from a set of task-oriented dialogs is an important challenge in computational linguistics. The learned dialog structure can shed light on how to…
Rethinking Action Spaces for Reinforcement Learning in End-to-end Dialog Agents with Latent Variable Models
Tiancheng Zhao, Kaige Xie, Maxine Eskenazi
Defining action spaces for conversational agents and optimizing their decision-making process with reinforcement learning is an enduring challenge. Common practice has been to use…
Beyond Turing: Intelligent Agents Centered on the User
Maxine Eskenazi, Shikib Mehri, Evgeniia Razumovskaia +1
Most research on intelligent agents centers on the agent and not on the user. We look at the origins of agent-centric research for slot-filling, gaming and chatbot agents. We then…
Dirichlet Variational Autoencoder for Text Modeling
Yijun Xiao, Tiancheng Zhao, William Yang Wang
We introduce an improved variational autoencoder (VAE) for text modeling with topic information explicitly modeled as a Dirichlet latent variable. By providing the proposed model t…
Texar: A Modularized, Versatile, and Extensible Toolkit for Text Generation
Zhiting Hu, Haoran Shi, Bowen Tan +12
We introduce Texar, an open-source toolkit aiming to support the broad set of text generation tasks that transform any inputs into natural language, such as machine translation, su…
Zero-Shot Dialog Generation with Cross-Domain Latent Actions
Tiancheng Zhao, Maxine Eskenazi
This paper introduces zero-shot dialog generation (ZSDG), as a step towards neural dialog systems that can instantly generalize to new situations with minimal data. ZSDG enables an…
Multimodal Hierarchical Reinforcement Learning Policy for Task-Oriented Visual Dialog
Jiaping Zhang, Tiancheng Zhao, Zhou Yu
Creating an intelligent conversational system that understands vision and language is one of the ultimate goals in Artificial Intelligence (AI)~\cite{winograd1972understanding}. Ex…
Unsupervised Discrete Sentence Representation Learning for Interpretable Neural Dialog Generation
Tiancheng Zhao, Kyusong Lee, Maxine Eskenazi
The encoder-decoder dialog model is one of the most prominent methods used to build dialog systems in complex domains. Yet it is limited because it cannot output interpretable acti…
Generative Encoder-Decoder Models for Task-Oriented Spoken Dialog Systems with Chatting Capability
Tiancheng Zhao, Allen Lu, Kyusong Lee +1
Generative encoder-decoder models offer great promise in developing domain-general dialog systems. However, they have mainly been applied to open-domain conversations. This paper p…
Learning Discourse-level Diversity for Neural Dialog Models using Conditional Variational Autoencoders
Tiancheng Zhao, Ran Zhao, Maxine Eskenazi
While recent neural encoder-decoder models have shown great promise in modeling open-domain conversations, they often generate dull and generic responses. Unlike past work that has…
Leveraging Recurrent Neural Networks for Multimodal Recognition of Social Norm Violation in Dialog
Tiancheng Zhao, Ran Zhao, Zhao Meng +1
Social norms are shared rules that govern and facilitate social interaction. Violating such social norms via teasing and insults may serve to upend power imbalances or, on the cont…