Denevil: Towards Deciphering and Navigating the Ethical Values of Large Language Models via Instruction Learning

Large Language Models (LLMs) have made unprecedented breakthroughs, yet their increasing integration into everyday life might raise societal risks due to generated unethical content. Despite extensive study on specific issues like bias, the intrinsic values of LLMs remain largely unexplored from a moral philosophy perspective. This work delves into ethical values utilizing Moral Foundation Theory. Moving beyond conventional discriminative evaluations with poor reliability, we propose DeNEVIL, a novel prompt generation algorithm tailored to dynamically exploit LLMs' value vulnerabilities and elicit the violation of ethics in a generative manner, revealing their underlying value inclinations. On such a basis, we construct MoralPrompt, a high-quality dataset comprising 2,397 prompts covering 500+ value principles, and then benchmark the intrinsic values across a spectrum of LLMs. We discovered that most models are essentially misaligned, necessitating further ethical value alignment. In response, we develop VILMO, an in-context alignment method that substantially enhances the value compliance of LLM outputs by learning to generate appropriate value instructions, outperforming existing competitors. Our methods are suitable for black-box and open-source models, offering a promising initial step in studying the ethical values of LLMs.

Unpacking the Ethical Value Alignment in Big Models

Big models have greatly advanced AI's ability to understand, generate, and manipulate information and content, enabling numerous applications. However, as these models become increasingly integrated into everyday life, their inherent ethical values and potential biases pose unforeseen risks to society. This paper provides an overview of the risks and challenges associated with big models, surveys existing AI ethics guidelines, and examines the ethical implications arising from the limitations of these models. Taking a normative ethics perspective, we propose a reassessment of recent normative guidelines, highlighting the importance of collaborative efforts in academia to establish a unified and universal AI ethics framework. Furthermore, we investigate the moral inclinations of current mainstream LLMs using the Moral Foundation theory, analyze existing alignment algorithms, and outline the unique challenges encountered in aligning ethical values within them. To address these challenges, we introduce a novel conceptual paradigm for aligning the ethical values of big models and discuss promising research directions for alignment criteria, evaluation, and method, representing an initial step towards the interdisciplinary construction of the ethically aligned AI This paper is a modified English version of our Chinese paper https://crad.ict.ac.cn/cn/article/doi/10.7544/issn1000-1239.202330553, intended to help non-Chinese native speakers better understand our work.

CompeteAI: Understanding the Competition Behaviors in Large Language Model-based Agents

Large language models (LLMs) have been widely used as agents to complete different tasks, such as personal assistance or event planning. While most work has focused on cooperation and collaboration between agents, little work explores competition, another important mechanism that fosters the development of society and economy. In this paper, we seek to examine the competition behaviors in LLM-based agents. We first propose a general framework to study the competition between agents. Then, we implement a practical competitive environment using GPT-4 to simulate a virtual town with two types of agents, including restaurant agents and customer agents. Specifically, restaurant agents compete with each other to attract more customers, where the competition fosters them to transform, such as cultivating new operating strategies. The results of our experiments reveal several interesting findings ranging from social learning to Matthew Effect, which aligns well with existing sociological and economic theories. We believe that competition between agents deserves further investigation to help us understand society better. The code will be released soon.

Evaluating General-Purpose AI with Psychometrics

Artificial intelligence (AI) has witnessed an evolution from task-specific to general-purpose systems that trend toward human versatility. As AI systems begin to play pivotal roles in society, it is important to ensure that they are adequately evaluated. Current AI benchmarks typically assess performance on collections of specific tasks. This has drawbacks when used for assessing general-purpose AI systems. First, it is difficult to predict whether AI systems could complete a new task it has never seen or that did not previously exist. Second, these benchmarks often focus on overall performance metrics, potentially overlooking the finer details crucial for making informed decisions. Lastly, there are growing concerns about the reliability of existing benchmarks and questions about what is being measured. To solve these challenges, this paper suggests that psychometrics, the science of psychological measurement, should be placed at the core of evaluating general-purpose AI. Psychometrics provides a rigorous methodology for identifying and measuring the latent constructs that underlie performance across multiple tasks. We discuss its merits, warn against potential pitfalls, and propose a framework for putting it into practice. Finally, we explore future opportunities to integrate psychometrics with AI.

