Related papers: Information Gain-Guided Causal Intervention for Au…

Large Language Models (LLMs) are powerful tools with the potential to benefit society immensely, yet, they have demonstrated biases that perpetuate societal inequalities. Despite significant advancements in bias mitigation techniques using…

Recovering the structure of causal graphical models from observational data is an essential yet challenging task for causal discovery in scientific scenarios. Domain-specific causal discovery usually relies on expert validation or prior…

Large Language models (LLMs) possess the capability to engage In-context Learning (ICL) by leveraging a few demonstrations pertaining to a new downstream task as conditions. However, this particular learning paradigm suffers from high…

Reward models (RMs) are essential in reinforcement learning from human feedback (RLHF) to align large language models (LLMs) with human values. However, RM training data is commonly recognized as low-quality, containing inductive biases…

Dataset bias is a significant problem in training fair classifiers. When attributes unrelated to classification exhibit strong biases towards certain classes, classifiers trained on such dataset may overfit to these bias attributes,…

Large language models exhibit exciting capabilities, yet can show surprisingly narrow generalization from finetuning. E.g. they can fail to generalize to simple reversals of relations they are trained on, or fail to make simple logical…

Causal learning is the cognitive process of developing the capability of making causal inferences based on available information, often guided by normative principles. This process is prone to errors and biases, such as the illusion of…

Large language models (LLMs) have achieved impressive performance on various natural language generation tasks. Nonetheless, they suffer from generating negative and harmful contents that are biased against certain demographic groups (e.g.,…

Mitigating social bias in large language models (LLMs) has become an increasingly important research objective. However, existing debiasing methods often incur high human and computational costs, exhibit limited effectiveness, and struggle…

Ensuring that large language models (LMs) are fair, robust and useful requires an understanding of how different modifications to their inputs impact the model's behaviour. In the context of open-text generation tasks, however, such an…

Large Language Models (LLMs) have demonstrated impressive capabilities in reasoning tasks, yet their reliance on static prompt structures and limited adaptability to complex scenarios remains a significant challenge. In this paper, we…

Generative AI technologies, particularly Large Language Models (LLMs), have transformed information management systems but introduced substantial biases that can compromise their effectiveness in informing business decision-making. This…

Causal learning is the cognitive process of developing the capability of making causal inferences based on available information, often guided by normative principles. This process is prone to errors and biases, such as the illusion of…

Recent studies have demonstrated that some Large Language Models exhibit choice-supportive bias (CSB) when performing evaluations, systematically favoring their chosen options and potentially compromising the objectivity of AI-assisted…

Self-Correction based on feedback improves the output quality of Large Language Models (LLMs). Moreover, as Self-Correction functions like the slow and conscious System-2 thinking from cognitive psychology's perspective, it can potentially…

The black-box nature of large language models (LLMs) poses challenges in interpreting results, impacting issues such as data intellectual property protection and hallucination tracing. Training data attribution (TDA) methods are considered…

Despite the notable advancements of existing prompting methods, such as In-Context Learning and Chain-of-Thought for Large Language Models (LLMs), they still face challenges related to various biases. Traditional debiasing methods primarily…

Current social bias benchmarks for Large Language Models (LLMs) primarily rely on predefined question formats like multiple-choice, limiting their ability to reflect the complexity and open-ended nature of real-world interactions. To close…

With widening deployments of natural language processing (NLP) in daily life, inherited social biases from NLP models have become more severe and problematic. Previous studies have shown that word embeddings trained on human-generated…

With the increasing complexity and rapid expansion of the scale of AI systems in cloud platforms, the log data generated during system operation is massive, unstructured, and semantically ambiguous, which brings great challenges to fault…