This paper presents our research towards a near-term future in which legal entities, such as individuals and organisations can entrust semi-autonomous AI-driven agents to carry out online interactions on their behalf. The author's research concerns the development of semi-autonomous Web agents, which consult users if and only if the system does not have sufficient context or confidence to proceed working autonomously. This creates a user-agent dialogue that allows the user to teach the agent about the information sources they trust, their data-sharing preferences, and their decision-making preferences. Ultimately, this enables the user to maximise control over their data and decisions while retaining the convenience of using agents, including those driven by LLMs. In view of developing near-term solutions, the research seeks to answer the question: "How do we build a trustworthy and reliable network of semi-autonomous agents which represent individuals and organisations on the Web?". After identifying key requirements, the paper presents a demo for a sample use case of a generic personal assistant. This is implemented using (Notation3) rules to enforce safety guarantees around belief, data sharing and data usage and LLMs to allow natural language interaction with users and serendipitous dialogues between software agents.

The amount of training compute used by frontier large language models (LLMs) increased by 5000x between the release of GPT-2 in 2019 and GPT-4 in 2023 and estimates from Epoch AI suggest a similar increase over the next six years. How does this massive increase in model training compute map onto performance? The empirical machine learning literature has derived remarkably consistent'scaling laws' suggesting a strong relationship between a model's training compute and model perplexity, a measure of model loss, across more than seven orders of magnitude. But there is so far a very limited understanding of how this reduction in perplexity affects key economic and social outcomes. This paper aims to offer the first experimental evidence on this question by conducting a randomized controlled trial(RCT) involving 300 professional translators conducting 1800 tasks of varying complexities. The participants were randomly assigned to either treatment groups where they could utilize one of thirteen LLMs of differing model training compute to help them complete their task or to a control group where they completed tasks without any AI assistance. Participants face high-powered incentives with significant bonus payments for high-quality tasks as evaluated by three experienced professionals in the field. The key outcome variables, therefore, were how translator's time taken, quality of tasks completed, and earnings per minute (inclusive of bonuses) varied by model training compute.

Large language models (LLMs) have demonstrated remarkable capacities across a variety of language tasks, showcasing their broad-ranging capabilities in natural language processing. Notable models include ChatGPT (OpenAI, 2023), Claude (Anthropic, 2023), and Gemini (Team et al., 2023). However, despite these advances, even the most advanced closed-source LLMs still struggle with complex reasoning tasks that require multi-rounds of decision making. In particular, for the representative task of mathematical problem solving, LLMs often fail with basic arithmetic and symbolic computations (Cobbe et al., 2021b; Hendrycks et al., 2021; Zheng et al., 2021). To address this issue, recent studies recommend the integration of external tools (e.g., calculators, computational Python libraries and symbolic solvers) to augment the LLMs' mathematical problem-solving capabilities (Cobbe et al., 2021b; Mishra et al., 2022; Shao et al., 2022; Zhang et al., 2024a). Specifically, by integrating natural language reasoning with the use of these external tools, these enhanced LLMs can receive external messages from tool interactions and reason based on both previously generated tokens and external messages, which significantly improves their performance in mathematical tasks (Gou et al., 2023b; Shao et al., 2024; Toshniwal et al., 2024). These successes of tool-integrated LLMs lead to a natural research question: how can we better train LLMs to combine tool usage with intrinsic reasoning to tackle complex reasoning tasks? For the mathematical problem solving task, existing works primarily focus on synthetic data generation (by a strong teacher model) and supervised fine-tuning (SFT), as seen in ToRA (Gou et al., 2023b), Meta-Work done during an internship at Google DeepMind. A preliminary draft without the results of Gemma-2 had been circulated internally in early July.

Specifically focusing on the landscape of abstractive text summarization, as opposed to extractive techniques, this survey presents a comprehensive overview, delving into state-of-the-art techniques, prevailing challenges, and prospective research directions. We categorize the techniques into traditional sequence-to-sequence models, pre-trained large language models, reinforcement learning, hierarchical methods, and multi-modal summarization. Unlike prior works that did not examine complexities, scalability and comparisons of techniques in detail, this review takes a comprehensive approach encompassing state-of-the-art methods, challenges, solutions, comparisons, limitations and charts out future improvements - providing researchers an extensive overview to advance abstractive summarization research. We provide vital comparison tables across techniques categorized - offering insights into model complexity, scalability and appropriate applications. The paper highlights challenges such as inadequate meaning representation, factual consistency, controllable text summarization, cross-lingual summarization, and evaluation metrics, among others. Solutions leveraging knowledge incorporation and other innovative strategies are proposed to address these challenges. The paper concludes by highlighting emerging research areas like factual inconsistency, domain-specific, cross-lingual, multilingual, and long-document summarization, as well as handling noisy data. Our objective is to provide researchers and practitioners with a structured overview of the domain, enabling them to better understand the current landscape and identify potential areas for further research and improvement.