A Data-Centric Multi-Objective Learning Framework for Responsible Recommendation Systems

Recommendation systems effectively guide users in locating their desired information within extensive content repositories. Generally, a recommendation model is optimized to enhance accuracy metrics from a user utility standpoint, such as click-through rate or matching relevance. However, a responsible industrial recommendation system must address not only user utility (responsibility to users) but also other objectives, including increasing platform revenue (responsibility to platforms), ensuring fairness (responsibility to content creators), and maintaining unbiasedness (responsibility to long-term healthy development). Multi-objective learning is a potent approach for achieving responsible recommendation systems. Nevertheless, current methods encounter two challenges: difficulty in scaling to heterogeneous objectives within a unified framework, and inadequate controllability over objective priority during optimization, leading to uncontrollable solutions. In this paper, we present a data-centric optimization framework, MoRec, which unifies the learning of diverse objectives. MoRec is a tri-level framework: the outer level manages the balance between different objectives, utilizing a proportional-integral-derivative (PID)-based controller to ensure a preset regularization on the primary objective. The middle level transforms objective-aware optimization into data sampling weights using sign gradients. The inner level employs a standard optimizer to update model parameters with the sampled data. Consequently, MoRec can flexibly support various objectives while maintaining the original model intact. Comprehensive experiments on two public datasets and one industrial dataset showcase the effectiveness, controllability, flexibility, and Pareto efficiency of MoRec, making it highly suitable for real-world implementation.

Meta Semantic Template for Evaluation of Large Language Models

Do large language models (LLMs) genuinely understand the semantics of the language, or just memorize the training data? The recent concern on potential data contamination of LLMs has raised awareness of the community to conduct research on LLMs evaluation. In this paper, we propose MSTemp, an approach that creates meta semantic templates to evaluate the semantic understanding ability of LLMs. The core of MSTemp is not to perform evaluation directly on existing benchmark datasets, but to generate new out-of-distribution (OOD) evaluation sets using existing datasets as seeds. Specifically, for a given sentence, MSTemp leverages another language model to generate new samples while preserving its semantics. The new samples are called semantic templates to the original sentence. Then, MSTemp generates evaluation samples via sentence parsing and random word replacement on the semantic templates. MSTemp is highly flexible, dynamic, and cost-effective. Our initial experiments show that MSTemp-generated samples can significantly reduce the performance of LLMs using existing datasets as seeds. We hope this initial work can shed light on future research of LLMs evaluation.

Survey on Factuality in Large Language Models: Knowledge, Retrieval and Domain-Specificity

This survey addresses the crucial issue of factuality in Large Language Models (LLMs). As LLMs find applications across diverse domains, the reliability and accuracy of their outputs become vital. We define the Factuality Issue as the probability of LLMs to produce content inconsistent with established facts. We first delve into the implications of these inaccuracies, highlighting the potential consequences and challenges posed by factual errors in LLM outputs. Subsequently, we analyze the mechanisms through which LLMs store and process facts, seeking the primary causes of factual errors. Our discussion then transitions to methodologies for evaluating LLM factuality, emphasizing key metrics, benchmarks, and studies. We further explore strategies for enhancing LLM factuality, including approaches tailored for specific domains. We focus two primary LLM configurations standalone LLMs and Retrieval-Augmented LLMs that utilizes external data, we detail their unique challenges and potential enhancements. Our survey offers a structured guide for researchers aiming to fortify the factual reliability of LLMs.

ZooPFL: Exploring Black-box Foundation Models for Personalized Federated Learning

When personalized federated learning (FL) meets large foundation models, new challenges arise from various limitations in resources. In addition to typical limitations such as data, computation, and communication costs, access to the models is also often limited. This paper endeavors to solve both the challenges of limited resources and personalization. i.e., distribution shifts between clients. To do so, we propose a method named ZOOPFL that uses Zeroth-Order Optimization for Personalized Federated Learning. ZOOPFL avoids direct interference with the foundation models and instead learns to adapt its inputs through zeroth-order optimization. In addition, we employ simple yet effective linear projections to remap its predictions for personalization. To reduce the computation costs and enhance personalization, we propose input surgery to incorporate an auto-encoder with low-dimensional and client-specific embeddings. We provide theoretical support for ZOOPFL to analyze its convergence. Extensive empirical experiments on computer vision and natural language processing tasks using popular foundation models demonstrate its effectiveness for FL on black-box foundation models.