Large language models (LLMs) are currently at the forefront of intertwining AI systems with human communication and everyday life. Due to rapid technological advances and their extreme versatility, LLMs nowadays have millions of users and are at the cusp of being the main go-to technology for information retrieval, content generation, problem-solving, etc. Therefore, it is of great importance to thoroughly assess and scrutinize their capabilities. Due to increasingly complex and novel behavioral patterns in current LLMs, this can be done by treating them as participants in psychology experiments that were originally designed to test humans. For this purpose, the paper introduces a new field of research called "machine psychology". The paper outlines how different subfields of psychology can inform behavioral tests for LLMs. It defines methodological standards for machine psychology research, especially by focusing on policies for prompt designs. Additionally, it describes how behavioral patterns discovered in LLMs are to be interpreted. In sum, machine psychology aims to discover emergent abilities in LLMs that cannot be detected by most traditional natural language processing benchmarks.
相關內容
We propose a method that allows to develop shared understanding between two agents for the purpose of performing a task that requires cooperation. Our method focuses on efficiently establishing successful task-oriented communication in an open multi-agent system, where the agents do not know anything about each other and can only communicate via grounded interaction. The method aims to assist researchers that work on human-machine interaction or scenarios that require a human-in-the-loop, by defining interaction restrictions and efficiency metrics. To that end, we point out the challenges and limitations of such a (diverse) setup, while also restrictions and requirements which aim to ensure that high task performance truthfully reflects the extent to which the agents correctly understand each other. Furthermore, we demonstrate a use-case where our method can be applied for the task of cooperative query answering. We design the experiments by modifying an established ontology alignment benchmark. In this example, the agents want to query each other, while representing different databases, defined in their own ontologies that contain different and incomplete knowledge. Grounded interaction here has the form of examples that consists of common instances, for which the agents are expected to have similar knowledge. Our experiments demonstrate successful communication establishment under the required restrictions, and compare different agent policies that aim to solve the task in an efficient manner.
Deep learning has revolutionized many areas of machine learning, from computer vision to natural language processing, but these high-performance models are generally "black box." Explaining such models would improve transparency and trust in AI-powered decision making and is necessary for understanding other practical needs such as robustness and fairness. A popular means of enhancing model transparency is to quantify how individual inputs contribute to model outputs (called attributions) and the magnitude of interactions between groups of inputs. A growing number of these methods import concepts and results from game theory to produce attributions and interactions. This work presents a unifying framework for game-theory-inspired attribution and $k^\text{th}$-order interaction methods. We show that, given modest assumptions, a unique full account of interactions between features, called synergies, is possible in the continuous input setting. We identify how various methods are characterized by their policy of distributing synergies. We also demonstrate that gradient-based methods are characterized by their actions on monomials, a type of synergy function, and introduce unique gradient-based methods. We show that the combination of various criteria uniquely defines the attribution/interaction methods. Thus, the community needs to identify goals and contexts when developing and employing attribution and interaction methods.
In this study, we investigate the capacity of large language models (LLMs), specifically GPT-3.5, to operationalise natural language descriptions of cooperative, competitive, altruistic, and self-interested behavior in social dilemmas. Our focus is on the iterated Prisoner's Dilemma, a classic example of a non-zero-sum interaction, but our broader research program encompasses a range of experimental economics scenarios, including the ultimatum game, dictator game, and public goods game. Using a within-subject experimental design, we instantiated LLM-generated agents with various prompts that conveyed different cooperative and competitive stances. We then assessed the agents' level of cooperation in the iterated Prisoner's Dilemma, taking into account their responsiveness to the cooperative or defection actions of their partners. Our results provide evidence that LLMs can translate natural language descriptions of altruism and selfishness into appropriate behaviour to some extent, but exhibit limitations in adapting their behavior based on conditioned reciprocity. The observed pattern of increased cooperation with defectors and decreased cooperation with cooperators highlights potential constraints in the LLM's ability to generalize its knowledge about human behavior in social dilemmas. We call upon the research community to further explore the factors contributing to the emergent behavior of LLM-generated agents in a wider array of social dilemmas, examining the impact of model architecture, training parameters, and various partner strategies on agent behavior. As more advanced LLMs like GPT-4 become available, it is crucial to investigate whether they exhibit similar limitations or are capable of more nuanced cooperative behaviors, ultimately fostering the development of AI systems that better align with human values and social norms.
