10 papers
Representational Similarity and Model Behavior in Multi-Agent Interaction
Yujin Potter, Seun Eisape, Shiyang Lai +6
Researchers have shown that neural similarity among humans predicts social closeness and cooperative success, whereas innovation often emerges from interactions among dissimilar in…
Probing Multimodal Large Language Models on Cognitive Biases in Chinese Short-Video Misinformation
Jen-tse Huang, Chang Chen, Shiyang Lai +3
Short-video platforms have become major channels for misinformation, where deceptive claims frequently leverage visual experiments and social cues. While Multimodal Large Language…
Multi-LLM Systems Exhibit Robust Semantic Collapse
Weiyi Kong, Shiyang Lai, Jinghua Piao +1
Whether machines can originate novel content has been debated for nearly two centuries, from Lovelace's assertion that no engine can "originate anything" to Turing's question of wh…
Signal in the Noise: Polysemantic Interference Transfers and Predicts Cross-Model Influence
Bofan Gong, Shiyang Lai, James Evans +1
Polysemanticity is pervasive in language models and remains a major challenge for interpretation and model behavioral control. Leveraging sparse autoencoders (SAEs), we map the pol…
Reasoning Models Generate Societies of Thought
Junsol Kim, Shiyang Lai, Nino Scherrer +2
Large language models have achieved remarkable capabilities across domains, yet mechanisms underlying sophisticated reasoning remain elusive. Recent reasoning models outperform com…
Can Editing LLMs Inject Harm?
Canyu Chen, Baixiang Huang, Zekun Li +12
Large Language Models (LLMs) have emerged as a new information channel. Meanwhile, one critical but under-explored question is: Is it possible to bypass the safety alignment and in…