In machine learning, temporal shifts occur when there are differences between training and test splits in terms of time. For streaming data such as news or social media, models are commonly trained on a fixed corpus from a certain period of time, and they can become obsolete due to the dynamism and evolving nature of online content. This paper focuses on temporal shifts in social media and, in particular, Twitter. We propose a unified evaluation scheme to assess the performance of language models (LMs) under temporal shift on standard social media tasks. LMs are tested on five diverse social media NLP tasks under different temporal settings, which revealed two important findings: (i) the decrease in performance under temporal shift is consistent across different models for entity-focused tasks such as named entity recognition or disambiguation, and hate speech detection, but not significant in the other tasks analysed (i.e., topic and sentiment classification); and (ii) continuous pre-training on the test period does not improve the temporal adaptability of LMs.

This paper introduces the first Turkish crossword puzzle generator designed to leverage the capabilities of large language models (LLMs) for educational purposes. In this work, we introduced two specially created datasets: one with over 180,000 unique answer-clue pairs for generating relevant clues from the given answer, and another with over 35,000 samples containing text, answer, category, and clue data, aimed at producing clues for specific texts and keywords within certain categories. Beyond entertainment, this generator emerges as an interactive educational tool that enhances memory, vocabulary, and problem-solving skills.

The ability to build and leverage world models is essential for a general-purpose AI agent. Testing such capabilities is hard, in part because the building blocks of world models are ill-defined. We present Elements of World Knowledge (EWOK), a framework for evaluating world modeling in language models by testing their ability to use knowledge of a concept to match a target text with a plausible/implausible context. EWOK targets specific concepts from multiple knowledge domains known to be vital for world modeling in humans. Domains range from social interactions (help/hinder) to spatial relations (left/right). Both, contexts and targets are minimal pairs. Objects, agents, and locations in the items can be flexibly filled in enabling easy generation of multiple controlled datasets. We then introduce EWOK-CORE-1.0, a dataset of 4,374 items covering 11 world knowledge domains. We evaluate 20 openweights large language models (1.3B--70B parameters) across a battery of evaluation paradigms along with a human norming study comprising 12,480 measurements. The overall performance of all tested models is worse than human performance, with results varying drastically across domains. These data highlight simple cases where even large models fail and present rich avenues for targeted research on LLM world modeling capabilities.

Heterogeneous, interconnected, systems-level, molecular data have become increasingly available and key in precision medicine. We need to utilize them to better stratify patients into risk groups, discover new biomarkers and targets, repurpose known and discover new drugs to personalize medical treatment. Existing methodologies are limited and a paradigm shift is needed to achieve quantitative and qualitative breakthroughs. In this perspective paper, we survey the literature and argue for the development of a comprehensive, general framework for embedding of multi-scale molecular network data that would enable their explainable exploitation in precision medicine in linear time. Network embedding methods map nodes to points in low-dimensional space, so that proximity in the learned space reflects the network's topology-function relationships. They have recently achieved unprecedented performance on hard problems of utilizing few omic data in various biomedical applications. However, research thus far has been limited to special variants of the problems and data, with the performance depending on the underlying topology-function network biology hypotheses, the biomedical applications and evaluation metrics. The availability of multi-omic data, modern graph embedding paradigms and compute power call for a creation and training of efficient, explainable and controllable models, having no potentially dangerous, unexpected behaviour, that make a qualitative breakthrough. We propose to develop a general, comprehensive embedding framework for multi-omic network data, from models to efficient and scalable software implementation, and to apply it to biomedical informatics. It will lead to a paradigm shift in computational and biomedical understanding of data and diseases that will open up ways to solving some of the major bottlenecks in precision medicine and other domains.

We study the problem of automatically annotating relevant numerals (GAAP metrics) occurring in the financial documents with their corresponding XBRL tags. Different from prior works, we investigate the feasibility of solving this extreme classification problem using a generative paradigm through instruction tuning of Large Language Models (LLMs). To this end, we leverage metric metadata information to frame our target outputs while proposing a parameter efficient solution for the task using LoRA. We perform experiments on two recently released financial numeric labeling datasets. Our proposed model, FLAN-FinXC, achieves new state-of-the-art performances on both the datasets, outperforming several strong baselines. We explain the better scores of our proposed model by demonstrating its capability for zero-shot as well as the least frequently occurring tags. Also, even when we fail to predict the XBRL tags correctly, our generated output has substantial overlap with the ground-truth in majority of the cases.