A Conversational Recommender System (CRS) offers increased transparency and control to users by enabling them to engage with the system through a real-time multi-turn dialogue. Recently, Large Language Models (LLMs) have exhibited an unprecedented ability to converse naturally and incorporate world knowledge and common-sense reasoning into language understanding, unlocking the potential of this paradigm. However, effectively leveraging LLMs within a CRS introduces new technical challenges, including properly understanding and controlling a complex conversation and retrieving from external sources of information. These issues are exacerbated by a large, evolving item corpus and a lack of conversational data for training. In this paper, we provide a roadmap for building an end-to-end large-scale CRS using LLMs. In particular, we propose new implementations for user preference understanding, flexible dialogue management and explainable recommendations as part of an integrated architecture powered by LLMs. For improved personalization, we describe how an LLM can consume interpretable natural language user profiles and use them to modulate session-level context. To overcome conversational data limitations in the absence of an existing production CRS, we propose techniques for building a controllable LLM-based user simulator to generate synthetic conversations. As a proof of concept we introduce RecLLM, a large-scale CRS for YouTube videos built on LaMDA, and demonstrate its fluency and diverse functionality through some illustrative example conversations.
Computational models are powerful tools for understanding human cognition and behavior. They let us express our theories clearly and precisely, and offer predictions that can be subtle and often counter-intuitive. However, this same richness and ability to surprise means our scientific intuitions and traditional tools are ill-suited to designing experiments to test and compare these models. To avoid these pitfalls and realize the full potential of computational modeling, we require tools to design experiments that provide clear answers about what models explain human behavior and the auxiliary assumptions those models must make. Bayesian optimal experimental design (BOED) formalizes the search for optimal experimental designs by identifying experiments that are expected to yield informative data. In this work, we provide a tutorial on leveraging recent advances in BOED and machine learning to find optimal experiments for any kind of model that we can simulate data from, and show how by-products of this procedure allow for quick and straightforward evaluation of models and their parameters against real experimental data. As a case study, we consider theories of how people balance exploration and exploitation in multi-armed bandit decision-making tasks. We validate the presented approach using simulations and a real-world experiment. As compared to experimental designs commonly used in the literature, we show that our optimal designs more efficiently determine which of a set of models best account for individual human behavior, and more efficiently characterize behavior given a preferred model. We provide code to replicate all analyses as well as tutorial notebooks and pointers to adapt the methodology to other experimental settings.
Evaluating human-AI decision-making systems is an emerging challenge as new ways of combining multiple AI models towards a specific goal are proposed every day. As humans interact with AI in decision-making systems, multiple factors may be present in a task including trust, interpretability, and explainability, amongst others. In this context, this work proposes a retrospective method to support a more holistic understanding of how people interact with and connect multiple AI models and combine multiple outputs in human-AI decision-making systems. The method consists of employing a retrospective end-user walkthrough with the objective of providing support to HCI practitioners so that they may gain an understanding of the higher order cognitive processes in place and the role that AI model outputs play in human-AI decision-making. The method was qualitatively assessed with 29 participants (four participants in a pilot phase; 25 participants in the main user study) interacting with a human-AI decision-making system in the context of financial decision-making. The system combines visual analytics, three AI models for revenue prediction, AI-supported analogues analysis, and hypothesis testing using external news and natural language processing to provide multiple means for comparing companies. Beyond results on tasks and usability problems, outcomes presented suggest that the method is promising in highlighting why AI models are ignored, used, or trusted, and how future interactions are planned. We suggest that HCI practitioners researching human-AI interaction can benefit by adding this step to user studies in a debriefing stage as a retrospective Thinking-Aloud protocol would be applied, but with emphasis on revisiting tasks and understanding why participants ignored or connected predictions while performing a task.
