相关论文: Biases in the Blind Spot: Detecting What LLMs Fail…

Chain-of-thought (CoT) reasoning enhances performance of large language models, but questions remain about whether these reasoning traces faithfully reflect the internal processes of the model. We present the first comprehensive study of…

Large Language Models (LLMs) inherit explicit and implicit biases from their training datasets. Identifying and mitigating biases in LLMs is crucial to ensure fair outputs, as they can perpetuate harmful stereotypes and misinformation. This…

There exist both scalable tasks, like reading comprehension and fact-checking, where model performance improves with model size, and unscalable tasks, like arithmetic reasoning and symbolic reasoning, where model performance does not…

Due to the implement of guardrails by developers, Large language models (LLMs) have demonstrated exceptional performance in explicit bias tests. However, bias in LLMs may occur not only explicitly, but also implicitly, much like humans who…

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…

Over the last year, Large Language Models (LLMs) like ChatGPT have become widely available and have exhibited fairness issues similar to those in previous machine learning systems. Current research is primarily focused on analyzing and…

Advancements in Large Language Models (LLMs) have increased the performance of different natural language understanding as well as generation tasks. Although LLMs have breached the state-of-the-art performance in various tasks, they often…

Large Language Models (LLMs) can achieve strong performance on many tasks by producing step-by-step reasoning before giving a final output, often referred to as chain-of-thought reasoning (CoT). It is tempting to interpret these CoT…

Large language models (LLMs) have garnered significant attention for their remarkable performance in a continuously expanding set of natural language processing tasks. However, these models have been shown to harbor inherent societal…

Large language models (LLMs) can pass explicit social bias tests but still harbor implicit biases, similar to humans who endorse egalitarian beliefs yet exhibit subtle biases. Measuring such implicit biases can be a challenge: as LLMs…

Bias in Large Language Models (LLMs) significantly undermines their reliability and fairness. We focus on a common form of bias: when two reference concepts in the model's concept space, such as sentiment polarities (e.g., "positive" and…

Large Language Models (LLMs) are being adopted across a wide range of tasks, including decision-making processes in industries where bias in AI systems is a significant concern. Recent research indicates that LLMs can harbor implicit biases…

Pre-trained large language models (LLMs) can now be easily adapted for specific business purposes using custom prompts or fine tuning. These customizations are often iteratively re-engineered to improve some aspect of performance, but after…

The widespread adoption of large language models (LLMs) underscores the urgent need to ensure their fairness. However, LLMs frequently present dominant viewpoints while ignoring alternative perspectives from minority parties, resulting in…

Large Language Models (LLMs) are prone to inheriting and amplifying societal biases embedded within their training data, potentially reinforcing harmful stereotypes related to gender, occupation, and other sensitive categories. This issue…

This paper investigates the subtle and often concealed biases present in Large Language Models (LLMs), focusing on implicit biases that may remain despite passing explicit bias tests. Implicit biases are significant because they influence…

Large Language Models (LLMs) have shown a high capability in answering questions on a diverse range of topics. However, these models sometimes produce biased, ideologized or incorrect responses, limiting their applications if there is no…

Large language models (LLMs) are increasingly deployed in socially sensitive settings despite substantial documentation that they encode gender biases. Chain-of-Thought (CoT) prompting has been proposed as a bias-mitigation approach.…

While various approaches have recently been studied for bias identification, little is known about how implicit language that does not explicitly convey a viewpoint affects bias amplification in large language models. To examine the…

Large language models (LLMs) offer significant potential as tools to support an expanding range of decision-making tasks. Given their training on human (created) data, LLMs have been shown to inherit societal biases against protected…