Search Results for author: Ziming Li

Found 17 papers, 11 papers with code

MedAgents: Large Language Models as Collaborators for Zero-shot Medical Reasoning

1 code implementation16 Nov 2023 Xiangru Tang, Anni Zou, Zhuosheng Zhang, Ziming Li, Yilun Zhao, Xingyao Zhang, Arman Cohan, Mark Gerstein

Large language models (LLMs), despite their remarkable progress across various general domains, encounter significant barriers in medicine and healthcare.

Improving Response Quality with Backward Reasoning in Open-domain Dialogue Systems

1 code implementation30 Apr 2021 Ziming Li, Julia Kiseleva, Maarten de Rijke

The proposed backward reasoning step pushes the model to produce more informative and coherent content because the forward generation step's output is used to infer the dialogue context in the backward direction.

Response Generation

DEUS: A Data-driven Approach to Estimate User Satisfaction in Multi-turn Dialogues

no code implementations1 Mar 2021 Ziming Li, Dookun Park, Julia Kiseleva, Young-Bum Kim, Sungjin Lee

Digital assistants are experiencing rapid growth due to their ability to assist users with day-to-day tasks where most dialogues are happening multi-turn.

Optimizing Interactive Systems via Data-Driven Objectives

no code implementations19 Jun 2020 Ziming Li, Julia Kiseleva, Alekh Agarwal, Maarten de Rijke, Ryen W. White

Effective optimization is essential for real-world interactive systems to provide a satisfactory user experience in response to changing user behavior.

Guided Dialog Policy Learning without Adversarial Learning in the Loop

1 code implementation7 Apr 2020 Ziming Li, Sungjin Lee, Baolin Peng, Jinchao Li, Julia Kiseleva, Maarten de Rijke, Shahin Shayandeh, Jianfeng Gao

Reinforcement Learning (RL) methods have emerged as a popular choice for training an efficient and effective dialogue policy.

Reinforcement Learning (RL)

An Additive Decomposition in S-Primitive Towers

1 code implementation6 Feb 2020 Hao Du, Jing Guo, Ziming Li, Elaine Wong

We consider the additive decomposition problem in primitive towers and present an algorithm to decompose a function in an S-primitive tower as a sum of a derivative in the tower and a remainder which is minimal in some sense.

Symbolic Computation

Dialogue Generation: From Imitation Learning to Inverse Reinforcement Learning

1 code implementation9 Dec 2018 Ziming Li, Julia Kiseleva, Maarten de Rijke

The performance of adversarial dialogue generation models relies on the quality of the reward signal produced by the discriminator.

Dialogue Generation Imitation Learning +2

Learning Data-Driven Objectives to Optimize Interactive Systems

no code implementations17 Feb 2018 Ziming Li, Julia Kiseleva, Alekh Agarwal, Maarten de Rijke

Effective optimization is essential for interactive systems to provide a satisfactory user experience.

Additive Decompositions in Primitive Extensions

1 code implementation7 Feb 2018 Shaoshi Chen, Hao Du, Ziming Li

This paper extends the classical Ostrogradsky-Hermite reduction for rational functions to more general functions in primitive extensions of certain types.

Symbolic Computation 33F10, 68W30, 12H05

Hermite Reduction and Creative Telescoping for Hyperexponential Functions

1 code implementation21 Jan 2013 Alin Bostan, Shaoshi Chen, Frédéric Chyzak, Ziming Li, Guoce Xin

Based on this reduction algorithm, we design a new method to compute minimal telescopers for bivariate hyperexponential functions.

Symbolic Computation Combinatorics 33F10

Cannot find the paper you are looking for? You can Submit a new open access paper.