Prognostics and health management (PHM) technology plays a critical role in industrial production and equipment maintenance by identifying and predicting possible equipment failures and damages, thereby allowing necessary maintenance measures to be taken to enhance equipment service life and reliability while reducing production costs and downtime. In recent years, PHM technology based on artificial intelligence (AI) has made remarkable achievements in the context of the industrial IoT and big data, and it is widely used in various industries, such as railway, energy, and aviation, for condition monitoring, fault prediction, and health management. The emergence of large-scale foundation models (LSF-Models) such as ChatGPT and DALLE-E marks the entry of AI into a new era of AI-2.0 from AI-1.0, where deep models have rapidly evolved from a research paradigm of single-modal, single-task, and limited-data to a multi-modal, multi-task, massive data, and super-large model paradigm. ChatGPT represents a landmark achievement in this research paradigm, offering hope for general artificial intelligence due to its highly intelligent natural language understanding ability. However, the PHM field lacks a consensus on how to respond to this significant change in the AI field, and a systematic review and roadmap is required to elucidate future development directions. To fill this gap, this paper systematically expounds on the key components and latest developments of LSF-Models. Then, we systematically answered how to build the LSF-Model applicable to PHM tasks and outlined the challenges and future development roadmaps for this research paradigm.
Dialogue systems can leverage large pre-trained language models and knowledge to generate fluent and informative responses. However, these models are still prone to produce hallucinated responses not supported by the input source, which greatly hinders their application. The heterogeneity between external knowledge and dialogue context challenges representation learning and source integration, and further contributes to unfaithfulness. To handle this challenge and generate more faithful responses, this paper presents RHO ($\rho$) utilizing the representations of linked entities and relation predicates from a knowledge graph (KG). We propose (1) local knowledge grounding to combine textual embeddings with the corresponding KG embeddings; and (2) global knowledge grounding to equip RHO with multi-hop reasoning abilities via the attention mechanism. In addition, we devise a response re-ranking technique based on walks over KG sub-graphs for better conversational reasoning. Experimental results on OpenDialKG show that our approach significantly outperforms state-of-the-art methods on both automatic and human evaluation by a large margin, especially in hallucination reduction (17.54% in FeQA).
Advances in artificial intelligence often stem from the development of new environments that abstract real-world situations into a form where research can be done conveniently. This paper contributes such an environment based on ideas inspired by elementary Microeconomics. Agents learn to produce resources in a spatially complex world, trade them with one another, and consume those that they prefer. We show that the emergent production, consumption, and pricing behaviors respond to environmental conditions in the directions predicted by supply and demand shifts in Microeconomics. We also demonstrate settings where the agents' emergent prices for goods vary over space, reflecting the local abundance of goods. After the price disparities emerge, some agents then discover a niche of transporting goods between regions with different prevailing prices -- a profitable strategy because they can buy goods where they are cheap and sell them where they are expensive. Finally, in a series of ablation experiments, we investigate how choices in the environmental rewards, bartering actions, agent architecture, and ability to consume tradable goods can either aid or inhibit the emergence of this economic behavior. This work is part of the environment development branch of a research program that aims to build human-like artificial general intelligence through multi-agent interactions in simulated societies. By exploring which environment features are needed for the basic phenomena of elementary microeconomics to emerge automatically from learning, we arrive at an environment that differs from those studied in prior multi-agent reinforcement learning work along several dimensions. For example, the model incorporates heterogeneous tastes and physical abilities, and agents negotiate with one another as a grounded form of communication.
There is a resurgent interest in developing intelligent open-domain dialog systems due to the availability of large amounts of conversational data and the recent progress on neural approaches to conversational AI. Unlike traditional task-oriented bots, an open-domain dialog system aims to establish long-term connections with users by satisfying the human need for communication, affection, and social belonging. This paper reviews the recent works on neural approaches that are devoted to addressing three challenges in developing such systems: semantics, consistency, and interactiveness. Semantics requires a dialog system to not only understand the content of the dialog but also identify user's social needs during the conversation. Consistency requires the system to demonstrate a consistent personality to win users trust and gain their long-term confidence. Interactiveness refers to the system's ability to generate interpersonal responses to achieve particular social goals such as entertainment, conforming, and task completion. The works we select to present here is based on our unique views and are by no means complete. Nevertheless, we hope that the discussion will inspire new research in developing more intelligent dialog systems.
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191