Pre-trained language models are effective in a variety of natural language tasks, but it has been argued their capabilities fall short of fully learning meaning or understanding language. To understand the extent to which language models can learn some form of meaning, we investigate their ability to capture semantics of code beyond superficial frequency and co-occurrence. In contrast to previous research on probing models for linguistic features, we study pre-trained models in a setting that allows for objective and straightforward evaluation of a model's ability to learn semantics. In this paper, we examine whether such models capture the semantics of code, which is precisely and formally defined. Through experiments involving the manipulation of code fragments, we show that code pre-trained models of code learn a robust representation of the computational semantics of code that goes beyond superficial features of form alone

Polis is a platform that leverages machine intelligence to scale up deliberative processes. In this paper, we explore the opportunities and risks associated with applying Large Language Models (LLMs) towards challenges with facilitating, moderating and summarizing the results of Polis engagements. In particular, we demonstrate with pilot experiments using Anthropic's Claude that LLMs can indeed augment human intelligence to help more efficiently run Polis conversations. In particular, we find that summarization capabilities enable categorically new methods with immense promise to empower the public in collective meaning-making exercises. And notably, LLM context limitations have a significant impact on insight and quality of these results. However, these opportunities come with risks. We discuss some of these risks, as well as principles and techniques for characterizing and mitigating them, and the implications for other deliberative or political systems that may employ LLMs. Finally, we conclude with several open future research directions for augmenting tools like Polis with LLMs.

Recent advances in open-domain text generation models powered by large pre-trained language models (LLMs) have achieved remarkable performance. However, evaluating and controlling these models for desired attributes remains a challenge, as traditional reference-based metrics such as BLEU, ROUGE, and METEOR are insufficient for open-ended generation tasks. Similarly, while trainable discriminator-based evaluation metrics show promise, obtaining high-quality training data is a non-trivial task. In this paper, we introduce a novel approach to evaluate open-domain generation - the Meta-Distribution Methods (MDM). Drawing on the correlation between the rising parameter counts and the improving performance of LLMs, MDM creates a mapping from the contrast of two probabilistic distributions -- one known to be superior to the other -- to quality measures, which can be viewed as a distribution of distributions i.e. Meta-Distribution. We investigate MDM for open-domain text generation evaluation under two paradigms: 1) \emph{Generative} MDM, which leverages the Meta-Distribution Methods to generate in-domain negative samples for training discriminator-based metrics; 2) \emph{Discriminative} MDM, which directly uses distribution discrepancies between two language models for evaluation. Our experiments on multi-turn dialogue and factuality in abstractive summarization demonstrate that MDMs correlate better with human judgment than existing automatic evaluation metrics on both tasks, highlighting the strong performance and generalizability of such methods.

NeurAlly-Decomposed Oracle (NADO) is a powerful approach for controllable generation with large language models. Differentiating from finetuning/prompt tuning, it has the potential to avoid catastrophic forgetting of the large base model and achieve guaranteed convergence to an entropy-maximized closed-form solution without significantly limiting the model capacity. Despite its success, several challenges arise when applying NADO to more complex scenarios. First, the best practice of using NADO for the composition of multiple control signals is under-explored. Second, vanilla NADO suffers from gradient vanishing for low-probability control signals and is highly reliant on the forward-consistency regularization. In this paper, we study the aforementioned challenges when using NADO theoretically and empirically. We show we can achieve guaranteed compositional generalization of NADO with a certain practice, and propose a novel alternative parameterization of NADO to perfectly guarantee the forward-consistency. We evaluate the improved training of NADO, i.e. NADO++, on CommonGen. Results show that NADO++ improves the effectiveness of the algorithm in multiple aspects.

The advent of large language models (LLM) has led to significant progress in image analysis with potential for future advancements. SAM [Kirillov et al., 2023] is a revolutionary foundation model for image segmentation and has already shown the capability of handling diverse segmentation tasks. SAM especially prevails in zero-shot domain generalization cases compared with the existing elaborate, fine-tuned models trained on specific domains. An important prospect for the application of SAM would be its adaptation to the complex task of segmenting medical images with significant inter-subject variations and a low signal-to-noise ratio. The segmentation task allows separation of different structures in medical images, which are then used to detect the region of interest or reconstruct multi-dimensional anatomical models [Sinha and Dolz, 2021]. The existing AI-based segmentation methods, however, do not fully bridge the domain gap among different imaging modalities, such as computed tomography (CT), magnetic resonance imaging (MRI), or ultrasound (US) [Wang et al., 2020]. The domain gap refers to the difference in the data format across various image modalities, as each modality offers a distinct advantage in visualizing anatomical structures and related pathologies (e.g., tumor, bone fracture). This difference introduces specific challenges for training AI systems to perform common analysis without the need for a comprehensive dataset that includes all relevant domains from various image modalities.

