4 papers
Do LLMs Really Lack Difference Awareness? Uncovering Heuristic Substitution in Group-Differentiating Fairness
Jingshen Zhang, Bo Wang, Yanlin Fu +4
In this paper, we investigate the issue of difference awareness in LLMs, defined as a model's ability to recognize and acknowledge meaningful differences between social groups in f…
Understanding the Self-Reflection Mechanisms of LLMs through Biased Attitude Associations
Jingshen Zhang, Bo Wang, Boci Yang +4
While the emergent self-reflection capabilities of Large Language Models (LLMs) offer a promising paradigm for autonomous bias mitigation, their internal mechanics remain unclear,…
I CAN Debias: Uncovering and Enhancing Self-debiasing Mechanisms of Social Bias in LLMs
Jingshen Zhang, Bo Wang, Yanlin Fu +5
As LLMs rapidly advance and become increasingly agentic, mitigating social bias and ensuring fairness at scale have become critical challenges. Prior work has shown that LLMs exhib…
A Multi-Memory Segment System for Generating High-Quality Long-Term Memory Content in Agents
Gaoke Zhang, Bo Wang, Yunlong Ma +2
In the current field of agent memory, extensive explorations have been conducted in the area of memory retrieval, yet few studies have focused on exploring the memory content. Most…