papers

Publications (6)

cs.CL2026

From Biased Chatbots to Biased Agents: Examining Role Assignment Effects on LLM Agent Robustness

Linbo Cao, Lihao Sun, Yang Yue

Large Language Models (LLMs) are increasingly deployed as autonomous agents capable of actions with real-world impacts beyond text generation. While persona-induced biases in text…

cs.CL2025

Aligned but Blind: Alignment Increases Implicit Bias by Reducing Awareness of Race

Lihao Sun, Chengzhi Mao, Valentin Hofmann +1

Although value-aligned language models (LMs) appear unbiased in explicit bias evaluations, they often exhibit stereotypes in implicit word association tasks, raising concerns about…

cs.CL2026

LLM Reasoning as Trajectories: Step-Specific Representation Geometry and Correctness Signals

Lihao Sun, Hang Dong, Bo Qiao +3

This work characterizes large language models' chain-of-thought generation as a structured trajectory through representation space. We show that mathematical reasoning traverses fu…

cs.AI2025

Probing Scientific General Intelligence of LLMs with Scientist-Aligned Workflows

Wanghan Xu, Yuhao Zhou, Yifan Zhou +104

Despite advances in scientific AI, a coherent framework for Scientific General Intelligence (SGI)-the ability to autonomously conceive, investigate, and reason across scientific do…

cs.CL2026

Valence-Arousal Subspace in LLMs: Circular Emotion Geometry and Multi-Behavioral Control

Lihao Sun, Lewen Yan, Xiaoya Lu +3

We show that emotion vectors in LLMs are organized by a two-dimensional valence-arousal (VA) subspace exhibiting circular geometry. Through principal component decomposition and ri…

cs.AI2025

The Geometry of Self-Verification in a Task-Specific Reasoning Model

Andrew Lee, Lihao Sun, Chris Wendler +2

How do reasoning models verify their own answers? We study this question by training a model using DeepSeek R1's recipe on the CountDown task. We leverage the fact that preference…