Prediction sets have recently been shown to be a promising strategy for quantifying the uncertainty of deep neural networks in a way that provides theoretical guarantees. However, existing techniques have largely targeted settings where the space of labels is simple, so prediction sets can be arbitrary subsets of labels. For structured prediction problems where the space of labels is exponential in size, even prediction sets containing a small fraction of all labels can be exponentially large. In the context of code generation, we propose a solution that considers a restricted set of prediction sets that can compactly be represented as partial programs, which are programs with portions replaced with holes. Given a trained code generation model, our algorithm leverages a programming language's abstract syntax tree to generate a set of programs such that the correct program is in the set with high-confidence. Valuable applications of our algorithm include a Codex-style code generator with holes in uncertain parts of the generated code, which provides a partial program with theoretical guarantees. We evaluate our approach on PICARD (a T5 model for SQL semantic parsing) and Codex (a GPT model for over a dozen programming languages, including Python), demonstrating that our approach generates compact PAC prediction sets. This is the first research contribution that generates PAC prediction sets for generative code models.

This study investigates the application of Large Language Models (LLMs), specifically GPT-4, within Astronomy. We employ in-context prompting, supplying the model with up to 1000 papers from the NASA Astrophysics Data System, to explore the extent to which performance can be improved by immersing the model in domain-specific literature. Our findings point towards a substantial boost in hypothesis generation when using in-context prompting, a benefit that is further accentuated by adversarial prompting. We illustrate how adversarial prompting empowers GPT-4 to extract essential details from a vast knowledge base to produce meaningful hypotheses, signaling an innovative step towards employing LLMs for scientific research in Astronomy.

State-of-The-Art (SoTA) image captioning models often rely on the Microsoft COCO (MS-COCO) dataset for training. This dataset contains annotations provided by human annotators, who typically produce captions averaging around ten tokens. However, this constraint presents a challenge in effectively capturing complex scenes and conveying detailed information. Furthermore, captioning models tend to exhibit bias towards the ``average'' caption, which captures only the more general aspects. What would happen if we were able to automatically generate longer captions, thereby making them more detailed? Would these captions, evaluated by humans, be more or less representative of the image content compared to the original MS-COCO captions? In this paper, we present a novel approach to address previous challenges by showcasing how captions generated from different SoTA models can be effectively fused, resulting in richer captions. Our proposed method leverages existing models from the literature, eliminating the need for additional training. Instead, it utilizes an image-text based metric to rank the captions generated by SoTA models for a given image. Subsequently, the top two captions are fused using a Large Language Model (LLM). Experimental results demonstrate the effectiveness of our approach, as the captions generated by our model exhibit higher consistency with human judgment when evaluated on the MS-COCO test set. By combining the strengths of various SoTA models, our method enhances the quality and appeal of image captions, bridging the gap between automated systems and the rich, informative nature of human-generated descriptions. This advance opens up new possibilities for generating captions that are more suitable for the training of both vision-language and captioning models.

The legal profession necessitates a multidimensional approach that involves synthesizing an in-depth comprehension of a legal issue with insightful commentary based on personal experience, combined with a comprehensive understanding of pertinent legislation, regulation, and case law, in order to deliver an informed legal solution. The present offering with generative AI presents major obstacles in replicating this, as current models struggle to integrate and navigate such a complex interplay of understanding, experience, and fact-checking procedures. It is noteworthy that where generative AI outputs understanding and experience, which reflect the aggregate of various subjective views on similar topics, this often deflects the model's attention from the crucial legal facts, thereby resulting in hallucination. Hence, this paper delves into the feasibility of three independent LLMs, each focused on understanding, experience, and facts, synthesising as one single ensemble model to effectively counteract the current challenges posed by the existing monolithic generative AI models. We introduce an idea of mutli-length tokenisation to protect key information assets like common law judgements, and finally we interrogate the most advanced publicly available models for legal hallucination, with some interesting results.

Large Language Models (LLMs) such as ChatGPT, have gained significant attention due to their impressive natural language processing capabilities. It is crucial to prioritize human-centered principles when utilizing these models. Safeguarding the ethical and moral compliance of LLMs is of utmost importance. However, individual ethical issues have not been well studied on the latest LLMs. Therefore, this study aims to address these gaps by introducing a new benchmark -- TrustGPT. TrustGPT provides a comprehensive evaluation of LLMs in three crucial areas: toxicity, bias, and value-alignment. Initially, TrustGPT examines toxicity in language models by employing toxic prompt templates derived from social norms. It then quantifies the extent of bias in models by measuring quantifiable toxicity values across different groups. Lastly, TrustGPT assesses the value of conversation generation models from both active value-alignment and passive value-alignment tasks. Through the implementation of TrustGPT, this research aims to enhance our understanding of the performance of conversation generation models and promote the development of language models that are more ethical and socially responsible.