We propose a general framework for human-AI collaboration that amplifies the distinct capabilities of both types of intelligence. We refer to this as Generative Collective Intelligence (GCI). GCI employs AI in dual roles: as interactive agents and as technology that accumulates, organizes, and leverages knowledge. In this second role, AI creates a cognitive bridge between human reasoning and AI models. The AI functions as a social and cultural technology that enables groups to solve complex problems through structured collaboration that transcends traditional communication barriers. We argue that GCI can overcome limitations of purely algorithmic approaches to problem-solving and decision-making. We describe the mathematical foundations of GCI, based on the law of comparative judgment and minimum regret principles, and briefly illustrate its applications across various domains, including climate adaptation, healthcare transformation, and civic participation. By combining human creativity with AI's computational capabilities, GCI offers a promising approach to addressing complex societal challenges that neither humans nor machines can solve alone.

The performance on general tasks decreases after Large Language Models (LLMs) are fine-tuned on domain-specific tasks, the phenomenon is known as Catastrophic Forgetting (CF). However, this paper presents a further challenge for real application of domain-specific LLMs beyond CF, called General Capabilities Integration (GCI), which necessitates the integration of both the general capabilities and domain knowledge within a single instance. The objective of GCI is not merely to retain previously acquired general capabilities alongside new domain knowledge, but to harmonize and utilize both sets of skills in a cohesive manner to enhance performance on domain-specific tasks. Taking legal domain as an example, we carefully design three groups of training and testing tasks without lacking practicability, and construct the corresponding datasets. To better incorporate general capabilities across domain-specific scenarios, we introduce ALoRA, which utilizes a multi-head attention module upon LoRA, facilitating direct information transfer from preceding tokens to the current one. This enhancement permits the representation to dynamically switch between domain-specific knowledge and general competencies according to the attention. Extensive experiments are conducted on the proposed tasks. The results exhibit the significance of our setting, and the effectiveness of our method.

This paper presents LightLM, a lightweight Transformer-based language model for generative recommendation. While Transformer-based generative modeling has gained importance in various AI sub-fields such as NLP and vision, generative recommendation is still in its infancy due to its unique demand on personalized generative modeling. Existing works on generative recommendation often use NLP-oriented Transformer architectures such as T5, GPT, LLaMA and M6, which are heavy-weight and are not specifically designed for recommendation tasks. LightLM tackles the issue by introducing a light-weight deep and narrow Transformer architecture, which is specifically tailored for direct generation of recommendation items. This structure is especially apt for straightforward generative recommendation and stems from the observation that language model does not have to be too wide for this task, as the input predominantly consists of short tokens that are well-suited for the model's capacity. We also show that our devised user and item ID indexing methods, i.e., Spectral Collaborative Indexing (SCI) and Graph Collaborative Indexing (GCI), enables the deep and narrow Transformer architecture to outperform large-scale language models for recommendation. Besides, to address the hallucination problem of generating items as output, we propose the constrained generation process for generative recommenders. Experiments on real-world datasets show that LightLM outperforms various competitive baselines in terms of both recommendation accuracy and efficiency. The code can be found at https://github.com/dongyuanjushi/LightLM.

Explainable AI (XAI) underwent a recent surge in research on concept extraction, focusing on extracting human-interpretable concepts from Deep Neural Networks. An important challenge facing concept extraction approaches is the difficulty of interpreting and evaluating discovered concepts, especially for complex tasks such as molecular property prediction. We address this challenge by presenting GCI: a (G)raph (C)oncept (I)nterpretation framework, used for quantitatively measuring alignment between concepts discovered from Graph Neural Networks (GNNs) and their corresponding human interpretations. GCI encodes concept interpretations as functions, which can be used to quantitatively measure the alignment between a given interpretation and concept definition. We demonstrate four applications of GCI: (i) quantitatively evaluating concept extractors, (ii) measuring alignment between concept extractors and human interpretations, (iii) measuring the completeness of interpretations with respect to an end task and (iv) a practical application of GCI to molecular property prediction, in which we demonstrate how to use chemical functional groups to explain GNNs trained on molecular property prediction tasks, and implement interpretations with a 0.76 AUCROC completeness score.

To create tomorrow's smarter cities, today's initiatives will need to create measurable improvements. However, a city is a complex system and measuring its performance generates a breadth of issues. Specifically, determining what criteria should be measured, how indications should be defined, and how should the identified indicators be derived. This working paper is one in series that addresses the creation of a Semantic Web based representation of the 17 different themes of ISO 37120 indicators as part of the larger PolisGnosis Project (Fox, 2017). We define a standard ontology for representing general knowledge for the Energy Theme indicators, and for representing both the definition and data used to derive the Energy indicators.

In order to compare and analyse open data across cities, standard representations or ontologies have to be created. This paper defines a shelter ontology that includes concepts of shelters, slums, households and homelessness. The design of the ontology is based upon the data requirements of ISO 37120. ISO 37120 defines 100 indicators to measure and compare city performance. There are three shelter-themed indicators defined, namely 15.1 Percentage of city population living in slums, 15.2 Number of homeless per 100 000 population, and 15.3 Percentage of households that exist without registered legal titles. This ontology enables both the representation of the ISO 37120 Shelter theme indicators' definitions, and a city's indicator values and supporting data. This enables the analysis of city indicators by intelligent agents.