This paper will present textual corpora for Serbian (and Serbo-Croatian), usable for the training of large language models and publicly available at one of the several notable online repositories. Each corpus will be classified using multiple methods and its characteristics will be detailed. Additionally, the paper will introduce three new corpora: a new umbrella web corpus of Serbo-Croatian, a new high-quality corpus based on the doctoral dissertations stored within National Repository of Doctoral Dissertations from all Universities in Serbia, and a parallel corpus of abstract translation from the same source. The uniqueness of both old and new corpora will be accessed via frequency-based stylometric methods, and the results will be briefly discussed.

In this paper cum technical report, we present PHUDGE A fine tuned Phi3 model that achieved SOTA results in 4 tasks as Feedback Test, Feedback OOD, MT Human, Preference Test surpassing each and every existing model in latency and throughput. It shows very strong correlation not only with GPT4 but with Human annotators too in unseen data as well as in both absolute and relative grading tasks. We have not only addressed the usage of small LMs for cost effective production grade systems but have also shown that Causal modelling is not only slow in nature but sometimes it can hinder models learning capabilities and should be replaced by simpler tasks whenever we can to make the overall system faster and better. We show that by following systematic ML experimentation, thoughtful data augmentation and re purposing the problem itself, we can even beat 10x bigger models even with lesser training data. To the best of our knowledge, we are re the first one to experiment and showcase the usage of generalised version of Earth Movers Distance AKA Wasserstein distance by using Minkowski Distance with a penalty to control loss smoothing and can be used as a loss function instead of Cross Entropy to get stable training and better results for grading tasks.

The rapid advancement of AI technologies yields numerous future impacts on individuals and society. Policy-makers are therefore tasked to react quickly and establish policies that mitigate those impacts. However, anticipating the effectiveness of policies is a difficult task, as some impacts might only be observable in the future and respective policies might not be applicable to the future development of AI. In this work we develop a method for using large language models (LLMs) to evaluate the efficacy of a given piece of policy at mitigating specified negative impacts. We do so by using GPT-4 to generate scenarios both pre- and post-introduction of policy and translating these vivid stories into metrics based on human perceptions of impacts. We leverage an already established taxonomy of impacts of generative AI in the media environment to generate a set of scenario pairs both mitigated and non-mitigated by the transparency legislation of Article 50 of the EU AI Act. We then run a user study (n=234) to evaluate these scenarios across four risk-assessment dimensions: severity, plausibility, magnitude, and specificity to vulnerable populations. We find that this transparency legislation is perceived to be effective at mitigating harms in areas such as labor and well-being, but largely ineffective in areas such as social cohesion and security. Through this case study on generative AI harms we demonstrate the efficacy of our method as a tool to iterate on the effectiveness of policy on mitigating various negative impacts. We expect this method to be useful to researchers or other stakeholders who want to brainstorm the potential utility of different pieces of policy or other mitigation strategies.

The White House Executive Order on Artificial Intelligence highlights the risks of large language models (LLMs) empowering malicious actors in developing biological, cyber, and chemical weapons. To measure these risks of malicious use, government institutions and major AI labs are developing evaluations for hazardous capabilities in LLMs. However, current evaluations are private, preventing further research into mitigating risk. Furthermore, they focus on only a few, highly specific pathways for malicious use. To fill these gaps, we publicly release the Weapons of Mass Destruction Proxy (WMDP) benchmark, a dataset of 3,668 multiple-choice questions that serve as a proxy measurement of hazardous knowledge in biosecurity, cybersecurity, and chemical security. WMDP was developed by a consortium of academics and technical consultants, and was stringently filtered to eliminate sensitive information prior to public release. WMDP serves two roles: first, as an evaluation for hazardous knowledge in LLMs, and second, as a benchmark for unlearning methods to remove such hazardous knowledge. To guide progress on unlearning, we develop RMU, a state-of-the-art unlearning method based on controlling model representations. RMU reduces model performance on WMDP while maintaining general capabilities in areas such as biology and computer science, suggesting that unlearning may be a concrete path towards reducing malicious use from LLMs. We release our benchmark and code publicly at https://wmdp.ai

We introduce a novel LLM based solution design approach that utilizes combinatorial optimization and sampling. Specifically, a set of factors that influence the quality of the solution are identified. They typically include factors that represent prompt types, LLM inputs alternatives, and parameters governing the generation and design alternatives. Identifying the factors that govern the LLM solution quality enables the infusion of subject matter expert knowledge. Next, a set of interactions between the factors are defined and combinatorial optimization is used to create a small subset $P$ that ensures all desired interactions occur in $P$. Each element $p \in P$ is then developed into an appropriate benchmark. Applying the alternative solutions on each combination, $p \in P$ and evaluating the results facilitate the design of a high quality LLM solution pipeline. The approach is especially applicable when the design and evaluation of each benchmark in $P$ is time-consuming and involves manual steps and human evaluation. Given its efficiency the approach can also be used as a baseline to compare and validate an autoML approach that searches over the factors governing the solution.