58 citations · 112 across the 61 of their papers we have counts for
27 papers · 1 filter
MONICA: Real-Time Monitoring and Calibration of Chain-of-Thought Sycophancy in Large Reasoning Models
Jingyu Hu, Shu Yang, Xilin Gong +3
Large Reasoning Models (LRMs) suffer from sycophantic behavior, where models tend to agree with users' incorrect beliefs and follow misinformation rather than maintain independent…
Investigating CoT Monitorability in Large Reasoning Models
Shu Yang, Junchao Wu, Xilin Gong +4
Large Reasoning Models (LRMs) have demonstrated remarkable performance on complex tasks by engaging in extended reasoning before producing final answers. Beyond improving abilities…
PAHQ: Accelerating Automated Circuit Discovery through Mixed-Precision Inference Optimization
Xinhai Wang, Shu Yang, Liangyu Wang +4
Circuit discovery, which involves identifying sparse and task-relevant subnetworks in pre-trained language models, is a cornerstone of mechanistic interpretability. Automated Circu…
Can AI Truly Represent Your Voice in Deliberations? A Comprehensive Study of Large-Scale Opinion Aggregation with LLMs
Shenzhe Zhu, Shu Yang, Michiel A. Bakker +2
Large-scale public deliberations generate thousands of free-form contributions that must be synthesized into representative and neutral summaries for policy use. While LLMs have be…
Benchmarking and Mitigating Sycophancy in Medical Vision Language Models
Juangui Xu, Zikun Guo, Jingwei Lv +5
Visual language models (VLMs) have the potential to transform medical workflows. However, the deployment is limited by sycophancy. Despite this serious threat to patient safety, a…
RepreGuard: Detecting LLM-Generated Text by Revealing Hidden Representation Patterns
Xin Chen, Junchao Wu, Shu Yang +7
Detecting content generated by large language models (LLMs) is crucial for preventing misuse and building trustworthy AI systems. Although existing detection methods perform well,…
PersRM-R1: Enhance Personalized Reward Modeling with Reinforcement Learning
Mengdi Li, Guanqiao Chen, Xufeng Zhao +3
Reward models (RMs), which are central to existing post-training methods, aim to align LLM outputs with human values by providing feedback signals during fine-tuning. However, exis…
Understanding and Mitigating Political Stance Cross-topic Generalization in Large Language Models
Jiayi Zhang, Shu Yang, Junchao Wu +2
Fine-tuning Large Language Models on a political topic will significantly manipulate their political stance on various issues and unintentionally affect their stance on unrelated t…
When Truth Is Overridden: Uncovering the Internal Origins of Sycophancy in Large Language Models
Keyu Wang, Jin Li, Shu Yang +2
Large Language Models (LLMs) often exhibit sycophantic behavior, agreeing with user-stated opinions even when those contradict factual knowledge. While prior work has documented th…
Is Long-to-Short a Free Lunch? Investigating Inconsistency and Reasoning Efficiency in LRMs
Shu Yang, Junchao Wu, Xuansheng Wu +3
Large Reasoning Models (LRMs) have achieved remarkable performance on complex tasks by engaging in extended reasoning before producing final answers, yet this strength introduces t…
The Compositional Architecture of Regret in Large Language Models
Xiangxiang Cui, Shu Yang, Tianjin Huang +3
Regret in Large Language Models refers to their explicit regret expression when presented with evidence contradicting their previously generated misinformation. Studying the regret…
Is Your LLM-Based Multi-Agent a Reliable Real-World Planner? Exploring Fraud Detection in Travel Planning
Junchi Yao, Jianhua Xu, Tianyu Xin +4
The rise of Large Language Model-based Multi-Agent Planning has leveraged advanced frameworks to enable autonomous and collaborative task execution. Some systems rely on platforms…
Mitigating Behavioral Hallucination in Multimodal Large Language Models for Sequential Images
Liangliang You, Junchi Yao, Shu Yang +3
While multimodal large language models excel at various tasks, they still suffer from hallucinations, which limit their reliability and scalability for broader domain applications.…
Understanding and Mitigating Cross-lingual Privacy Leakage via Language-specific and Universal Privacy Neurons
Wenshuo Dong, Qingsong Yang, Shu Yang +5
Large Language Models (LLMs) trained on massive data capture rich information embedded in the training data. However, this also introduces the risk of privacy leakage, particularly…
Stable Vision Concept Transformers for Medical Diagnosis
Lijie Hu, Songning Lai, Yuan Hua +3
Transparency is a paramount concern in the medical field, prompting researchers to delve into the realm of explainable AI (XAI). Among these XAI methods, Concept Bottleneck Models…
Flattery in Motion: Benchmarking and Analyzing Sycophancy in Video-LLMs
Wenrui Zhou, Mohamed Hendy, Shu Yang +5
As video large language models (Video-LLMs) become increasingly integrated into real-world applications that demand grounded multimodal reasoning, ensuring their factual consistenc…
Understanding How Value Neurons Shape the Generation of Specified Values in LLMs
Yi Su, Jiayi Zhang, Shu Yang +3
Rapid integration of large language models (LLMs) into societal applications has intensified concerns about their alignment with universal ethical principles, as their internal val…
A Survey on the Safety and Security Threats of Computer-Using Agents: JARVIS or Ultron?
Ada Chen, Yongjiang Wu, Junyuan Zhang +6
Recently, AI-driven interactions with computing devices have advanced from basic prototype tools to sophisticated, LLM-based systems that emulate human-like operations in graphical…
Understanding Aha Moments: from External Observations to Internal Mechanisms
Shu Yang, Junchao Wu, Xin Chen +4
Large Reasoning Models (LRMs), capable of reasoning through complex problems, have become crucial for tasks like programming, mathematics, and commonsense reasoning. However, a key…
Understanding the Repeat Curse in Large Language Models from a Feature Perspective
Junchi Yao, Shu Yang, Jianhua Xu +3
Large language models (LLMs) have made remarkable progress in various domains, yet they often suffer from repetitive text generation, a phenomenon we refer to as the "Repeat Curse"…
Why Reasoning Matters? A Survey of Advancements in Multimodal Reasoning (v1)
Jing Bi, Susan Liang, Xiaofei Zhou +16
Reasoning is central to human intelligence, enabling structured problem-solving across diverse tasks. Recent advances in large language models (LLMs) have greatly enhanced their re…
Rethinking Prompt-based Debiasing in Large Language Models
Xinyi Yang, Runzhe Zhan, Derek F. Wong +3
Investigating bias in large language models (LLMs) is crucial for developing trustworthy AI. While prompt-based through prompt engineering is common, its effectiveness relies on th…
Backdooring CLIP through Concept Confusion
Lijie Hu, Junchi Liao, Weimin Lyu +5
Backdoor attacks pose a serious threat to deep learning models by allowing adversaries to implant hidden behaviors that remain dormant on clean inputs but are maliciously triggered…
EAP-GP: Mitigating Saturation Effect in Gradient-based Automated Circuit Identification
Lin Zhang, Wenshuo Dong, Zhuoran Zhang +5
Understanding the internal mechanisms of transformer-based language models remains challenging. Mechanistic interpretability based on circuit discovery aims to reverse engineer neu…