CompeteAI: Understanding the Competition Behaviors in Large Language Model-based Agents
This work studies the competition dynamics among LLM-based agents, revealing emergent behaviors and strategic patterns in multi-agent systems....
Apr 30, 2024
Prototypical Reward Network for Data-Efficient RLHF
We propose a prototypical reward network that enables data-efficient reinforcement learning from human feedback (RLHF) for large language models....
Jan 1, 2024
MM-SOC: Benchmarking Multimodal Large Language Models in Social Media Platforms
Social media platforms are hubs for multimodal information exchange, encompassing text, images, and videos, making it challenging for machines to comprehensively understand the information. Multimodal...
Jan 1, 2024
Better to Ask in English: Cross-Lingual Evaluation of Large Language Models for Healthcare Queries
We present a framework and benchmark to evaluate LLMs' multilingual capabilities in healthcare queries, revealing significant performance gaps across languages and providing insights for improving hea...
Jan 1, 2024
Semi-Offline Reinforcement Learning for Optimized Text Generation
We propose a semi-offline reinforcement learning approach for optimizing text generation in language models, balancing exploration and exploitation effectively....
May 1, 2023
Code Recommendation for Open Source Project Developers
CODER is a graph-based code recommendation framework for open source developers, modeling heterogeneous OSS contribution networks to deliver multi-modal recommendations across realistic workloads.
Apr 30, 2023
Prototypical Fine-Tuning: Towards Robust Performance under Varying Data Sizes
We propose prototypical fine-tuning, a novel framework for fine-tuning pretrained language models that maintains robust performance across varying data sizes.
Jan 1, 2023
Predicting Information Pathways Across Online Communities
We develop methods to predict how information spreads across different online communities, revealing patterns in cross-platform information diffusion....
Jan 1, 2023
Reinforcement Subgraph Reasoning for Fake News Detection
A novel subgraph reasoning paradigm for fake news detection that provides explainability while improving generalization through reinforcement learning and hierarchical graph attention networks.
Jun 1, 2022
Towards Fine-Grained Reasoning for Fake News Detection
We propose a fine-grained reasoning framework for fake news detection by following the human information-processing model and designing a prior-aware bi-channel kernel graph network....
Jan 1, 2022