After OpenAI released GPT-3 in July 2020, independent artificial intelligence researcher Shawn Presser and a few of his fellow machine-learning enthusiasts set a challenge for themselves: Could they recreate it? "We were like, OK, there's actually not that much standing in the way of us doing this ourselves," Presser says. So what if OpenAI had deep pockets and a head start? That summer, they pored over papers about GPT-3, strategizing in marathon Discord chats about how to best approximate its training data sets. Presser honed in on the books they needed.

Taxonomies represent hierarchical relations between entities, frequently applied in various software modeling and natural language processing (NLP) activities. They are typically subject to a set of structural constraints restricting their content. However, manual taxonomy construction can be time-consuming, incomplete, and costly to maintain. Recent studies of large language models (LLMs) have demonstrated that appropriate user inputs (called prompting) can effectively guide LLMs, such as GPT-3, in diverse NLP tasks without explicit (re-)training. However, existing approaches for automated taxonomy construction typically involve fine-tuning a language model by adjusting model parameters. In this paper, we present a general framework for taxonomy construction that takes into account structural constraints. We subsequently conduct a systematic comparison between the prompting and fine-tuning approaches performed on a hypernym taxonomy and a novel computer science taxonomy dataset. Our result reveals the following: (1) Even without explicit training on the dataset, the prompting approach outperforms fine-tuning-based approaches. Moreover, the performance gap between prompting and fine-tuning widens when the training dataset is small. However, (2) taxonomies generated by the fine-tuning approach can be easily post-processed to satisfy all the constraints, whereas handling violations of the taxonomies produced by the prompting approach can be challenging. These evaluation findings provide guidance on selecting the appropriate method for taxonomy construction and highlight potential enhancements for both approaches.

Large language models, in particular generative pre-trained transformers (GPTs), show impressive results on a wide variety of language-related tasks. In this paper, we explore ChatGPT's zero-shot ability to perform affective computing tasks using prompting alone. We show that ChatGPT a) performs meaningful sentiment analysis in the Valence, Arousal and Dominance dimensions, b) has meaningful emotion representations in terms of emotion categories and these affective dimensions, and c) can perform basic appraisal-based emotion elicitation of situations based on a prompt-based computational implementation of the OCC appraisal model. These findings are highly relevant: First, they show that the ability to solve complex affect processing tasks emerges from language-based token prediction trained on extensive data sets. Second, they show the potential of large language models for simulating, processing and analyzing human emotions, which has important implications for various applications such as sentiment analysis, socially interactive agents, and social robotics.

Large vision-language models (LVLMs) have recently witnessed rapid advancements, exhibiting a remarkable capacity for perceiving, understanding, and processing visual information by connecting visual receptor with large language models (LLMs). However, current assessments mainly focus on recognizing and reasoning abilities, lacking direct evaluation of conversational skills and neglecting visual storytelling abilities. In this paper, we propose an evaluation method that uses strong LLMs as judges to comprehensively evaluate the various abilities of LVLMs. Firstly, we construct a comprehensive visual dialogue dataset TouchStone, consisting of open-world images and questions, covering five major categories of abilities and 27 subtasks. This dataset not only covers fundamental recognition and comprehension but also extends to literary creation. Secondly, by integrating detailed image annotations we effectively transform the multimodal input content into a form understandable by LLMs. This enables us to employ advanced LLMs for directly evaluating the quality of the multimodal dialogue without requiring human intervention. Through validation, we demonstrate that powerful LVLMs, such as GPT-4, can effectively score dialogue quality by leveraging their textual capabilities alone, aligning with human preferences. We hope our work can serve as a touchstone for LVLMs' evaluation and pave the way for building stronger LVLMs. The evaluation code is available at https://github.com/OFA-Sys/TouchStone.

Instruction-tuning has become an integral part of training pipelines for Large Language Models (LLMs) and has been shown to yield strong performance gains. In an orthogonal line of research, Annotation Error Detection (AED) has emerged as a tool for detecting quality issues of gold-standard labels. But so far, the application of AED methods is limited to discriminative settings. It is an open question how well AED methods generalize to generative settings which are becoming widespread via generative LLMs. In this work, we present a first and new benchmark for AED on instruction-tuning data: Donkii. It encompasses three instruction-tuning datasets enriched with annotations by experts and semi-automatic methods. We find that all three datasets contain clear-cut errors that sometimes directly propagate into instruction-tuned LLMs. We propose four AED baselines for the generative setting and evaluate them comprehensively on the newly introduced dataset. Our results demonstrate that choosing the right AED method and model size is indeed crucial, thereby deriving practical recommendations. To gain insights, we provide a first case-study to examine how the quality of the instruction-tuning datasets influences downstream performance.

