8 papers
Are the Financial Reasoning from LLMs Credible? A Real World Test over Long-Horizon Statements
Xinke Tong, Xuanming Zhang, Tianyi Tang +10
Do Large Language Models (LLMs) possess genuine structural reasoning, or merely rely on surface-level pattern matching? The financial domain, demanding numerical precision and mult…
Deeper is Not Always Better: Mitigating the Alignment Tax via Confident Layer Decoding
Xuanming Zhang, Sining Zhoubian, Yuxuan Chen +8
Autoregressive generation in large language models (LLMs) conventionally decodes from the final layer, assuming that deeper representations yield more reliable next-token predictio…
Human Decision-making is Susceptible to AI-driven Manipulation
Sahand Sabour, June M. Liu, Siyang Liu +13
AI systems are increasingly intertwined with daily life, assisting users with various tasks and guiding decision-making. This integration introduces risks of AI-driven manipulation…
Cognition-of-Thought Elicits Social-Aligned Reasoning in Large Language Models
Xuanming Zhang, Yuxuan Chen, Samuel Yeh +1
Large language models (LLMs) excel at complex reasoning but can still exhibit harmful behaviors. Current alignment strategies typically embed safety into model weights, making thes…
MetaMind: Modeling Human Social Thoughts with Metacognitive Multi-Agent Systems
Xuanming Zhang, Yuxuan Chen, Samuel Yeh +1
Human social interactions depend on the ability to infer others' unspoken intentions, emotions, and beliefs-a cognitive skill grounded in the psychological concept of Theory of Min…
Towards Exception Safety Code Generation with Intermediate Representation Agents Framework
Xuanming Zhang, Yuxuan Chen, Yuan Yuan +1
Large Language Models (LLMs) often struggle with robust exception handling in generated code, leading to fragile programs that are prone to runtime errors. We propose Seeker, a nov…