相关论文: Some Issues in Predictive Ethics Modeling: An Anno…

Recent research on large language models (LLMs) has demonstrated their ability to understand and employ deceptive behavior, even without explicit prompting. However, such behavior has only been observed in rare, specialized cases and has…

In social settings, much of human behavior is governed by unspoken rules of conduct. For artificial systems to be fully integrated into social environments, adherence to such norms is a central prerequisite. We investigate whether…

In this work, we study the alignment (BrainScore) of large language models (LLMs) fine-tuned for moral reasoning on behavioral data and/or brain data of humans performing the same task. We also explore if fine-tuning several LLMs on the…

Sycophancy in Vision-Language Models (VLMs) refers to their tendency to align with user opinions, often at the expense of moral or factual accuracy. While prior studies have explored sycophantic behavior in general contexts, its impact on…

While advanced classifiers have been increasingly used in real-world safety-critical applications, how to properly evaluate the black-box models given specific human values remains a concern in the community. Such human values include…

Authorship attribution techniques are increasingly being used in online contexts such as sock puppet detection, malicious account linking, and cross-platform account linking. Yet, it is unknown whether these models perform equitably across…

Data used by automated decision-making systems, such as Machine Learning models, often reflects discriminatory behavior that occurred in the past. These biases in the training data are sometimes related to label noise, such as in COMPAS,…

Abusive language detection models tend to have a problem of being biased toward identity words of a certain group of people because of imbalanced training datasets. For example, "You are a good woman" was considered "sexist" when trained on…

Supporting model interpretability for complex phenomena where annotators can legitimately disagree, such as emotion recognition, is a challenging machine learning task. In this work, we show that explicitly quantifying the uncertainty in…

We study fair classification in the presence of an omniscient adversary that, given an $\eta$, is allowed to choose an arbitrary $\eta$-fraction of the training samples and arbitrarily perturb their protected attributes. The motivation…

Are AI systems truly representing human values, or merely averaging across them? Our study suggests a concerning reality: Large Language Models (LLMs) fail to represent diverse cultural moral frameworks despite their linguistic…

Moral actions are judged not only by their outcomes but by the context in which they occur. We present COMETH (Contextual Organization of Moral Evaluation from Textual Human inputs), a framework that integrates a probabilistic context…

This paper investigates the ethical implications of aligning Large Language Models (LLMs) with financial optimization, through the case study of GreedLlama, a model fine-tuned to prioritize economically beneficial outcomes. By comparing…

Advances in language modeling architectures and the availability of large text corpora have driven progress in automatic text generation. While this results in models capable of generating coherent texts, it also prompts models to…

Conversational agents have come increasingly closer to human competence in open-domain dialogue settings; however, such models can reflect insensitive, hurtful, or entirely incoherent viewpoints that erode a user's trust in the moral…

Conformal prediction has emerged as an effective strategy for uncertainty quantification by modifying a model to output sets of labels instead of a single label. These prediction sets come with the guarantee that they contain the true label…

Morality plays an important role in social well-being, but people's moral perception is not stable and changes over time. Recent advances in natural language processing have shown that text is an effective medium for informing moral change,…

If our models are used in new or unexpected cases, do we know if they will make fair predictions? Previously, researchers developed ways to debias a model for a single problem domain. However, this is often not how models are trained and…

Moral foundations theory (MFT) is a psychological assessment tool that decomposes human moral reasoning into five factors, including care/harm, liberty/oppression, and sanctity/degradation (Graham et al., 2009). People vary in the weight…

As large language models (LLMs) increasingly participate in tasks with ethical and societal stakes, a critical question arises: do they exhibit an emergent "moral mind" - a consistent structure of moral preferences guiding their decisions -…