Artificial Intelligence (cs.AI)

Abstract: The public release of ChatGPT has resulted in considerable publicity and has led to wide-spread discussion of the usefulness and capabilities of generative AI language models. Its ability to extract and summarise data from textual sources and present them as human-like contextual responses makes it an eminently suitable tool to answer questions users might ask. This paper tested what archaeological literature appears to have been included in ChatGPT's training phase. While ChatGPT offered seemingly pertinent references, a large percentage proved to be fictitious. Using cloze analysis to make inferences on the sources 'memorised' by a generative AI model, this paper was unable to prove that ChatGPT had access to the full texts of the genuine references. It can be shown that all references provided by ChatGPT that were found to be genuine have also been cited on Wikipedia pages. This strongly indicates that the source base for at least some of the data is found in those pages. The implications of this in relation to data quality are discussed.

Abstract: Aiming for a mixbiotic society that combines freedom and solidarity among people with diverse values, I focused on nonviolent communication (NVC) that enables compassionate giving in various situations of social division and conflict, and tried a generative AI for it. Specifically, ChatGPT was used in place of the traditional certified trainer to test the possibility of mediating (modifying) input sentences in four processes: observation, feelings, needs, and requests. The results indicate that there is potential for the application of generative AI, although not yet at a practical level. Suggested improvement guidelines included adding model responses, relearning revised responses, specifying appropriate terminology for each process, and re-asking for required information. The use of generative AI will be useful initially to assist certified trainers, to prepare for and review events and workshops, and in the future to support consensus building and cooperative behavior in digital democracy, platform cooperatives, and cyber-human social co-operating systems. It is hoped that the widespread use of NVC mediation using generative AI will lead to the early realization of a mixbiotic society.

Abstract: Communication is crucial for solving cooperative Multi-Agent Reinforcement Learning tasks in Partially-Observable Markov Decision Processes. Existing works often rely on black-box methods to encode local information/features into messages shared with other agents. However, such black-box approaches are unable to provide any quantitative guarantees on the expected return and often lead to the generation of continuous messages with high communication overhead and poor interpretability. In this paper, we establish an upper bound on the return gap between an ideal policy with full observability and an optimal partially-observable policy with discrete communication. This result enables us to recast multi-agent communication into a novel online clustering problem over the local observations at each agent, with messages as cluster labels and the upper bound on the return gap as clustering loss. By minimizing the upper bound, we propose a surprisingly simple design of message generation functions in multi-agent communication and integrate it with reinforcement learning using a Regularized Information Maximization loss function. Evaluations show that the proposed discrete communication significantly outperforms state-of-the-art multi-agent communication baselines and can achieve nearly-optimal returns with few-bit messages that are naturally interpretable.

Abstract: This paper is dedicated to a robust ordinal method for learning the preferences of a decision maker between subsets. The decision model, derived from Fishburn and LaValle (1996) and whose parameters we learn, is general enough to be compatible with any strict weak order on subsets, thanks to the consideration of possible interactions between elements. Moreover, we accept not to predict some preferences if the available preference data are not compatible with a reliable prediction. A predicted preference is considered reliable if all the simplest models (Occam's razor) explaining the preference data agree on it. Following the robust ordinal regression methodology, our predictions are based on an uncertainty set encompassing the possible values of the model parameters. We define a robust ordinal dominance relation between subsets and we design a procedure to determine whether this dominance relation holds. Numerical tests are provided on synthetic and real-world data to evaluate the richness and reliability of the preference predictions made.

Abstract: As the core of the Knowledge Tracking (KT) task, assessing students' dynamic mastery of knowledge concepts is crucial for both offline teaching and online educational applications. Since students' mastery of knowledge concepts is often unlabeled, existing KT methods rely on the implicit paradigm of historical practice to mastery of knowledge concepts to students' responses to practices to address the challenge of unlabeled concept mastery. However, purely predicting student responses without imposing specific constraints on hidden concept mastery values does not guarantee the accuracy of these intermediate values as concept mastery values. To address this issue, we propose a principled approach called Counterfactual Monotonic Knowledge Tracing (CMKT), which builds on the implicit paradigm described above by using a counterfactual assumption to constrain the evolution of students' mastery of knowledge concepts.

