Given that language models are trained on vast datasets that may contain inherent biases, there is a potential danger of inadvertently perpetuating systemic discrimination. Consequently, it becomes essential to examine and address biases in language models, integrating fairness into their development to ensure these models are equitable and free from bias. In this work, we demonstrate the importance of reasoning in zero-shot stereotype identification based on Vicuna-13B-v1.3. While we do observe improved accuracy by scaling from 13B to 33B, we show that the performance gain from reasoning significantly exceeds the gain from scaling up. Our findings suggest that reasoning could be a key factor that enables LLMs to trescend the scaling law on out-of-domain tasks such as stereotype identification. Additionally, through a qualitative analysis of select reasoning traces, we highlight how reasoning enhances not just accuracy but also the interpretability of the decision.

This study presents a comparative analysis of three Generative Pre-trained Transformer (GPT) solutions in a question and answer (Q&A) setting: Drug-GPT 3, Drug-GPT 4, and ChatGPT, in the context of healthcare applications. The objective is to determine which model delivers the most accurate and relevant information in response to prompts related to patient experiences with atopic dermatitis (AD) and healthcare professional (HCP) discussions about diabetes. The results demonstrate that while all three models are capable of generating relevant and accurate responses, Drug-GPT 3 and Drug-GPT 4, which are supported by curated datasets of patient and HCP social media and message board posts, provide more targeted and in-depth insights. ChatGPT, a more general-purpose model, generates broader and more general responses, which may be valuable for readers seeking a high-level understanding of the topics but may lack the depth and personal insights found in the answers generated by the specialized Drug-GPT models. This comparative analysis highlights the importance of considering the language model's perspective, depth of knowledge, and currency when evaluating the usefulness of generated information in healthcare applications.

This guide introduces Large Language Models (LLM) as a highly versatile text analysis method within the social sciences. As LLMs are easy-to-use, cheap, fast, and applicable on a broad range of text analysis tasks, ranging from text annotation and classification to sentiment analysis and critical discourse analysis, many scholars believe that LLMs will transform how we do text analysis. This how-to guide is aimed at students and researchers with limited programming experience, and offers a simple introduction to how LLMs can be used for text analysis in your own research project, as well as advice on best practices. We will go through each of the steps of analyzing textual data with LLMs using Python: installing the software, setting up the API, loading the data, developing an analysis prompt, analyzing the text, and validating the results. As an illustrative example, we will use the challenging task of identifying populism in political texts, and show how LLMs move beyond the existing state-of-the-art.

With the global increase in experimental data artifacts, harnessing them in a unified fashion leads to a major stumbling block - bad metadata. To bridge this gap, this work presents a Natural Language Processing (NLP) informed application, called FAIRMetaText, that compares metadata. Specifically, FAIRMetaText analyzes the natural language descriptions of metadata and provides a mathematical similarity measure between two terms. This measure can then be utilized for analyzing varied metadata, by suggesting terms for compliance or grouping similar terms for identification of replaceable terms. The efficacy of the algorithm is presented qualitatively and quantitatively on publicly available research artifacts and demonstrates large gains across metadata related tasks through an in-depth study of a wide variety of Large Language Models (LLMs). This software can drastically reduce the human effort in sifting through various natural language metadata while employing several experimental datasets on the same topic.

This paper presents a study on the feasibility of using large language models (LLM) for coding with low-resource and domain-specific programming languages that typically lack the amount of data required for effective LLM processing techniques. This study focuses on the econometric scripting language named hansl of the open-source software gretl and employs a proprietary LLM based on GPT-3.5. Our findings suggest that LLMs can be a useful tool for writing, understanding, improving, and documenting gretl code, which includes generating descriptive docstrings for functions and providing precise explanations for abstract and poorly documented econometric code. While the LLM showcased promoting docstring-to-code translation capability, we also identify some limitations, such as its inability to improve certain sections of code and to write accurate unit tests. This study is a step towards leveraging the power of LLMs to facilitate software development in low-resource programming languages and ultimately to lower barriers to entry for their adoption.

Recent text-to-audio generation techniques have the potential to allow novice users to freely generate music audio. Even if they do not have musical knowledge, such as about chord progressions and instruments, users can try various text prompts to generate audio. However, compared to the image domain, gaining a clear understanding of the space of possible music audios is difficult because users cannot listen to the variations of the generated audios simultaneously. We therefore facilitate users in exploring not only text prompts but also audio priors that constrain the text-to-audio music generation process. This dual-sided exploration enables users to discern the impact of different text prompts and audio priors on the generation results through iterative comparison of them. Our developed interface, IteraTTA, is specifically designed to aid users in refining text prompts and selecting favorable audio priors from the generated audios. With this, users can progressively reach their loosely-specified goals while understanding and exploring the space of possible results. Our implementation and discussions highlight design considerations that are specifically required for text-to-audio models and how interaction techniques can contribute to their effectiveness.

