430 citations · 478 across the 26 of their papers we have counts for
27 papers
TrajLong: Co-Designing Agentic and Long-Context Supervision for Mid-Training
Miao Peng, Qintong Zhang, Nuo Chen +8
LLM agents for coding, search, and workplace tasks increasingly rely on long-context capabilities to effectively aggregate and reason over extended interaction histories. Recent wo…
MedGame: Storytelling Gamification Empowered by Large Language Models for Medical Education
Qian Wu, Xinrong Zhou, Zizhan Ma +8
Large Language Models (LLMs) show promise for medical education, but most existing systems focus on localized interactions such as question answering or single-turn feedback, rathe…
Agentopia: Long-Term Life Simulation and Learning in Agent Societies
Xintao Wang, Sirui Zheng, Hongqiu Wu +10
Humans learn from social life. Simulating this process with LLM-powered agents represents a promising research direction, raising a natural question: whether LLMs can learn from su…
OPEN-THEATRE: An Open-Source Toolkit for LLM-based Interactive Drama
Tianyang Xu, Hongqiu Wu, Weiqi Wu +1
LLM-based Interactive Drama introduces a novel dialogue scenario in which the player immerses into a character and engages in a dramatic story by interacting with LLM agents. Despi…
BriLLM: Brain-inspired Large Language Model
Hai Zhao, Hongqiu Wu, Dongjie Yang +2
We introduce BriLLM, a brain-inspired large language model that fundamentally redefines the foundations of machine learning through its implementation of Signal Fully-connected flo…
Towards Enhanced Immersion and Agency for LLM-based Interactive Drama
Hongqiu Wu, Weiqi Wu, Tianyang Xu +2
LLM-based Interactive Drama is a novel AI-based dialogue scenario, where the user (i.e. the player) plays the role of a character in the story, has conversations with characters pl…
A Coin Has Two Sides: A Novel Detector-Corrector Framework for Chinese Spelling Correction
Xiangke Zeng, Zuchao Li, Lefei Zhang +3
Chinese Spelling Correction (CSC) stands as a foundational Natural Language Processing (NLP) task, which primarily focuses on the correction of erroneous characters in Chinese text…
X-TURING: Towards an Enhanced and Efficient Turing Test for Long-Term Dialogue Agents
Weiqi Wu, Hongqiu Wu, Hai Zhao
The Turing test examines whether AIs exhibit human-like behaviour in natural language conversations. The traditional setting limits each participant to one message at a time and re…
Game Development as Human-LLM Interaction
Jiale Hong, Hongqiu Wu, Hai Zhao
Game development is a highly specialized task that relies on a complex game engine powered by complex programming languages, preventing many gaming enthusiasts from handling it. Th…
Open Role-Playing with Delta-Engines
Hongqiu Wu, Zekai Xu, Tianyang Xu +5
Game roles can be reflections of personas from a parallel world. In this paper, we propose a new style of game-play to bridge self-expression and role-playing: \emph{open role-play…
From Role-Play to Drama-Interaction: An LLM Solution
Weiqi Wu, Hongqiu Wu, Lai Jiang +4
Drama is a form of storytelling inspired by human creativity, proceeding with a predefined storyline, carrying emotions and thoughts. This paper introduces \emph{LLM-based interact…
Instruction-Driven Game Engines on Large Language Models
Hongqiu Wu, Yan Wang, Xingyuan Liu +2
The Instruction-Driven Game Engine (IDGE) project aims to democratize game development by enabling a large language model (LLM) to follow free-form game rules and autonomously gene…
Unveiling Vulnerability of Self-Attention
Khai Jiet Liong, Hongqiu Wu, Hai Zhao
Pre-trained language models (PLMs) are shown to be vulnerable to minor word changes, which poses a big threat to real-world systems. While previous studies directly focus on manipu…
Episodic Return Decomposition by Difference of Implicitly Assigned Sub-Trajectory Reward
Haoxin Lin, Hongqiu Wu, Jiaji Zhang +3
Real-world decision-making problems are usually accompanied by delayed rewards, which affects the sample efficiency of Reinforcement Learning, especially in the extremely delayed c…
Empower Nested Boolean Logic via Self-Supervised Curriculum Learning
Hongqiu Wu, Linfeng Liu, Hai Zhao +1
Beyond the great cognitive powers showcased by language models, it is crucial to scrutinize whether their reasoning capabilities stem from strong generalization or merely exposure…
Chinese Spelling Correction as Rephrasing Language Model
Linfeng Liu, Hongqiu Wu, Hai Zhao
This paper studies Chinese Spelling Correction (CSC), which aims to detect and correct the potential spelling errors in a given sentence. Current state-of-the-art methods regard CS…
Rethinking Masked Language Modeling for Chinese Spelling Correction
Hongqiu Wu, Shaohua Zhang, Yuchen Zhang +1
In this paper, we study Chinese Spelling Correction (CSC) as a joint decision made by two separate models: a language model and an error model. Through empirical analysis, we find…
Attack Named Entity Recognition by Entity Boundary Interference
Yifei Yang, Hongqiu Wu, Hai Zhao
Named Entity Recognition (NER) is a cornerstone NLP task while its robustness has been given little attention. This paper rethinks the principles of NER attacks derived from senten…
Toward Adversarial Training on Contextualized Language Representation
Hongqiu Wu, Yongxiang Liu, Hanwen Shi +2
Beyond the success story of adversarial training (AT) in the recent text domain on top of pre-trained language models (PLMs), our empirical study showcases the inconsistent gains f…
Forging Multiple Training Objectives for Pre-trained Language Models via Meta-Learning
Hongqiu Wu, Ruixue Ding, Hai Zhao +4
Multiple pre-training objectives fill the vacancy of the understanding capability of single-objective language modeling, which serves the ultimate purpose of pre-trained language m…
Semantic-Preserving Adversarial Code Comprehension
Yiyang Li, Hongqiu Wu, Hai Zhao
Based on the tremendous success of pre-trained language models (PrLMs) for source code comprehension tasks, current literature studies either ways to further improve the performanc…
Adversarial Self-Attention for Language Understanding
Hongqiu Wu, Ruixue Ding, Hai Zhao +3
Deep neural models (e.g. Transformer) naturally learn spurious features, which create a ``shortcut'' between the labels and inputs, thus impairing the generalization and robustness…
Adversarial Counterfactual Environment Model Learning
Xiong-Hui Chen, Yang Yu, Zheng-Mao Zhu +8
A good model for action-effect prediction, named environment model, is important to achieve sample-efficient decision-making policy learning in many domains like robot control, rec…
Not All Attention Is All You Need
Hongqiu Wu, Hai Zhao, Min Zhang
Beyond the success story of pre-trained language models (PrLMs) in recent natural language processing, they are susceptible to over-fitting due to unusual large model size. To this…