This article focuses on bibliographic references generated by the ChatGPT3.5 tool. Using this tool based on the trained GPT generation model ChatGPT3.5, developed by the company OpenAI, we explored six different themes and analyzed a sample of references generated by the model, in French and English. The results revealed high percentages of fictitious references in several fields, underlining the importance of carefully checking these references before using them in research work. An improvement in results was nevertheless noted between May and July with regard to English references for themes on which ChatGPR3.5 has been particularly trained, but the situation remains unsatisfactory in French, for example. It should also be pointed out that much of the text in this article was generated by ChatGPT in a joint effort with the human author.

Objective: To evaluate the efficiency of large language models (LLMs) such as ChatGPT to assist in diagnosing neuro-ophthalmic diseases based on detailed case descriptions. Methods: We selected 22 different case reports of neuro-ophthalmic diseases from a publicly available online database. These cases included a wide range of chronic and acute diseases that are commonly seen by neuro-ophthalmic sub-specialists. We inserted the text from each case as a new prompt into both ChatGPT v3.5 and ChatGPT Plus v4.0 and asked for the most probable diagnosis. We then presented the exact information to two neuro-ophthalmologists and recorded their diagnoses followed by comparison to responses from both versions of ChatGPT. Results: ChatGPT v3.5, ChatGPT Plus v4.0, and the two neuro-ophthalmologists were correct in 13 (59%), 18 (82%), 19 (86%), and 19 (86%) out of 22 cases, respectively. The agreement between the various diagnostic sources were as follows: ChatGPT v3.5 and ChatGPT Plus v4.0, 13 (59%); ChatGPT v3.5 and the first neuro-ophthalmologist, 12 (55%); ChatGPT v3.5 and the second neuro-ophthalmologist, 12 (55%); ChatGPT Plus v4.0 and the first neuro-ophthalmologist, 17 (77%); ChatGPT Plus v4.0 and the second neuro-ophthalmologist, 16 (73%); and first and second neuro-ophthalmologists 17 (17%). Conclusions: The accuracy of ChatGPT v3.5 and ChatGPT Plus v4.0 in diagnosing patients with neuro-ophthalmic diseases was 59% and 82%, respectively. With further development, ChatGPT Plus v4.0 may have potential to be used in clinical care settings to assist clinicians in providing quick, accurate diagnoses of patients in neuro-ophthalmology. The applicability of using LLMs like ChatGPT in clinical settings that lack access to subspeciality trained neuro-ophthalmologists deserves further research.

3D printing or additive manufacturing is a revolutionary technology that enables the creation of physical objects from digital models. However, the quality and accuracy of 3D printing depend on the correctness and efficiency of the G-code, a low-level numerical control programming language that instructs 3D printers how to move and extrude material. Debugging G-code is a challenging task that requires a syntactic and semantic understanding of the G-code format and the geometry of the part to be printed. In this paper, we present the first extensive evaluation of six state-of-the-art foundational large language models (LLMs) for comprehending and debugging G-code files for 3D printing. We design effective prompts to enable pre-trained LLMs to understand and manipulate G-code and test their performance on various aspects of G-code debugging and manipulation, including detection and correction of common errors and the ability to perform geometric transformations. We analyze their strengths and weaknesses for understanding complete G-code files. We also discuss the implications and limitations of using LLMs for G-code comprehension.

"Once the machine thinking method had started, it would not take long to outstrip our feeble powers. At some stage therefore we should have to expect the machines to take control" Alan Turing 1951 [35] AGI [91] safety is of the utmost urgency, since corporations and research labs are racing to build AGI despite prominent AI researchers and business leaders warning that it may lead to human extinction [11]. While governments are drafting AI regulations, there's little indication that they will be sufficient to resist competitive pressures and prevent the creation of AGI. Median estimates on the forecasting platform Metaculus of the date of AGI's creation have plummeted over the past few years from many decades away to 2027 [25] or 2032 [24] depending on definitions, with superintelligence expected to follow a few years later [23]. Is Alan Turing correct that we now "have to expect the machines to take control"?

The rapid advancement of large language models, such as the Generative Pre-trained Transformer (GPT) series, has had significant implications across various disciplines. In this study, we investigate the potential of the state-of-the-art large language model (GPT-4) for planning tasks. We explore its effectiveness in multiple planning subfields, highlighting both its strengths and limitations. Through a comprehensive examination, we identify areas where large language models excel in solving planning problems and reveal the constraints that limit their applicability. Our empirical analysis focuses on GPT-4's performance in planning domain extraction, graph search path planning, and adversarial planning. We then propose a way of fine-tuning a domain-specific large language model to improve its Chain of Thought (CoT) capabilities for the above-mentioned tasks. The results provide valuable insights into the potential applications of large language models in the planning domain and pave the way for future research to overcome their limitations and expand their capabilities.