The digital landscape is rapidly evolving with an ever-increasing volume of online news, emphasizing the need for swift and precise analysis of complex events. We refer to the complex events composed of many news articles over an extended period as Temporal Complex Event (TCE). This paper proposes a novel approach using Large Language Models (LLMs) to systematically extract and analyze the event chain within TCE, characterized by their key points and timestamps. We establish a benchmark, named TCELongBench, to evaluate the proficiency of LLMs in handling temporal dynamics and understanding extensive text. This benchmark encompasses three distinct tasks - reading comprehension, temporal sequencing, and future event forecasting. In the experiment, we leverage retrieval-augmented generation (RAG) method and LLMs with long context window to deal with lengthy news articles of TCE. Our findings indicate that models with suitable retrievers exhibit comparable performance with those utilizing long context window.

This study evaluates the effectiveness of child-robot interactions with the HaKsh-E social robot in India, examining both individual and group interaction settings. The research centers on game-based interactions designed to teach hand hygiene to children aged 7-11. Utilizing video analysis, rubric assessments, and post-study questionnaires, the study gathered data from 36 participants. Findings indicate that children in both settings developed positive perceptions of the robot in terms of the robot's trustworthiness, closeness, and social support. The significant difference in the interaction level scores presented in the study suggests that group settings foster higher levels of interaction, potentially due to peer influence and collaborative dynamics. While both settings showed significant improvements in learning outcomes, the individual setting had more pronounced learning gains. This suggests that personal interactions with the robot might lead to deeper or more effective learning experiences. Consequently, this study concludes that individual interaction settings are more conducive for focused learning gains, while group settings enhance interaction and engagement.

Building a reliable visual question answering~(VQA) system across different languages is a challenging problem, primarily due to the lack of abundant samples for training. To address this challenge, recent studies have employed machine translation systems for the cross-lingual VQA task. This involves translating the evaluation samples into a source language (usually English) and using monolingual models (i.e., translate-test). However, our analysis reveals that translated texts contain unique characteristics distinct from human-written ones, referred to as translation artifacts. We find that these artifacts can significantly affect the models, confirmed by extensive experiments across diverse models, languages, and translation processes. In light of this, we present a simple data augmentation strategy that can alleviate the adverse impacts of translation artifacts.

A key challenge in e-learning environments like Intelligent Tutoring Systems (ITSs) is to induce effective pedagogical policies efficiently. While Deep Reinforcement Learning (DRL) often suffers from sample inefficiency and reward function design difficulty, Apprenticeship Learning(AL) algorithms can overcome them. However, most AL algorithms can not handle heterogeneity as they assume all demonstrations are generated with a homogeneous policy driven by a single reward function. Still, some AL algorithms which consider heterogeneity, often can not generalize to large continuous state space and only work with discrete states. In this paper, we propose an expectation-maximization(EM)-EDM, a general AL framework to induce effective pedagogical policies from given optimal or near-optimal demonstrations, which are assumed to be driven by heterogeneous reward functions. We compare the effectiveness of the policies induced by our proposed EM-EDM against four AL-based baselines and two policies induced by DRL on two different but related tasks that involve pedagogical action prediction. Our overall results showed that, for both tasks, EM-EDM outperforms the four AL baselines across all performance metrics and the two DRL baselines. This suggests that EM-EDM can effectively model complex student pedagogical decision-making processes through the ability to manage a large, continuous state space and adapt to handle diverse and heterogeneous reward functions with very few given demonstrations.

Addressing the challenge of effectively processing long contexts has become a critical issue for Large Language Models (LLMs). Two common strategies have emerged: 1) reducing the input length, such as retrieving relevant chunks by Retrieval-Augmented Generation (RAG), and 2) expanding the context window limit of LLMs. However, both strategies have drawbacks: input reduction has no guarantee of covering the part with needed information, while window extension struggles with focusing on the pertinent information for solving the task. To mitigate these limitations, we propose Chain-of-Agents (CoA), a novel framework that harnesses multi-agent collaboration through natural language to enable information aggregation and context reasoning across various LLMs over long-context tasks. CoA consists of multiple worker agents who sequentially communicate to handle different segmented portions of the text, followed by a manager agent who synthesizes these contributions into a coherent final output. CoA processes the entire input by interleaving reading and reasoning, and it mitigates long context focus issues by assigning each agent a short context. We perform comprehensive evaluation of CoA on a wide range of long-context tasks in question answering, summarization, and code completion, demonstrating significant improvements by up to 10% over strong baselines of RAG, Full-Context, and multi-agent LLMs.

Class-incremental learning (CIL) aims to train a model to learn new classes from non-stationary data streams without forgetting old ones. In this paper, we propose a new kind of connectionist model by tailoring neural unit dynamics that adapt the behavior of neural networks for CIL. In each training session, it introduces a supervisory mechanism to guide network expansion whose growth size is compactly commensurate with the intrinsic complexity of a newly arriving task. This constructs a near-minimal network while allowing the model to expand its capacity when cannot sufficiently hold new classes. At inference time, it automatically reactivates the required neural units to retrieve knowledge and leaves the remaining inactivated to prevent interference. We name our model AutoActivator, which is effective and scalable. To gain insights into the neural unit dynamics, we theoretically analyze the model's convergence property via a universal approximation theorem on learning sequential mappings, which is under-explored in the CIL community. Experiments show that our method achieves strong CIL performance in rehearsal-free and minimal-expansion settings with different backbones.

