Reinforcement learning from human feedback (RLHF) aligns Large Language Models (LLMs) with human preferences. However, these preferences can often change over time due to external factors (e.g. environment change and societal influence). Consequently, what was wrong then might be right now. Current preference optimization algorithms do not account for temporal preference drift in their modeling, which can lead to severe misalignment. To address this limitation, we use a Dynamic Bradley-Terry model that models preferences via time-dependent reward functions, and propose Non-Stationary Direct Preference Optimisation (NS-DPO). By introducing a discount parameter in the loss function, NS-DPO applies exponential weighting, which proportionally focuses learning on more time-relevant datapoints. We theoretically analyse the convergence of NS-DPO in the offline setting, providing upper bounds on the estimation error caused by non-stationary preferences. Finally, we demonstrate the effectiveness of NS-DPO1 for fine-tuning LLMs in scenarios with drifting preferences. By simulating preference drift using renowned reward models and modifying popular LLM datasets accordingly, we show that NS-DPO fine-tuned LLMs remain robust under non-stationarity, significantly outperforming baseline algorithms that ignore temporal preference changes, without sacrificing performance in stationary cases.

Investigating the genetic architecture of complex diseases is challenging due to the highly polygenic and interactive landscape of genetic and environmental factors. Although genome-wide association studies (GWAS) have identified thousands of variants for multiple complex phenotypes, conventional statistical approaches can be limited by simplified assumptions such as linearity and lack of epistasis models. In this work, we trained artificial neural networks for predicting complex traits using both simulated and real genotype/phenotype datasets. We extracted feature importance scores via different post hoc interpretability methods to identify potentially associated loci (PAL) for the target phenotype. Simulations we performed with various parameters demonstrated that associated loci can be detected with good precision using strict selection criteria, but downstream analyses are required for fine-mapping the exact variants due to linkage disequilibrium, similarly to conventional GWAS. By applying our approach to the schizophrenia cohort in the Estonian Biobank, we were able to detect multiple PAL related to this highly polygenic and heritable disorder. We also performed enrichment analyses with PAL in genic regions, which predominantly identified terms associated with brain morphology. With further improvements in model optimization and confidence measures, artificial neural networks can enhance the identification of genomic loci associated with complex diseases, providing a more comprehensive approach for GWAS and serving as initial screening tools for subsequent functional studies.

Compliance checking is an essential part of a construction project. The recent rapid uptake of building information models (BIM) in the construction industry has created more opportunities for automated compliance checking (ACC). BIM enables sharing of digital building design data that can be used for compliance checking with legal requirements, which are conventionally conveyed in natural language and not intended for machine processing. Creating a computable representation of legal requirements suitable for ACC is complex, costly, and time-consuming. Large language models (LLMs) such as the generative pre-trained transformers (GPT), GPT-3.5 and GPT-4, powering OpenAI's ChatGPT, can generate logically coherent text and source code responding to user prompts. This capability could be used to automate the conversion of building regulations into a semantic and computable representation. This paper evaluates the performance of LLMs in translating building regulations into LegalRuleML in a few-shot learning setup. By providing GPT-3.5 with only a few example translations, it can learn the basic structure of the format. Using a system prompt, we further specify the LegalRuleML representation and explore the existence of expert domain knowledge in the model. Such domain knowledge might be ingrained in GPT-3.5 through the broad pre-training but needs to be brought forth by careful contextualisation. Finally, we investigate whether strategies such as chain-of-thought reasoning and self-consistency could apply to this use case. As LLMs become more sophisticated, the increased common sense, logical coherence, and means to domain adaptation can significantly support ACC, leading to more efficient and effective checking processes.

Learning performance data, such as correct or incorrect responses to questions in Intelligent Tutoring Systems (ITSs) is crucial for tracking and assessing the learners' progress and mastery of knowledge. However, the issue of data sparsity, characterized by unexplored questions and missing attempts, hampers accurate assessment and the provision of tailored, personalized instruction within ITSs. This paper proposes using the Generative Adversarial Imputation Networks (GAIN) framework to impute sparse learning performance data, reconstructed into a three-dimensional (3D) tensor representation across the dimensions of learners, questions and attempts. Our customized GAIN-based method computational process imputes sparse data in a 3D tensor space, significantly enhanced by convolutional neural networks for its input and output layers. This adaptation also includes the use of a least squares loss function for optimization and aligns the shapes of the input and output with the dimensions of the questions-attempts matrices along the learners' dimension. Through extensive experiments on six datasets from various ITSs, including AutoTutor, ASSISTments and MATHia, we demonstrate that the GAIN approach generally outperforms existing methods such as tensor factorization and other generative adversarial network (GAN) based approaches in terms of imputation accuracy. This finding enhances comprehensive learning data modeling and analytics in AI-based education.

