AI auditing is a rapidly growing field of research and practice. This review article, which doubles as an editorial to Digital Societys topical collection on Auditing of AI, provides an overview of previous work in the field. Three key points emerge from the review. First, contemporary attempts to audit AI systems have much to learn from how audits have historically been structured and conducted in areas like financial accounting, safety engineering and the social sciences. Second, both policymakers and technology providers have an interest in promoting auditing as an AI governance mechanism. Academic researchers can thus fill an important role by studying the feasibility and effectiveness of different AI auditing procedures. Third, AI auditing is an inherently multidisciplinary undertaking, to which substantial contributions have been made by computer scientists and engineers as well as social scientists, philosophers, legal scholars and industry practitioners. Reflecting this diversity of perspectives, different approaches to AI auditing have different affordances and constraints. Specifically, a distinction can be made between technology-oriented audits, which focus on the properties and capabilities of AI systems, and process oriented audits, which focus on technology providers governance structures and quality management systems. The next step in the evolution of auditing as an AI governance mechanism, this article concludes, should be the interlinking of these available (and complementary) approaches into structured and holistic procedures to audit not only how AI systems are designed and used but also how they impact users, societies and the natural environment in applied settings over time.

One of the most reliable ways to create deployable models for specialized tasks is to obtain an adequate amount of high-quality task-specific data. However, for specialized tasks, often such datasets do not exist. Existing methods address this by creating such data from large language models (LLMs) and then distilling such knowledge into smaller models. However, these methods are limited by the quality of the LLMs output, and tend to generate repetitive or incorrect data. In this work, we present Retrieval Based Distillation (ReBase), a method that first retrieves data from rich online sources and then transforms them into domain-specific data. This method greatly enhances data diversity. Moreover, ReBase generates Chain-of-Thought reasoning and distills the reasoning capacity of LLMs. We test our method on 4 benchmarks and results show that our method significantly improves performance by up to 7.8% on SQuAD, 1.37% on MNLI, and 1.94% on BigBench-Hard.

Human culture relies on collective innovation: our ability to continuously explore how existing elements in our environment can be combined to create new ones. Language is hypothesized to play a key role in human culture, driving individual cognitive capacities and shaping communication. Yet the majority of models of collective innovation assign no cognitive capacities or language abilities to agents. Here, we contribute a computational study of collective innovation where agents are Large Language Models (LLMs) that play Little Alchemy 2, a creative video game originally developed for humans that, as we argue, captures useful aspects of innovation landscapes not present in previous test-beds. We, first, study an LLM in isolation and discover that it exhibits both useful skills and crucial limitations. We, then, study groups of LLMs that share information related to their behaviour and focus on the effect of social connectivity on collective performance. In agreement with previous human and computational studies, we observe that groups with dynamic connectivity out-compete fully-connected groups. Our work reveals opportunities and challenges for future studies of collective innovation that are becoming increasingly relevant as Generative Artificial Intelligence algorithms and humans innovate alongside each other.

The ability of large language models (LLMs) to mimic human-like intelligence has led to a surge in LLM-based autonomous agents. Though recent LLMs seem capable of planning and reasoning given user instructions, their effectiveness in applying these capabilities for autonomous task solving remains underexplored. This is especially true in enterprise settings, where automated agents hold the promise of a high impact. To fill this gap, we propose WorkArena++, a novel benchmark consisting of 682 tasks corresponding to realistic workflows routinely performed by knowledge workers. WorkArena++ is designed to evaluate the planning, problem-solving, logical/arithmetic reasoning, retrieval, and contextual understanding abilities of web agents. Our empirical studies across state-of-the-art LLMs and vision-language models (VLMs), as well as human workers, reveal several challenges for such models to serve as useful assistants in the workplace. In addition to the benchmark, we provide a mechanism to effortlessly generate thousands of ground-truth observation/action traces, which can be used for fine-tuning existing models. Overall, we expect this work to serve as a useful resource to help the community progress toward capable autonomous agents.

The rapid expansion of large foundation models within the pre-training and fine-tuning framework has underscored that larger models often yield better results. However, the scaling up of large foundation models has led to soaring costs in fine-tuning and parameter storage, rendering extensive adaptations impractical. This challenge has sparked the development of parameter-efficient fine-tuning (PEFT), which focuses on optimizing a select subset of parameters while keeping the rest fixed, significantly lowering computational and storage overheads. While recent years have witnessed a significant success in PEFT, a deep understanding of the fundamental principles behind these methods remains unexplored. To this end, here we take the first step to unify all approaches by dissecting them from a decomposition perspective. We initiate a comprehensive mathematical analysis of these methods, allowing us to delve deeply into their underlying mechanisms, and we explore the reasons behind the variations in performance among different techniques. Furthermore, inspired by our theoretical analysis, we introduce two novel PEFT methods alongside a simple yet effective framework designed to enhance the performance of PEFT techniques across various applications. Our empirical validations, conducted across multiple datasets, demonstrate the efficacy of these methods, showcasing both theoretical validity and practical performance improvements under the guidance of our analytical findings. We believe our work will deepen researchers' understanding of PEFT and other techniques, prompting further contemplation and advancing the research across the whole community.