Recent advancements in natural language processing, particularly with large language models (LLMs) like GPT-4, have significantly enhanced dialogue systems, enabling them to generate more natural and fluent conversations. Despite these improvements, challenges persist, such as managing continuous dialogues, memory retention, and minimizing hallucinations. The AIWolfDial2024 addresses these challenges by employing the Werewolf Game, an incomplete information game, to test the capabilities of LLMs in complex interactive environments. This paper introduces a LLM-based Werewolf Game AI, where each role is supported by situation analysis to aid response generation. Additionally, for the werewolf role, various persuasion strategies, including logical appeal, credibility appeal, and emotional appeal, are employed to effectively persuade other players to align with its actions.

Situation awareness is essential for understanding and reasoning about 3D scenes in embodied AI agents. However, existing datasets and benchmarks for situated understanding are limited in data modality, diversity, scale, and task scope. To address these limitations, we propose Multi-modal Situated Question Answering (MSQA), a large-scale multi-modal situated reasoning dataset, scalably collected leveraging 3D scene graphs and vision-language models (VLMs) across a diverse range of real-world 3D scenes. MSQA includes 251K situated question-answering pairs across 9 distinct question categories, covering complex scenarios within 3D scenes. We introduce a novel interleaved multi-modal input setting in our benchmark to provide text, image, and point cloud for situation and question description, resolving ambiguity in previous single-modality convention (e.g., text). Additionally, we devise the Multi-modal Situated Next-step Navigation (MSNN) benchmark to evaluate models' situated reasoning for navigation. Comprehensive evaluations on MSQA and MSNN highlight the limitations of existing vision-language models and underscore the importance of handling multi-modal interleaved inputs and situation modeling. Experiments on data scaling and cross-domain transfer further demonstrate the efficacy of leveraging MSQA as a pre-training dataset for developing more powerful situated reasoning models.

Detecting anomalies or out-of-distribution (OOD) samples is critical for maintaining the reliability and trustworthiness of machine learning systems. Recently, Large Language Models (LLMs) have demonstrated their effectiveness not only in natural language processing but also in broader applications due to their advanced comprehension and generative capabilities. The integration of LLMs into anomaly and OOD detection marks a significant shift from the traditional paradigm in the field. This survey focuses on the problem of anomaly and OOD detection under the context of LLMs. We propose a new taxonomy to categorize existing approaches into three classes based on the role played by LLMs. Following our proposed taxonomy, we further discuss the related work under each of the categories and finally discuss potential challenges and directions for future research in this field. We also provide an up-to-date reading list of relevant papers.

The relation extraction (RE) in complex scenarios faces challenges such as diverse relation types and ambiguous relations between entities within a single sentence, leading to the poor performance of pure "text-in, text-out" language models (LMs). To address these challenges, in this paper, we propose an agent-based RE framework, namely AgentRE, which fully leverages the potential of large language models (LLMs) including memory, retrieval and reflection, to achieve RE in complex scenarios. Specifically, three major modules are built in AgentRE serving as the tools to help the agent acquire and process various useful information, thereby obtaining improved RE performance. Our extensive experimental results upon two datasets in English and Chinese demonstrate our AgentRE's superior performance, especially in low-resource scenarios. Additionally, the trajectories generated by AgentRE can be refined to construct a high-quality training dataset incorporating different reasoning methods, which can be used to fine-tune smaller models. Code is available at https://github.com/Lightblues/AgentRE.

This paper explores the potential of using Large Language Models (LLMs) to automate the evaluation of responses in medical Question and Answer (Q\&A) systems, a crucial form of Natural Language Processing. Traditionally, human evaluation has been indispensable for assessing the quality of these responses. However, manual evaluation by medical professionals is time-consuming and costly. Our study examines whether LLMs can reliably replicate human evaluations by using questions derived from patient data, thereby saving valuable time for medical experts. While the findings suggest promising results, further research is needed to address more specific or complex questions that were beyond the scope of this initial investigation.

Given Large Language Models (LLMs) demonstrate proficiency this constrained context window, context distillation (CD) across diverse tasks but often require targeted adaptations extends accessible task-specific examples by internalizing for specific applications. Various methods have them, greatly increasing the number of available examples been proposed to facilitate this adaptation, including fewshot outside of the query prompt [1]. This not only limits the fine-tuning, in-context learning, and context distillation.