Open-domain generative systems have gained significant attention in the field of conversational AI (e.g., generative search engines). This paper presents a comprehensive review of the attribution mechanisms employed by these systems, particularly large language models. Though attribution or citation improve the factuality and verifiability, issues like ambiguous knowledge reservoirs, inherent biases, and the drawbacks of excessive attribution can hinder the effectiveness of these systems. The aim of this survey is to provide valuable insights for researchers, aiding in the refinement of attribution methodologies to enhance the reliability and veracity of responses generated by open-domain generative systems. We believe that this field is still in its early stages; hence, we maintain a repository to keep track of ongoing studies at https://github.com/HITsz-TMG/awesome-llm-attributions.

The integration of Large Language Models (LLMs) like ChatGPT into the workflows of geotechnical engineering has a high potential to transform how the discipline approaches problem-solving and decision-making. This paper delves into the innovative application of LLMs in geotechnical engineering, as explored in a hands-on workshop held in Tokyo, Japan. The event brought together a diverse group of 20 participants, including students, researchers, and professionals from academia, industry, and government sectors, to investigate practical uses of LLMs in addressing specific geotechnical challenges. The workshop facilitated the creation of solutions for four different practical geotechnical problems as illustrative examples, culminating in the development of an academic paper. The paper discusses the potential of LLMs to transform geotechnical engineering practices, highlighting their proficiency in handling a range of tasks from basic data analysis to complex, multimodal problem-solving. It also addresses the challenges in implementing LLMs, particularly in achieving high precision and accuracy in specialized tasks, and underscores the need for expert oversight. The findings demonstrate LLMs' effectiveness in enhancing efficiency, data processing, and decision-making in geotechnical engineering, suggesting a paradigm shift towards more integrated, data-driven approaches in this field. This study not only showcases the potential of LLMs in a specific engineering domain, but also sets a precedent for their broader application in interdisciplinary research and practice, where the synergy of human expertise and artificial intelligence redefines the boundaries of problem-solving.

As coding challenges become more complex, recent advancements in Large Language Models (LLMs) have led to notable successes, such as achieving a 94.6\% solve rate on the HumanEval benchmark. Concurrently, there is an increasing commercial push for repository-level inline code completion tools, such as GitHub Copilot and Tab Nine, aimed at enhancing developer productivity. This paper delves into the transition from individual coding problems to repository-scale solutions, presenting a thorough review of the current literature on effective LLM prompting for code generation at the repository level. We examine approaches that will work with black-box LLMs such that they will be useful and applicable to commercial use cases, and their applicability in interpreting code at a repository scale. We juxtapose the Repository-Level Prompt Generation technique with RepoCoder, an iterative retrieval and generation method, to highlight the trade-offs inherent in each approach and to establish best practices for their application in cutting-edge coding benchmarks. The interplay between iterative refinement of prompts and the development of advanced retrieval systems forms the core of our discussion, offering a pathway to significantly improve LLM performance in code generation tasks. Insights from this study not only guide the application of these methods but also chart a course for future research to integrate such techniques into broader software engineering contexts.

A core function of intelligence is grounding, which is the process of connecting the natural language and abstract knowledge to the internal representation of the real world in an intelligent being, e.g., a human. Human cognition is grounded in our sensorimotor experiences in the external world and subjective feelings in our internal world. We use languages to communicate with each other and the languages are grounded on our shared sensorimotor experiences and feelings. Without this shard grounding, it is impossible for us to understand each other because all natural languages are highly abstract and are only able to describe a tiny portion of what has happened or is happening in the real world. Although grounding at high or abstract levels has been studied in different fields and applications, to our knowledge, limited systematic work at fine-grained levels has been done. With the rapid progress of large language models (LLMs), it is imperative that we have a sound understanding of grounding in order to move to the next level of intelligence. It is also believed that grounding is necessary for Artificial General Intelligence (AGI). This paper makes an attempt to systematically study this problem.

This paper explores the potential of a multidisciplinary approach to testing and aligning artificial general intelligence (AGI) and LLMs. Due to the rapid development and wide application of LLMs, challenges such as ethical alignment, controllability, and predictability of these models have become important research topics. This study investigates an innovative simulation-based multi-agent system within a virtual reality framework that replicates the real-world environment. The framework is populated by automated 'digital citizens,' simulating complex social structures and interactions to examine and optimize AGI. Application of various theories from the fields of sociology, social psychology, computer science, physics, biology, and economics demonstrates the possibility of a more human-aligned and socially responsible AGI. The purpose of such a digital environment is to provide a dynamic platform where advanced AI agents can interact and make independent decisions, thereby mimicking realistic scenarios. The actors in this digital city, operated by the LLMs, serve as the primary agents, exhibiting high degrees of autonomy. While this approach shows immense potential, there are notable challenges and limitations, most significantly the unpredictable nature of real-world social dynamics. This research endeavors to contribute to the development and refinement of AGI, emphasizing the integration of social, ethical, and theoretical dimensions for future research.

