76 citations · 128 across the 17 of their papers we have counts for
17 papers
GradCuit: Credit-Assigned Gradient Flow Enables Robust and Interpretable Test-Time Latent Reasoning
Zhaoxin Yu, Qi Shen, Hengli Li +4
Optimization-based latent reasoning improves large language model outputs by optimizing instance-specific continuous states at test time while keeping model parameters frozen. Exis…
PILA: Plug-and-Play Insertion for LLM-native Advertising
Zhaowei Zhang, Yuhan Fu, Yihang Zhang +6
How to monetize large language models (LLMs) by naturally integrating sponsored content into their responses, known as LLM-native advertising, has recently emerged as a critical pr…
LLMs Know More Than Words: A Genre Study with Syntax, Metaphor & Phonetics
Weiye Shi, Zhaowei Zhang, Shaoheng Yan +1
Large language models (LLMs) demonstrate remarkable potential across diverse language related tasks, yet whether they capture deeper linguistic properties, such as syntactic struct…
PoliCon: Evaluating LLMs on Achieving Diverse Political Consensus Objectives
Zhaowei Zhang, Xiaobo Wang, Minghua Yi +5
Achieving political consensus is crucial yet challenging for the effective functioning of social governance. However, although frontier AI systems represented by large language mod…
Amulet: ReAlignment During Test Time for Personalized Preference Adaptation of LLMs
Zhaowei Zhang, Fengshuo Bai, Qizhi Chen +5
How to align large language models (LLMs) with user preferences from a static general dataset has been frequently studied. However, user preferences are usually personalized, chang…
Magnetic Preference Optimization: Achieving Last-iterate Convergence for Language Model Alignment
Mingzhi Wang, Chengdong Ma, Qizhi Chen +7
Self-play methods have demonstrated remarkable success in enhancing model capabilities across various domains. In the context of Reinforcement Learning from Human Feedback (RLHF),…
Efficient Model-agnostic Alignment via Bayesian Persuasion
Fengshuo Bai, Mingzhi Wang, Zhaowei Zhang +4
With recent advancements in large language models (LLMs), alignment has emerged as an effective technique for keeping LLMs consensus with human intent. Current methods primarily in…
Roadmap on Incentive Compatibility for AI Alignment and Governance in Sociotechnical Systems
Zhaowei Zhang, Fengshuo Bai, Mingzhi Wang +3
The burgeoning integration of artificial intelligence (AI) into human society brings forth significant implications for societal governance and safety. While considerable strides h…
CivRealm: A Learning and Reasoning Odyssey in Civilization for Decision-Making Agents
Siyuan Qi, Shuo Chen, Yexin Li +11
The generalization of decision-making agents encompasses two fundamental elements: learning from past experiences and reasoning in novel contexts. However, the predominant emphasis…
AI Alignment: A Comprehensive Survey
Jiaming Ji, Tianyi Qiu, Boyuan Chen +23
AI alignment aims to make AI systems behave in line with human intentions and values. As AI systems grow more capable, so do risks from misalignment. To provide a comprehensive and…
ValueDCG: Measuring Comprehensive Human Value Understanding Ability of Language Models
Zhaowei Zhang, Fengshuo Bai, Jun Gao +1
Personal values are a crucial factor behind human decision-making. Considering that Large Language Models (LLMs) have been shown to impact human decisions significantly, it is esse…
ProAgent: Building Proactive Cooperative Agents with Large Language Models
Ceyao Zhang, Kaijie Yang, Siyi Hu +12
Building agents with adaptive behavior in cooperative tasks stands as a paramount goal in the realm of multi-agent systems. Current approaches to developing cooperative agents rely…
Heterogeneous Value Alignment Evaluation for Large Language Models
Zhaowei Zhang, Ceyao Zhang, Nian Liu +5
The emergent capabilities of Large Language Models (LLMs) have made it crucial to align their values with those of humans. However, current methodologies typically attempt to assig…
STAS: Spatial-Temporal Return Decomposition for Multi-agent Reinforcement Learning
Sirui Chen, Zhaowei Zhang, Yaodong Yang +1
Centralized Training with Decentralized Execution (CTDE) has been proven to be an effective paradigm in cooperative multi-agent reinforcement learning (MARL). One of the major chal…
Contextual Transformer for Offline Meta Reinforcement Learning
Runji Lin, Ye Li, Xidong Feng +6
The pretrain-finetuning paradigm in large-scale sequence models has made significant progress in natural language processing and computer vision tasks. However, such a paradigm is…
Continuous Decomposition of Granularity for Neural Paraphrase Generation
Xiaodong Gu, Zhaowei Zhang, Sang-Woo Lee +2
While Transformers have had significant success in paragraph generation, they treat sentences as linear sequences of tokens and often neglect their hierarchical information. Prior…
Diet Code Is Healthy: Simplifying Programs for Pre-trained Models of Code
Zhaowei Zhang, Hongyu Zhang, Beijun Shen +1
Pre-trained code representation models such as CodeBERT have demonstrated superior performance in a variety of software engineering tasks, yet they are often heavy in complexity, q…