Large language models (LLMs) and Vision-Language Models (VLMs) have been proven to excel at multiple tasks, such as commonsense reasoning. Powerful as these models can be, they are not grounded in the 3D physical world, which involves richer concepts such as spatial relationships, affordances, physics, layout, and so on. In this work, we propose to inject the 3D world into large language models and introduce a whole new family of 3D-LLMs. Specifically, 3D-LLMs can take 3D point clouds and their features as input and perform a diverse set of 3D-related tasks, including captioning, dense captioning, 3D question answering, task decomposition, 3D grounding, 3D-assisted dialog, navigation, and so on. Using three types of prompting mechanisms that we design, we are able to collect over 300k 3D-language data covering these tasks. To efficiently train 3D-LLMs, we first utilize a 3D feature extractor that obtains 3D features from rendered multi- view images. Then, we use 2D VLMs as our backbones to train our 3D-LLMs. By introducing a 3D localization mechanism, 3D-LLMs can better capture 3D spatial information. Experiments on ScanQA show that our model outperforms state-of-the-art baselines by a large margin (e.g., the BLEU-1 score surpasses state-of-the-art score by 9%). Furthermore, experiments on our held-in datasets for 3D captioning, task composition, and 3D-assisted dialogue show that our model outperforms 2D VLMs. Qualitative examples also show that our model could perform more tasks beyond the scope of existing LLMs and VLMs. Project Page: : https://vis-www.cs.umass.edu/3dllm/.

The zero-shot learning capabilities of large language models (LLMs) make them ideal for text classification without annotation or supervised training. Many studies have shown impressive results across multiple tasks. While tasks, data, and results differ widely, their similarities to human annotation can aid us in tackling new tasks with minimal expenses. We evaluate using 5 state-of-the-art LLMs as "annotators" on 5 different tasks (age, gender, topic, sentiment prediction, and hate speech detection), across 4 languages: English, French, German, and Spanish. No single model excels at all tasks, across languages, or across all labels within a task. However, aggregation techniques designed for human annotators perform substantially better than any one individual model. Overall, though, LLMs do not rival even simple supervised models, so they do not (yet) replace the need for human annotation. We also discuss the tradeoffs between speed, accuracy, cost, and bias when it comes to aggregated model labeling versus human annotation.

Large Language Models (LLMs) trained on extensive textual corpora have emerged as leading solutions for a broad array of Natural Language Processing (NLP) tasks. Despite their notable performance, these models are prone to certain limitations such as misunderstanding human instructions, generating potentially biased content, or factually incorrect (hallucinated) information. Hence, aligning LLMs with human expectations has become an active area of interest within the research community. This survey presents a comprehensive overview of these alignment technologies, including the following aspects. (1) Data collection: the methods for effectively collecting high-quality instructions for LLM alignment, including the use of NLP benchmarks, human annotations, and leveraging strong LLMs. (2) Training methodologies: a detailed review of the prevailing training methods employed for LLM alignment. Our exploration encompasses Supervised Fine-tuning, both Online and Offline human preference training, along with parameter-efficient training mechanisms. (3) Model Evaluation: the methods for evaluating the effectiveness of these human-aligned LLMs, presenting a multifaceted approach towards their assessment. In conclusion, we collate and distill our findings, shedding light on several promising future research avenues in the field. This survey, therefore, serves as a valuable resource for anyone invested in understanding and advancing the alignment of LLMs to better suit human-oriented tasks and expectations. An associated GitHub link collecting the latest papers is available at https://github.com/GaryYufei/AlignLLMHumanSurvey.

Medical imaging is a key component in clinical diagnosis, treatment planning and clinical trial design, accounting for almost 90% of all healthcare data. CNNs achieved performance gains in medical image analysis (MIA) over the last years. CNNs can efficiently model local pixel interactions and be trained on small-scale MI data. The main disadvantage of typical CNN models is that they ignore global pixel relationships within images, which limits their generalisation ability to understand out-of-distribution data with different 'global' information. The recent progress of Artificial Intelligence gave rise to Transformers, which can learn global relationships from data. However, full Transformer models need to be trained on large-scale data and involve tremendous computational complexity. Attention and Transformer compartments (Transf/Attention) which can well maintain properties for modelling global relationships, have been proposed as lighter alternatives of full Transformers. Recently, there is an increasing trend to co-pollinate complementary local-global properties from CNN and Transf/Attention architectures, which led to a new era of hybrid models. The past years have witnessed substantial growth in hybrid CNN-Transf/Attention models across diverse MIA problems. In this systematic review, we survey existing hybrid CNN-Transf/Attention models, review and unravel key architectural designs, analyse breakthroughs, and evaluate current and future opportunities as well as challenges. We also introduced a comprehensive analysis framework on generalisation opportunities of scientific and clinical impact, based on which new data-driven domain generalisation and adaptation methods can be stimulated.