Abstract: With recent advancements in natural language processing, Large Language Models (LLMs) have emerged as powerful tools for various real-world applications. Despite their prowess, the intrinsic generative abilities of LLMs may prove insufficient for handling complex tasks which necessitate a combination of task planning and the usage of external tools. In this paper, we first propose a structured framework tailored for LLM-based AI Agents and discuss the crucial capabilities necessary for tackling intricate problems. Within this framework, we design two distinct types of agents (i.e., one-step agent and sequential agent) to execute the inference process. Subsequently, we instantiate the framework using various LLMs and evaluate their Task Planning and Tool Usage (TPTU) abilities on typical tasks. By highlighting key findings and challenges, our goal is to provide a helpful resource for researchers and practitioners to leverage the power of LLMs in their AI applications. Our study emphasizes the substantial potential of these models, while also identifying areas that need more investigation and improvement.

Abstract: A knowledge graph is a powerful representation of real-world entities and their relations. The vast majority of these relations are defined as positive statements, but the importance of negative statements is increasingly recognized, especially under an Open World Assumption. Explicitly considering negative statements has been shown to improve performance on tasks such as entity summarization and question answering or domain-specific tasks such as protein function prediction. However, no attention has been given to the exploration of negative statements by knowledge graph embedding approaches despite the potential of negative statements to produce more accurate representations of entities in a knowledge graph. We propose a novel approach, TrueWalks, to incorporate negative statements into the knowledge graph representation learning process. In particular, we present a novel walk-generation method that is able to not only differentiate between positive and negative statements but also take into account the semantic implications of negation in ontology-rich knowledge graphs. This is of particular importance for applications in the biomedical domain, where the inadequacy of embedding approaches regarding negative statements at the ontology level has been identified as a crucial limitation. We evaluate TrueWalks in ontology-rich biomedical knowledge graphs in two different predictive tasks based on KG embeddings: protein-protein interaction prediction and gene-disease association prediction. We conduct an extensive analysis over established benchmarks and demonstrate that our method is able to improve the performance of knowledge graph embeddings on all tasks.

Abstract: Massive emerging applications are driving demand for the ubiquitous deployment of computing power today. This trend not only spurs the recent popularity of the \emph{Computing and Network Convergence} (CNC), but also introduces an urgent need for the intelligentization of a management platform to coordinate changing resources and tasks in the CNC. Therefore, in this article, we present the concept of an intelligence-endogenous management platform for CNCs called \emph{CNC brain} based on artificial intelligence technologies. It aims at efficiently and automatically matching the supply and demand with high heterogeneity in a CNC via four key building blocks, i.e., perception, scheduling, adaptation, and governance, throughout the CNC's life cycle. Their functionalities, goals, and challenges are presented. To examine the effectiveness of the proposed concept and framework, we also implement a prototype for the CNC brain based on a deep reinforcement learning technology. Also, it is evaluated on a CNC testbed that integrates two open-source and popular frameworks (OpenFaas and Kubernetes) and a real-world business dataset provided by Microsoft Azure. The evaluation results prove the proposed method's effectiveness in terms of resource utilization and performance. Finally, we highlight the future research directions of the CNC brain.

Abstract: Knowledge tracing (KT) aims to predict students' responses to practices based on their historical question-answering behaviors. However, most current KT methods focus on improving overall AUC, leaving ample room for optimization in modeling sequences of excessive or insufficient lengths. As sequences get longer, computational costs will increase exponentially. Therefore, KT methods usually truncate sequences to an acceptable length, which makes it difficult for models on online service systems to capture complete historical practice behaviors of students with too long sequences. Conversely, modeling students with short practice sequences using most KT methods may result in overfitting due to limited observation samples. To address the above limitations, we propose a model called Sequence-Flexible Knowledge Tracing (SFKT).