Large language models (LLMs) show remarkable human-like capability in various domains and languages. However, a notable quality gap arises in low-resource languages, e.g., Indonesian indigenous languages, rendering them ineffective and inefficient in such linguistic contexts. To bridge this quality gap, we introduce Cendol, a collection of Indonesian LLMs encompassing both decoder-only and encoder-decoder architectures across a range of model sizes. We highlight Cendol's effectiveness across a diverse array of tasks, attaining 20% improvement, and demonstrate its capability to generalize to unseen tasks and indigenous languages of Indonesia. Furthermore, Cendol models showcase improved human favorability despite their limitations in capturing indigenous knowledge and cultural values in Indonesia. In addition, we discuss the shortcomings of parameter-efficient tunings, such as LoRA, for language adaptation. Alternatively, we propose the usage of vocabulary adaptation to enhance efficiency. Lastly, we evaluate the safety of Cendol and showcase that safety in pre-training in one language such as English is transferable to low-resource languages, such as Indonesian, even without RLHF and safety fine-tuning.

Detecting hallucinations in large language model (LLM) outputs is pivotal, yet traditional fine-tuning for this classification task is impeded by the expensive and quickly outdated annotation process, especially across numerous vertical domains and in the face of rapid LLM advancements. In this study, we introduce an approach that automatically generates both faithful and hallucinated outputs by rewriting system responses. Experimental findings demonstrate that a T5-base model, fine-tuned on our generated dataset, surpasses state-of-the-art zero-shot detectors and existing synthetic generation methods in both accuracy and latency, indicating efficacy of our approach.

Language technologies should be judged on their usefulness in real-world use cases. An often overlooked aspect in natural language processing (NLP) research and evaluation is language variation in the form of non-standard dialects or language varieties (hereafter, varieties). Most NLP benchmarks are limited to standard language varieties. To fill this gap, we propose DIALECTBENCH, the first-ever large-scale benchmark for NLP on varieties, which aggregates an extensive set of task-varied variety datasets (10 text-level tasks covering 281 varieties). This allows for a comprehensive evaluation of NLP system performance on different language varieties. We provide substantial evidence of performance disparities between standard and non-standard language varieties, and we also identify language clusters with large performance divergence across tasks. We believe DIALECTBENCH provides a comprehensive view of the current state of NLP for language varieties and one step towards advancing it further. Code/data: https://github.com/ffaisal93/DialectBench

While large language models (LLMs) have shown remarkable capabilities in natural language processing, they struggle with complex, multi-step reasoning tasks involving knowledge graphs (KGs). Existing approaches that integrate LLMs and KGs either underutilize the reasoning abilities of LLMs or suffer from prohibitive computational costs due to tight coupling. To address these limitations, we propose a novel collaborative framework named EffiQA that can strike a balance between performance and efficiency via an iterative paradigm. EffiQA consists of three stages: global planning, efficient KG exploration, and self-reflection. Specifically, EffiQA leverages the commonsense capability of LLMs to explore potential reasoning pathways through global planning. Then, it offloads semantic pruning to a small plug-in model for efficient KG exploration. Finally, the exploration results are fed to LLMs for self-reflection to further improve the global planning and efficient KG exploration. Empirical evidence on multiple KBQA benchmarks shows EffiQA's effectiveness, achieving an optimal balance between reasoning accuracy and computational costs. We hope the proposed new framework will pave the way for efficient, knowledge-intensive querying by redefining the integration of LLMs and KGs, fostering future research on knowledge-based question answering.

Large language models~(LLMs) have demonstrated impressive performance in various applications, among which role-playing language agents (RPLAs) have engaged a broad user base. Now, there is a growing demand for RPLAs that represent Key Opinion Leaders (KOLs), \ie, Internet celebrities who shape the trends and opinions in their domains. However, research in this line remains underexplored. In this paper, we hence introduce MINDECHO, a comprehensive framework for the development and evaluation of KOL RPLAs. MINDECHO collects KOL data from Internet video transcripts in various professional fields, and synthesizes their conversations leveraging GPT-4. Then, the conversations and the transcripts are used for individualized model training and inference-time retrieval, respectively. Our evaluation covers both general dimensions (\ie, knowledge and tones) and fan-centric dimensions for KOLs. Extensive experiments validate the effectiveness of MINDECHO in developing and evaluating KOL RPLAs.