Plain language summarization with LLMs can be useful for improving textual accessibility of technical content. But how factual are these summaries in a high-stakes domain like medicine? This paper presents FactPICO, a factuality benchmark for plain language summarization of medical texts describing randomized controlled trials (RCTs), which are the basis of evidence-based medicine and can directly inform patient treatment. FactPICO consists of 345 plain language summaries of RCT abstracts generated from three LLMs (i.e., GPT-4, Llama-2, and Alpaca), with fine-grained evaluation and natural language rationales from experts. We assess the factuality of critical elements of RCTs in those summaries: Populations, Interventions, Comparators, Outcomes (PICO), as well as the reported findings concerning these. We also evaluate the correctness of the extra information (e.g., explanations) added by LLMs. Using FactPICO, we benchmark a range of existing factuality metrics, including the newly devised ones based on LLMs. We find that plain language summarization of medical evidence is still challenging, especially when balancing between simplicity and factuality, and that existing metrics correlate poorly with expert judgments on the instance level.

The advancement of large language models (LLMs) has enhanced the ability to generalize across a wide range of unseen natural language processing (NLP) tasks through instruction-following. Yet, their effectiveness often diminishes in low-resource languages like Chinese, exacerbated by biased evaluations from data leakage, casting doubt on their true generalizability to new linguistic territories. In response, we introduce the Chinese Instruction-Following Benchmark (CIF-Bench), designed to evaluate the zero-shot generalizability of LLMs to the Chinese language. CIF-Bench comprises 150 tasks and 15,000 input-output pairs, developed by native speakers to test complex reasoning and Chinese cultural nuances across 20 categories. To mitigate data contamination, we release only half of the dataset publicly, with the remainder kept private, and introduce diversified instructions to minimize score variance, totaling 45,000 data instances. Our evaluation of 28 selected LLMs reveals a noticeable performance gap, with the best model scoring only 52.9%, highlighting the limitations of LLMs in less familiar language and task contexts. This work not only uncovers the current limitations of LLMs in handling Chinese language tasks but also sets a new standard for future LLM generalizability research, pushing towards the development of more adaptable, culturally informed, and linguistically diverse models.

We propose a novel class of Nesterov's stochastic accelerated forward-reflected-based methods with variance reduction to solve root-finding problems under $\frac{1}{L}$-co-coerciveness. Our algorithm is single-loop and leverages a new family of unbiased variance-reduced estimators specifically designed for root-finding problems. It achieves both $\mathcal{O}(L^2/k^2)$ and $o(1/k^2)$-last-iterate convergence rates in terms of expected operator squared norm, where $k$ denotes the iteration counter. We instantiate our framework for two prominent estimators: SVRG and SAGA. By an appropriate choice of parameters, both variants attain an oracle complexity of $\mathcal{O}( n + Ln^{2/3}\epsilon^{-1})$ to reach an $\epsilon$-solution, where $n$ represents the number of summands in the finite-sum operator. Furthermore, under $\mu$-strong quasi-monotonicity, our method achieves a linear convergence rate and an oracle complexity of $\mathcal{O}(n+ \kappa n^{2/3}\log(\epsilon^{-1}))$, where $\kappa := \frac{L}{\mu}$. We extend our approach to solve a class of finite-sum monotone inclusions, demonstrating that our schemes retain the same theoretical guarantees as in the equation setting. Finally, numerical experiments validate our algorithms and demonstrate their promising performance compared to state-of-the-art methods.

In an era characterized by rapid societal changes and complex challenges, institutions' traditional methods of problem-solving in the public sector are increasingly proving inadequate. In this study, we present an innovative and effective model for how institutions can use artificial intelligence to enable groups of people to generate effective solutions to urgent problems more efficiently. We describe a proven collective intelligence method, called Smarter Crowdsourcing, which is designed to channel the collective intelligence of those with expertise about a problem into actionable solutions through crowdsourcing. Then we introduce Policy Synth, an innovative toolkit which leverages AI to make the Smarter Crowdsourcing problem-solving approach both more scalable, more effective and more efficient. Policy Synth is crafted using a human-centric approach, recognizing that AI is a tool to enhance human intelligence and creativity, not replace it. Based on a real-world case study comparing the results of expert crowdsourcing alone with expert sourcing supported by Policy Synth AI agents, we conclude that Smarter Crowdsourcing with Policy Synth presents an effective model for integrating the collective wisdom of human experts and the computational power of AI to enhance and scale up public problem-solving processes. While many existing approaches view AI as a tool to make crowdsourcing and deliberative processes better and more efficient, Policy Synth goes a step further, recognizing that AI can also be used to synthesize the findings from engagements together with research to develop evidence-based solutions and policies. The study offers practical tools and insights for institutions looking to engage communities effectively in addressing urgent societal challenges.