Related papers: CounterMoral: Editing Morals in Language Models

Model editing aims to correct errors and outdated knowledge in the Large language models (LLMs) with minimal cost. Prior research has proposed a variety of datasets to assess the effectiveness of these model editing methods. However, most…

Is it possible to use natural language to intervene in a model's behavior and alter its prediction in a desired way? We investigate the effectiveness of natural language interventions for reading-comprehension systems, studying this in the…

As large language models (LLMs) are increasingly deployed in high-stakes settings, their ability to refuse ethically sensitive prompts-such as those involving hate speech or illegal activities-has become central to content moderation and…

Stories are key to transmitting values across cultures, but their interpretation varies across linguistic and cultural contexts. Thus, we introduce multilingual story moral generation as a novel culturally grounded evaluation task. Using a…

Prior research has demonstrated that language models can, to a limited extent, represent moral norms in a variety of cultural contexts. This research aims to replicate these findings and further explore their validity, concentrating on…

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…

Ethics is one of the longest standing intellectual endeavors of humanity. In recent years, the fields of AI and NLP have attempted to wrangle with how learning systems that interact with humans should be constrained to behave ethically. One…

Aligning large language models (LLMs) with a human reasoning approach ensures that LLMs produce morally correct and human-like decisions. Ethical concerns are raised because current models are prone to generating false positives and…

Despite the ability to train capable LLMs, the methodology for maintaining their relevancy and rectifying errors remains elusive. To this end, the past few years have witnessed a surge in techniques for editing LLMs, the objective of which…

Large language models (LLMs) have become integral tools in diverse domains, yet their moral reasoning capabilities across cultural and linguistic contexts remain underexplored. This study investigates whether multilingual LLMs, such as…

This paper introduces an innovative task focused on editing the personality traits of Large Language Models (LLMs). This task seeks to adjust the models' responses to opinion-related questions on specified topics since an individual's…

As large language models (LLMs) become increasingly integrated into society, their alignment with human morals is crucial. To better understand this alignment, we created a large corpus of human- and LLM-generated responses to various moral…

The rapid integration of Large Vision-Language Models (LVLMs) into critical domains necessitates comprehensive moral evaluation to ensure their alignment with human values. While extensive research has addressed moral evaluation in LLMs,…

The question of how to make decisions that maximise the well-being of all persons is very relevant to design language models that are beneficial to humanity and free from harm. We introduce the Greatest Good Benchmark to evaluate the moral…

Counterfactuals refer to minimally edited inputs that cause a model's prediction to change, serving as a promising approach to explaining the model's behavior. Large language models (LLMs) excel at generating English counterfactuals and…

In this paper, we focus on editing Multimodal Large Language Models (MLLMs). Compared to editing single-modal LLMs, multimodal model editing is more challenging, which demands a higher level of scrutiny and careful consideration in the…

Large Language Models (LLMs) have shown strong performance across many tasks, but their ability to capture culturally diverse moral values remains unclear. In this paper, we examine whether LLMs mirror variations in moral attitudes reported…

As machine learning models evolve, maintaining transparency demands more human-centric explainable AI techniques. Counterfactual explanations, with roots in human reasoning, identify the minimal input changes needed to obtain a given output…

In this study, we delve into the realm of counterfactual reasoning capabilities of large language models (LLMs). Our primary objective is to cultivate the counterfactual thought processes within LLMs and rigorously assess these processes…

The increasing application of Artificial Intelligence and Machine Learning models poses potential risks of unfair behavior and, in light of recent regulations, has attracted the attention of the research community. Several researchers…