Decoding from the output distributions of large language models to produce high-quality text is a complex challenge in language modeling. Various approaches, such as beam search, sampling with temperature, $k-$sampling, nucleus $p-$sampling, typical decoding, contrastive decoding, and contrastive search, have been proposed to address this problem, aiming to improve coherence, diversity, as well as resemblance to human-generated text. In this study, we introduce adaptive contrastive search, a novel decoding strategy extending contrastive search by incorporating an adaptive degeneration penalty, guided by the estimated uncertainty of the model at each generation step. This strategy is designed to enhance both the creativity and diversity of the language modeling process while at the same time producing coherent and high-quality generated text output. Our findings indicate performance enhancement in both aspects, across different model architectures and datasets, underscoring the effectiveness of our method in text generation tasks. Our code base, datasets, and models are publicly available.

With the increasing attention to molecular machine learning, various innovations have been made in designing better models or proposing more comprehensive benchmarks. However, less is studied on the data preprocessing schedule for molecular graphs, where a different view of the molecular graph could potentially boost the model's performance. Inspired by the Byte-Pair Encoding (BPE) algorithm, a subword tokenization method popularly adopted in Natural Language Processing, we propose GraphBPE, which tokenizes a molecular graph into different substructures and acts as a preprocessing schedule independent of the model architectures. Our experiments on 3 graph-level classification and 3 graph-level regression datasets show that data preprocessing could boost the performance of models for molecular graphs, and GraphBPE is effective for small classification datasets and it performs on par with other tokenization methods across different model architectures.

DeepMind's AlphaProof AI can tackle a range of mathematical problems An AI from Google DeepMind has achieved a silver medal score at this year's International Mathematical Olympiad (IMO), the first time any AI has made it to the podium. The IMO is considered the world's most prestigious competition for young mathematicians. Correctly answering its test questions requires mathematical ability that AI systems typically lack. In January, Google DeepMind demonstrated AlphaGeometry, an AI system that could answer some IMO geometry questions as well as humans. However, this was not from a live competition, and it couldn't answer questions from other mathematical disciplines, such as number theory, algebra and combinatorics, which is necessary to win an IMO medal.

The Treasury has denied that copper coins are to be phased out after it ordered no new 1p and 2p pieces from the Royal Mint this year. "We are not scrapping 1p or 2p coins," a Treasury spokesperson told the BBC. They added that the lack of orders was due to there being enough coins already in circulation. The comments came after multiple reports suggested that the coins might be scrapped as the number of purchases involving cash continued to fall. "We are confident there are enough coins in the system without the need to order more this year," the Treasury said.

AI applications across classification, fairness, and human interaction often implicitly require ontologies of social concepts. Constructing these well, especially when there are many relevant categories, is a controversial task but is crucial for achieving meaningful inclusivity. Here, we focus on developing a pragmatic ontology of belief systems, which is a complex and often controversial space. By iterating on our community-based design until mutual agreement is reached, we found that epistemological methods were best for categorizing the fundamental ways beliefs differ, maximally respecting our principles of inclusivity and brevity. We demonstrate our methodology's utility and interpretability via user studies in term annotation and sentiment analysis experiments for belief fairness in language models.

The recent emergence of Large Language Models (LLMs) has heralded a new era of human-AI interaction. These sophisticated models, exemplified by Chat-GPT and its successors, have exhibited remarkable capabilities in language understanding. However, as these LLMs have undergone exponential growth, a crucial dimension that remains understudied is the personalization of these models. Large foundation models such as GPT-3 etc. focus on creating a universal model that serves a broad range of tasks and users. This approach emphasizes the model's generalization capabilities, treating users as a collective rather than as distinct individuals. While practical for many common applications, this one-size-fits-all approach often fails to address the rich tapestry of human diversity and individual needs. To explore this issue we introduce the PEFT-U Benchmark: a new dataset for building and evaluating NLP models for user personalization. \datasetname{} consists of a series of user-centered tasks containing diverse and individualized expressions where the preferences of users can potentially differ for the same input. Using PEFT-U, we explore the challenge of efficiently personalizing LLMs to accommodate user-specific preferences in the context of diverse user-centered tasks.