相关论文: Bias after Prompting: Persistent Discrimination in…

Large language models (LLMs) are revolutionizing every aspect of society. They are increasingly used in problem-solving tasks to substitute human assessment and reasoning. LLMs are trained on what humans write and are thus exposed to human…

Large Language Models (LLMs) exhibit social biases, which can lead to harmful stereotypes and unfair outcomes. We propose \textbf{Multi-Persona Thinking (MPT)}, a simple inference-time framework that reduces social bias by encouraging…

One of the most common complaints about large language models (LLMs) is their prompt sensitivity -- that is, the fact that their ability to perform a task or provide a correct answer to a question can depend unpredictably on the way the…

As LLMs are increasingly applied in socially impactful settings, concerns about gender bias have prompted growing efforts both to measure and mitigate such bias. These efforts often rely on evaluation tasks that differ from natural language…

Recently, a boom of papers has shown extraordinary progress in zero-shot and few-shot learning with various prompt-based models. It is commonly argued that prompts help models to learn faster in the same way that humans learn faster when…

While reasoning-based large language models excel at complex tasks through an internal, structured thinking process, a concerning phenomenon has emerged that such a thinking process can aggregate social stereotypes, leading to biased…

Prompt-based learning paradigm bridges the gap between pre-training and fine-tuning, and works effectively under the few-shot setting. However, we find that this learning paradigm inherits the vulnerability from the pre-training stage,…

Large Language Models (LLMs) such as Mistral and LLaMA have showcased remarkable performance across various natural language processing (NLP) tasks. Despite their success, these models inherit social biases from the diverse datasets on…

Text-to-Image (TTI) models are powerful creative tools but risk amplifying harmful social biases. We frame representational societal bias assessment as an image curation and evaluation task and introduce a pilot benchmark of occupational…

Rapid advancements of large language models (LLMs) have enabled the processing, understanding, and generation of human-like text, with increasing integration into systems that touch our social sphere. Despite this success, these models can…

Prompt-induced cognitive biases are changes in a general-purpose AI (GPAI) system's decisions caused solely by biased wording in the input (e.g., framing, anchors), not task logic. In software engineering (SE) decision support (where…

As LLMs are increasingly integrated into user-facing applications, addressing biases that perpetuate societal inequalities is crucial. While much work has gone into measuring or mitigating biases in these models, fewer studies have…

In many real-world applications, large language models (LLMs) operate as independent agents without interaction, thereby limiting coordination. In this setting, we examine how prompt framing influences decisions in a threshold voting task…

Detecting social bias in text is challenging due to nuance, subjectivity, and difficulty in obtaining good quality labeled datasets at scale, especially given the evolving nature of social biases and society. To address these challenges, we…

Large Language Models (LLMs) are increasingly utilized in educational tasks such as providing writing suggestions to students. Despite their potential, LLMs are known to harbor inherent biases which may negatively impact learners. Previous…

Chain-of-thought prompting (CoT) has the potential to improve the explainability of language model reasoning. But CoT can also systematically misrepresent the factors influencing models' behavior -- for example, rationalizing answers in…

Prompting is one of the main ways to adapt a pretrained model to target tasks. Besides manually constructing prompts, many prompt optimization methods have been proposed in the literature. Method development is mainly empirically driven,…

Large Language Models (LLMs) are reported to hold undesirable attestation bias on inference tasks: when asked to predict if a premise P entails a hypothesis H, instead of considering H's conditional truthfulness entailed by P, LLMs tend to…

Human judgments are inherently subjective and are actively affected by personal traits such as gender and ethnicity. While Large Language Models (LLMs) are widely used to simulate human responses across diverse contexts, their ability to…

The work presents an approach for addressing the challenge of robustness in Large Language Models (LLMs) to alterations and potential errors caused by semantically similar but textually different prompts. Recent works have shown that these…