76 citations · 152 across the 39 of their papers we have counts for
45 papers
A Blind Spot in Alignment: Quantifying Biosecurity Risks in Large Language Models
Shu Quan, Tianfang Hao, Sitong Fang +8
Large Language Models (LLMs) are accelerating biological research, yet this same capability poses a critical biosecurity threat: models that assist in protein engineering can equal…
SPADE-Bench: Evaluating Spontaneous Strategic Deception in Agents via Plan-Action Divergence
Yuyan Bu, Haowei Li, Qirui Zheng +7
As LLM-based agents expand their operational scope, reliability becomes a prerequisite for real-world deployment. However, in practical applications, human users cannot monitor eve…
SafeMCP: Proactive Power Regulation for LLM Agent Defense via Environment-Grounded Look-Ahead Reasoning
Lichao Wang, Zhaoxing Ren, Tianzhuo Yang +4
As Large Language Model (LLM) agents increasingly leverage the Model Context Protocol (MCP) to operate in complex environments, the expansion of their action spaces offers agents u…
Stable Reasoning, Unstable Responses: Mitigating LLM Deception via Stability Asymmetry
Guoxi Zhang, Jiawei Chen, Tianzhuo Yang +4
As Large Language Models (LLMs) expand in capability and application scope, their trustworthiness becomes critical. A vital risk is intrinsic deception, wherein models strategicall…
Align Once, Benefit Multilingually: Enforcing Multilingual Consistency for LLM Safety Alignment
Yuyan Bu, Xiaohao Liu, ZhaoXing Ren +2
The widespread deployment of large language models (LLMs) across linguistic communities necessitates reliable multilingual safety alignment. However, recent efforts to extend align…
FormalJudge: A Neuro-Symbolic Paradigm for Agentic Oversight
Jiayi Zhou, Yang Sheng, Hantao Lou +2
As LLM-based agents increasingly operate in high-stakes domains with real-world consequences, ensuring their behavioral safety becomes paramount. The dominant oversight paradigm, L…
Enhance the Safety in Reinforcement Learning by ADRC Lagrangian Methods
Mingxu Zhang, Huicheng Zhang, Jiaming Ji +2
Safe reinforcement learning (Safe RL) seeks to maximize rewards while satisfying safety constraints, typically addressed through Lagrangian-based methods. However, existing approac…
Your Group-Relative Advantage Is Biased
Fengkai Yang, Zherui Chen, Xiaohan Wang +10
Reinforcement Learning from Verifier Rewards (RLVR) has emerged as a widely used approach for post-training large language models on reasoning tasks, with group-based methods such…
SportsGPT: An LLM-driven Framework for Interpretable Sports Motion Assessment and Training Guidance
Wenbo Tian, Ruting Lin, Hongxian Zheng +4
Existing intelligent sports analysis systems mainly focus on "scoring and visualization," often lacking automatic performance diagnosis and interpretable training guidance. Recent…
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…
Are Your Agents Upward Deceivers?
Dadi Guo, Qingyu Liu, Dongrui Liu +13
Large Language Model (LLM)-based agents are increasingly used as autonomous subordinates that carry out tasks for users. This raises the question of whether they may also engage in…
AI Deception: Risks, Dynamics, and Controls
Boyuan Chen, Sitong Fang, Jiaming Ji +56
As intelligence increases, so does its shadow. AI deception, in which systems induce false beliefs to secure self-beneficial outcomes, has evolved from a speculative concern to an…
VLA-Arena: An Open-Source Framework for Benchmarking Vision-Language-Action Models
Borong Zhang, Jiahao Li, Jiachen Shen +8
While Vision-Language-Action models (VLAs) are rapidly advancing toward generalist robot policies, quantitatively characterizing their capability boundaries and failure modes remai…
Debate with Images: Detecting Deceptive Behaviors in Multimodal Large Language Models
Sitong Fang, Shiyi Hou, Kaile Wang +6
Are frontier AI systems becoming more capable? Certainly. Yet such progress is not an unalloyed blessing but rather a Trojan horse: behind their performance leaps lie more insidiou…
SafeEditor: Unified MLLM for Efficient Post-hoc T2I Safety Editing
Ruiyang Zhang, Jiahao Luo, Xiaoru Feng +3
With the rapid advancement of text-to-image (T2I) models, ensuring their safety has become increasingly critical. Existing safety approaches can be categorized into training-time a…
SafeMT: Multi-turn Safety for Multimodal Language Models
Han Zhu, Juntao Dai, Jiaming Ji +8
With the widespread use of multi-modal Large Language models (MLLMs), safety issues have become a growing concern. Multi-turn dialogues, which are more common in everyday interacti…
SafeLawBench: Towards Safe Alignment of Large Language Models
Chuxue Cao, Han Zhu, Jiaming Ji +7
With the growing prevalence of large language models (LLMs), the safety of LLMs has raised significant concerns. However, there is still a lack of definitive standards for evaluati…
Mitigating Deceptive Alignment via Self-Monitoring
Jiaming Ji, Wenqi Chen, Kaile Wang +8
Modern large language models rely on chain-of-thought (CoT) reasoning to achieve impressive performance, yet the same mechanism can amplify deceptive alignment, situations in which…
Generative RLHF-V: Learning Principles from Multi-modal Human Preference
Jiayi Zhou, Jiaming Ji, Boyuan Chen +6
Training multi-modal large language models (MLLMs) that align with human intentions is a long-term challenge. Traditional score-only reward models for alignment suffer from low acc…
J1: Exploring Simple Test-Time Scaling for LLM-as-a-Judge
Chi-Min Chan, Chunpu Xu, Jiaming Ji +7
The current focus of AI research is shifting from emphasizing model training towards enhancing evaluation quality, a transition that is crucial for driving further advancements in…
InterMT: Multi-Turn Interleaved Preference Alignment with Human Feedback
Boyuan Chen, Donghai Hong, Jiaming Ji +12
As multimodal large models (MLLMs) continue to advance across challenging tasks, a key question emerges: What essential capabilities are still missing? A critical aspect of human l…
When Slower Isn't Truer: Inverse Scaling Law of Truthfulness in Multimodal Reasoning
Sitong Fang, Wenjing Cao, Jiahao Li +7
Reasoning models have attracted increasing attention for their ability to tackle complex tasks, embodying the System II (slow thinking) paradigm in contrast to System I (fast, intu…
Benchmarking Multi-National Value Alignment for Large Language Models
Weijie Shi, Chengyi Ju, Chengzhong Liu +8
Do Large Language Models (LLMs) hold positions that conflict with your country's values? Occasionally they do! However, existing works primarily focus on ethical reviews, failing t…
Super Co-alignment of Human and AI for Sustainable Symbiotic Society
Yi Zeng, Feifei Zhao, Yuwei Wang +13
As Artificial Intelligence (AI) advances toward Artificial General Intelligence (AGI) and eventually Artificial Superintelligence (ASI), it may potentially surpass human control, d…