Search Results for author: Shao Zhang

Found 15 papers, 5 papers with code

Language Games as the Pathway to Artificial Superhuman Intelligence

no code implementations31 Jan 2025 Ying Wen, Ziyu Wan, Shao Zhang

The evolution of large language models (LLMs) toward artificial superhuman intelligence (ASI) hinges on data reproduction, a cyclical process in which models generate, curate and retrain on novel data to refine capabilities.

Diversity

Aligning Individual and Collective Objectives in Multi-Agent Cooperation

no code implementations19 Feb 2024 Yang Li, WenHao Zhang, Jianhong Wang, Shao Zhang, Yali Du, Ying Wen, Wei Pan

Among the research topics in multi-agent learning, mixed-motive cooperation is one of the most prominent challenges, primarily due to the mismatch between individual and collective goals.

SMAC+ Starcraft +1

Controlling Large Language Model-based Agents for Large-Scale Decision-Making: An Actor-Critic Approach

no code implementations23 Nov 2023 Bin Zhang, Hangyu Mao, Jingqing Ruan, Ying Wen, Yang Li, Shao Zhang, Zhiwei Xu, Dapeng Li, Ziyue Li, Rui Zhao, Lijuan Li, Guoliang Fan

The remarkable progress in Large Language Models (LLMs) opens up new avenues for addressing planning and decision-making problems in Multi-Agent Systems (MAS).

Decision Making Hallucination +4

Human Still Wins over LLM: An Empirical Study of Active Learning on Domain-Specific Annotation Tasks

no code implementations16 Nov 2023 Yuxuan Lu, Bingsheng Yao, Shao Zhang, Yun Wang, Peng Zhang, Tun Lu, Toby Jia-Jun Li, Dakuo Wang

Large Language Models (LLMs) have demonstrated considerable advances, and several claims have been made about their exceeding human performance.

Active Learning

More Samples or More Prompts? Exploring Effective In-Context Sampling for LLM Few-Shot Prompt Engineering

no code implementations16 Nov 2023 Bingsheng Yao, Guiming Chen, Ruishi Zou, Yuxuan Lu, Jiachen Li, Shao Zhang, Yisi Sang, Sijia Liu, James Hendler, Dakuo Wang

While most existing works on LLM prompting techniques focus only on how to select a better set of data samples inside one single prompt input (In-Context Learning or ICL), why can not we design and leverage multiple prompts together to further improve the LLM's performance?

In-Context Learning Prompt Engineering

StorySparkQA: Expert-Annotated QA Pairs with Real-World Knowledge for Children's Story-Based Learning

1 code implementation16 Nov 2023 Jiaju Chen, Yuxuan Lu, Shao Zhang, Bingsheng Yao, Yuanzhe Dong, Ying Xu, Yunyao Li, Qianwen Wang, Dakuo Wang, Yuling Sun

Interactive story reading is a common parent-child activity, where parents expect to teach both language skills and real-world knowledge beyond the story.

Question Answering World Knowledge

ZSC-Eval: An Evaluation Toolkit and Benchmark for Multi-agent Zero-shot Coordination

2 code implementations8 Oct 2023 Xihuai Wang, Shao Zhang, WenHao Zhang, Wentao Dong, Jingxiao Chen, Ying Wen, Weinan Zhang

ZSC-Eval consists of: 1) Generation of evaluation partner candidates through behavior-preferring rewards to approximate deployment-time partners' distribution; 2) Selection of evaluation partners by Best-Response Diversity (BR-Div); 3) Measurement of generalization performance with various evaluation partners via the Best-Response Proximity (BR-Prox) metric.

Diversity Multi-agent Reinforcement Learning

Talk2Care: Facilitating Asynchronous Patient-Provider Communication with Large-Language-Model

no code implementations17 Sep 2023 Ziqi Yang, Xuhai Xu, Bingsheng Yao, Shao Zhang, Ethan Rogers, Stephen Intille, Nawar Shara, Guodong Gordon Gao, Dakuo Wang

(2) For health providers, we built an LLM-based dashboard to summarize and present important health information based on older adults' conversations with the VA. We further conducted two user studies with older adults and providers to evaluate the usability of the system.

Language Modeling Language Modelling +1

Tackling Cooperative Incompatibility for Zero-Shot Human-AI Coordination

1 code implementation5 Jun 2023 Yang Li, Shao Zhang, Jichen Sun, WenHao Zhang, Yali Du, Ying Wen, Xinbing Wang, Wei Pan

In order to solve cooperative incompatibility in learning and effectively address the problem in the context of ZSC, we introduce the Cooperative Open-ended LEarning (COLE) framework, which formulates open-ended objectives in cooperative games with two players using perspectives of graph theory to evaluate and pinpoint the cooperative capacity of each strategy.

AI Agent

Cooperative Open-ended Learning Framework for Zero-shot Coordination

1 code implementation9 Feb 2023 Yang Li, Shao Zhang, Jichen Sun, Yali Du, Ying Wen, Xinbing Wang, Wei Pan

However, these approaches can result in a loss of learning and an inability to cooperate with certain strategies within the population, known as cooperative incompatibility.

Diversity

KnowledgeShovel: An AI-in-the-Loop Document Annotation System for Scientific Knowledge Base Construction

1 code implementation6 Oct 2022 Shao Zhang, Yuting Jia, Hui Xu, Dakuo Wang, Toby Jia-Jun Li, Ying Wen, Xinbing Wang, Chenghu Zhou

Constructing a comprehensive, accurate, and useful scientific knowledge base is crucial for human researchers synthesizing scientific knowledge and for enabling Al-driven scientific discovery.

Knowledge Base Construction scientific discovery

DeepShovel: An Online Collaborative Platform for Data Extraction in Geoscience Literature with AI Assistance

no code implementations21 Feb 2022 Shao Zhang, Yuting Jia, Hui Xu, Ying Wen, Dakuo Wang, Xinbing Wang

Geoscientists, as well as researchers in many fields, need to read a huge amount of literature to locate, extract, and aggregate relevant results and data to enable future research or to build a scientific database, but there is no existing system to support this use case well.

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