To address increasing compute demand from recent multi-model workloads with heavy models like large language models, we propose to deploy heterogeneous chiplet-based multi-chip module (MCM)-based accelerators. We develop an advanced scheduling framework for heterogeneous MCM accelerators that comprehensively consider complex heterogeneity and inter-chiplet pipelining. Our experiments using our framework on GPT-2 and ResNet-50 models on a 4-chiplet system have shown upto 2.2x and 1.9x increase in throughput and energy efficiency, compared to a monolithic accelerator with an optimized output-stationary dataflow.

Widely used alignment techniques, such as reinforcement learning from human feedback (RLHF), rely on the ability of humans to supervise model behavior - for example, to evaluate whether a model faithfully followed instructions or generated safe outputs. However, future superhuman models will behave in complex ways too difficult for humans to reliably evaluate; humans will only be able to weakly supervise superhuman models. We study an analogy to this problem: can weak model supervision elicit the full capabilities of a much stronger model? We test this using a range of pretrained language models in the GPT-4 family on natural language processing (NLP), chess, and reward modeling tasks. We find that when we naively finetune strong pretrained models on labels generated by a weak model, they consistently perform better than their weak supervisors, a phenomenon we call weak-to-strong generalization. However, we are still far from recovering the full capabilities of strong models with naive finetuning alone, suggesting that techniques like RLHF may scale poorly to superhuman models without further work. We find that simple methods can often significantly improve weak-to-strong generalization: for example, when finetuning GPT-4 with a GPT-2-level supervisor and an auxiliary confidence loss, we can recover close to GPT-3.5-level performance on NLP tasks. Our results suggest that it is feasible to make empirical progress today on a fundamental challenge of aligning superhuman models.

Climate change is one of the most significant challenges we face together as a society. Creating awareness and educating policy makers the wide-ranging impact of climate change is an essential step towards a sustainable future. Recently, Large Language Models (LLMs) like ChatGPT and Bard have shown impressive conversational abilities and excel in a wide variety of NLP tasks. While these models are close-source, recently alternative open-source LLMs such as Stanford Alpaca and Vicuna have shown promising results. However, these open-source models are not specifically tailored for climate related domain specific information and also struggle to generate meaningful responses in other languages such as, Arabic. To this end, we propose a light-weight Arabic Mini-ClimateGPT that is built on an open-source LLM and is specifically fine-tuned on a conversational-style instruction tuning curated Arabic dataset Clima500-Instruct with over 500k instructions about climate change and sustainability. Further, our model also utilizes a vector embedding based retrieval mechanism during inference. We validate our proposed model through quantitative and qualitative evaluations on climate-related queries. Our model surpasses the baseline LLM in 88.3% of cases during ChatGPT-based evaluation. Furthermore, our human expert evaluation reveals an 81.6% preference for our model's responses over multiple popular open-source models. Our open-source demos, code-base and models are available here https://github.com/mbzuai-oryx/ClimateGPT.

This paper introduces LLM-MARS, first technology that utilizes a Large Language Model based Artificial Intelligence for Multi-Agent Robot Systems. LLM-MARS enables dynamic dialogues between humans and robots, allowing the latter to generate behavior based on operator commands and provide informative answers to questions about their actions. LLM-MARS is built on a transformer-based Large Language Model, fine-tuned from the Falcon 7B model. We employ a multimodal approach using LoRa adapters for different tasks. The first LoRa adapter was developed by fine-tuning the base model on examples of Behavior Trees and their corresponding commands. The second LoRa adapter was developed by fine-tuning on question-answering examples. Practical trials on a multi-agent system of two robots within the Eurobot 2023 game rules demonstrate promising results. The robots achieve an average task execution accuracy of 79.28% in compound commands. With commands containing up to two tasks accuracy exceeded 90%. Evaluation confirms the system's answers on operators questions exhibit high accuracy, relevance, and informativeness. LLM-MARS and similar multi-agent robotic systems hold significant potential to revolutionize logistics, enabling autonomous exploration missions and advancing Industry 5.0.

Safe deployment of large language models (LLMs) may benefit from a reliable method for assessing their generated content to determine when to abstain or to selectively generate. While likelihood-based metrics such as perplexity are widely employed, recent research has demonstrated the limitations of using sequence-level probability estimates given by LLMs as reliable indicators of generation quality. Conversely, LLMs have demonstrated strong calibration at the token level, particularly when it comes to choosing correct answers in multiple-choice questions or evaluating true/false statements. In this work, we reformulate open-ended generation tasks into token-level prediction tasks, and leverage LLMs' superior calibration at the token level. We instruct an LLM to self-evaluate its answers, employing either a multi-way comparison or a point-wise evaluation approach, with the option to include a ``None of the above'' option to express the model's uncertainty explicitly. We benchmark a range of scoring methods based on self-evaluation and evaluate their performance in selective generation using TruthfulQA and TL;DR. Through experiments with PaLM-2 and GPT-3, we demonstrate that self-evaluation based scores not only improve accuracy, but also correlate better with the overall quality of generated content.