Abstract: Empathy is often understood as the ability to share and understand another individual's state of mind or emotion. With the increasing use of chatbots in various domains, e.g., children seeking help with homework, individuals looking for medical advice, and people using the chatbot as a daily source of everyday companionship, the importance of empathy in human-computer interaction has become more apparent. Therefore, our study investigates the extent to which ChatGPT based on GPT-3.5 can exhibit empathetic responses and emotional expressions. We analyzed the following three aspects: (1) understanding and expressing emotions, (2) parallel emotional response, and (3) empathic personality. Thus, we not only evaluate ChatGPT on various empathy aspects and compare it with human behavior but also show a possible way to analyze the empathy of chatbots in general. Our results show, that in 91.7% of the cases, ChatGPT was able to correctly identify emotions and produces appropriate answers. In conversations, ChatGPT reacted with a parallel emotion in 70.7% of cases. The empathic capabilities of ChatGPT were evaluated using a set of five questionnaires covering different aspects of empathy. Even though the results indicate that the empathic abilities of ChatGPT are still below the average of healthy humans, the scores are better than those of people who have been diagnosed with Asperger syndrome / high-functioning autism.

Abstract: When used in the context of decision theory, feature importance expresses how much changing the value of a feature can change the model outcome (or the utility of the outcome), compared to other features. Feature importance should not be confused with the feature influence used by most state-of-the-art post-hoc Explainable AI methods. Contrary to feature importance, feature influence is measured against a reference level or baseline. The Contextual Importance and Utility (CIU) method provides a unified definition of global and local feature importance that is applicable also for post-hoc explanations, where the value utility concept provides instance-level assessment of how favorable or not a feature value is for the outcome. The paper shows how CIU can be applied to both global and local explainability, assesses the fidelity and stability of different methods, and shows how explanations that use contextual importance and contextual utility can provide more expressive and flexible explanations than when using influence only.

Abstract: The original vision of AI was re-articulated in 2002 via the term 'Artificial General Intelligence' or AGI. This vision is to build 'Thinking Machines' - computer systems that can learn, reason, and solve problems similar to the way humans do. This is in stark contrast to the 'Narrow AI' approach practiced by almost everyone in the field over the many decades. While several large-scale efforts have nominally been working on AGI (most notably DeepMind), the field of pure focused AGI development has not been well funded or promoted. This is surprising given the fantastic value that true AGI can bestow on humanity. In addition to the dearth of effort in this field, there are also several theoretical and methodical missteps that are hampering progress. We highlight why purely statistical approaches are unlikely to lead to AGI, and identify several crucial cognitive abilities required to achieve human-like adaptability and autonomous learning. We conclude with a survey of socio-technical factors that have undoubtedly slowed progress towards AGI.

Abstract: One of the most enticing research areas is the stock market, and projecting stock prices may help investors profit by making the best decisions at the correct time. Deep learning strategies have emerged as a critical technique in the field of the financial market. The stock market is impacted due to two aspects, one is the geo-political, social and global events on the bases of which the price trends could be affected. Meanwhile, the second aspect purely focuses on historical price trends and seasonality, allowing us to forecast stock prices. In this paper, our aim is to focus on the second aspect and build a model that predicts future prices with minimal errors. In order to provide better prediction results of stock price, we propose a new model named Long Short-Term Memory (LSTM) with Sequential Self-Attention Mechanism (LSTM-SSAM). Finally, we conduct extensive experiments on the three stock datasets: SBIN, HDFCBANK, and BANKBARODA. The experimental results prove the effectiveness and feasibility of the proposed model compared to existing models. The experimental findings demonstrate that the root-mean-squared error (RMSE), and R-square (R2) evaluation indicators are giving the best results.

Abstract: QDax is an open-source library with a streamlined and modular API for Quality-Diversity (QD) optimization algorithms in Jax. The library serves as a versatile tool for optimization purposes, ranging from black-box optimization to continuous control. QDax offers implementations of popular QD, Neuroevolution, and Reinforcement Learning (RL) algorithms, supported by various examples. All the implementations can be just-in-time compiled with Jax, facilitating efficient execution across multiple accelerators, including GPUs and TPUs. These implementations effectively demonstrate the framework's flexibility and user-friendliness, easing experimentation for research purposes. Furthermore, the library is thoroughly documented and tested with 95\% coverage.

Abstract: Large Language Models (LLMs) are becoming increasingly smart and autonomous, targeting real-world pragmatic missions beyond traditional NLP tasks. As a result, there has been an urgent need to evaluate LLMs as agents on challenging tasks in interactive environments. We present AgentBench, a multi-dimensional evolving benchmark that currently consists of 8 distinct environments to assess LLM-as-Agent's reasoning and decision-making abilities in a multi-turn open-ended generation setting. Our extensive test over 25 LLMs (including APIs and open-sourced models) shows that, while top commercial LLMs present a strong ability of acting as agents in complex environments, there is a significant disparity in performance between them and open-sourced competitors. It also serves as a component of an ongoing project with wider coverage and deeper consideration towards systematic LLM evaluation. Datasets, environments, and an integrated evaluation package for AgentBench are released at https://github.com/THUDM/AgentBench

Abstract: Online violence against children has increased globally recently, demanding urgent attention. Competent authorities manually analyze abuse complaints to comprehend crime dynamics and identify patterns. However, the manual analysis of these complaints presents a challenge because it exposes analysts to harmful content during the review process. Given these challenges, we present a novel solution, an automated tool designed to analyze children's sexual abuse reports comprehensively. By automating the analysis process, our tool significantly reduces the risk of exposure to harmful content by categorizing the reports on three dimensions: Subject, Degree of Criminality, and Damage. Furthermore, leveraging our multidisciplinary team's expertise, we introduce a novel approach to annotate the collected data, enabling a more in-depth analysis of the reports. This approach improves the comprehension of fundamental patterns and trends, enabling law enforcement agencies and policymakers to create focused strategies in the fight against children's violence.

Abstract: Methods: Through an innovative approach, we construct ontology-based knowledge graphs from authentic medical literature and AI-generated content. Our goal is to distinguish factual information from unverified data. We compiled two datasets: one from biomedical literature using a "human disease and symptoms" query, and another generated by ChatGPT, simulating articles. With these datasets (PubMed and ChatGPT), we curated 10 sets of 250 abstracts each, selected randomly with a specific seed. Our method focuses on utilizing disease ontology (DOID) and symptom ontology (SYMP) to build knowledge graphs, robust mathematical models that facilitate unbiased comparisons. By employing our fact-checking algorithms and network centrality metrics, we conducted GPT disease-symptoms link analysis to quantify the accuracy of factual knowledge amid noise, hypotheses, and significant findings. Results: The findings obtained from the comparison of diverse ChatGPT knowledge graphs with their PubMed counterparts revealed some interesting observations. While PubMed knowledge graphs exhibit a wealth of disease-symptom terms, it is surprising to observe that some ChatGPT graphs surpass them in the number of connections. Furthermore, some GPT graphs are demonstrating supremacy of the centrality scores, especially for the overlapping nodes. This striking contrast indicates the untapped potential of knowledge that can be derived from AI-generated content, awaiting verification. Out of all the graphs, the factual link ratio between any two graphs reached its peak at 60%. Conclusions: An intriguing insight from our findings was the striking number of links among terms in the knowledge graph generated from ChatGPT datasets, surpassing some of those in its PubMed counterpart. This early discovery has prompted further investigation using universal network metrics to unveil the new knowledge the links may hold.