In causal inference, an important problem is to quantify the effects of interventions or treatments. Many studies focus on estimating the mean causal effects; however, these estimands may offer limited insight since two distributions can share the same mean yet exhibit significant differences. Examining the causal effects from a distributional perspective provides a more thorough understanding. In this paper, we employ a semiparametric density ratio model (DRM) to characterize the counterfactual distributions, introducing a framework that assumes a latent structure shared by these distributions. Our model offers flexibility by avoiding strict parametric assumptions on the counterfactual distributions. Specifically, the DRM incorporates a nonparametric component that can be estimated through the method of empirical likelihood (EL), using the data from all the groups stemming from multiple interventions. Consequently, the EL-DRM framework enables inference of the counterfactual distribution functions and their functionals, facilitating direct and transparent causal inference from a distributional perspective. Numerical studies on both synthetic and real-world data validate the effectiveness of our approach.

Advancements in artificial intelligence (AI) have transformed many scientific fields, with microbiology and microbiome research now experiencing significant breakthroughs through machine learning and deep learning applications. This review provides a comprehensive overview of AI-driven approaches tailored for microbiology and microbiome studies, emphasizing both technical advancements and biological insights. We begin with an introduction to foundational AI techniques, including primary machine learning paradigms and various deep learning architectures, and offer guidance on choosing between machine learning and deep learning methods based on specific research goals. The primary section on application scenarios spans diverse research areas, from taxonomic profiling, functional annotation & prediction, microbe-X interactions, microbial ecology, metabolic modeling, precision nutrition, clinical microbiology, to prevention & therapeutics. Finally, we discuss challenges unique to this field, including the balance between interpretability and complexity, the "small n, large p" problem, and the critical need for standardized benchmarking datasets to validate and compare models. Together, this review underscores AI's transformative role in microbiology and microbiome research, paving the way for innovative methodologies and applications that enhance our understanding of microbial life and its impact on our planet and our health.

Large Language Models (LLMs) have become foundational in modern language-driven applications, profoundly influencing daily life. A critical technique in leveraging their potential is role-playing, where LLMs simulate diverse roles to enhance their real-world utility. However, while research has highlighted the presence of social biases in LLM outputs, it remains unclear whether and to what extent these biases emerge during role-playing scenarios. In this paper, we introduce BiasLens, a fairness testing framework designed to systematically expose biases in LLMs during role-playing. Our approach uses LLMs to generate 550 social roles across a comprehensive set of 11 demographic attributes, producing 33,000 role-specific questions targeting various forms of bias. These questions, spanning Yes/No, multiple-choice, and open-ended formats, are designed to prompt LLMs to adopt specific roles and respond accordingly. We employ a combination of rule-based and LLM-based strategies to identify biased responses, rigorously validated through human evaluation. Using the generated questions as the benchmark, we conduct extensive evaluations of six advanced LLMs released by OpenAI, Mistral AI, Meta, Alibaba, and DeepSeek. Our benchmark reveals 72,716 biased responses across the studied LLMs, with individual models yielding between 7,754 and 16,963 biased responses, underscoring the prevalence of bias in role-playing contexts. To support future research, we have publicly released the benchmark, along with all scripts and experimental results.

We present Multi-expert Prompting, a novel enhancement of ExpertPrompting (Xu et al., 2023), designed to improve the large language model (LLM) generation. Specifically, it guides an LLM to fulfill an input instruction by simulating multiple experts, aggregating their responses, and selecting the best among individual and aggregated responses. This process is performed in a single chain of thoughts through our seven carefully designed subtasks derived from the Nominal Group Technique (Ven and Delbecq, 1974), a well-established decision-making framework. Our evaluations demonstrate that Multi-expert Prompting significantly outperforms ExpertPrompting and comparable baselines in enhancing the truthfulness, factuality, informativeness, and usefulness of responses while reducing toxicity and hurtfulness. It further achieves state-of-the-art truthfulness by outperforming the best baseline by 8.69% with ChatGPT. Multi-expert Prompting is efficient, explainable, and highly adaptable to diverse scenarios, eliminating the need for manual prompt construction.

Self-training often falls short under distribution shifts due to an increased discrepancy between prediction confidence and actual accuracy. This typically necessitates computationally demanding methods such as neighborhood or ensemble-based label corrections. Drawing inspiration from insights on early learning regularization, we develop a principled method to improve self-training under distribution shifts based on temporal consistency. Specifically, we build an uncertainty-aware temporal ensemble with a simple relative thresholding. Then, this ensemble smooths noisy pseudo labels to promote selective temporal consistency. We show that our temporal ensemble is asymptotically correct and our label smoothing technique can reduce the optimality gap of self-training. Our extensive experiments validate that our approach consistently improves self-training performances by 8% to 16% across diverse distribution shift scenarios without a computational overhead. Besides, our method exhibits attractive properties, such as improved calibration performance and robustness to different hyperparameter choices.

This paper explores how non-experts can teach robots desired skills in their environments. We argue that natural language is an intuitive and accessible interface for robot learning. To this end, we investigate two key aspects: (1) how non-experts collect robotic data using natural language supervision and (2) how pre-trained vision-language models learn end-to-end policies directly from this supervision. We propose a data collection framework that collects robot demonstrations based on natural language supervision (e.g., "move forward") and further augments these demonstrations. Next, we introduce a model that learns language-conditioned policies from natural language supervision called CLIP-RT. Our model employs pre-trained CLIP models and learns to predict actions represented in language via contrastive imitation learning. We first train CLIP-RT on large-scale robotic data and then enable it to learn desired skills using data collected from our framework. CLIP-RT shows strong capabilities in acquiring novel manipulation skills, outperforming the state-of-the-art model, OpenVLA (7B parameters), by 17% in average success rates, while using 7x fewer parameters (1B).

Curriculum learning (CL) describes a machine learning training strategy in which samples are gradually introduced into the training process based on their difficulty. Despite a partially contradictory body of evidence in the literature, CL finds popularity in deep learning research due to its promise of leveraging human-inspired curricula to achieve higher model performance. Yet, the subjectivity and biases that follow any necessary definition of difficulty, especially for those found in orderings derived from models or training statistics, have rarely been investigated. To shed more light on the underlying unanswered questions, we conduct an extensive study on the robustness and similarity of the most common scoring functions for sample difficulty estimation, as well as their potential benefits in CL, using the popular benchmark dataset CIFAR-10 and the acoustic scene classification task from the DCASE2020 challenge as representatives of computer vision and computer audition, respectively. We report a strong dependence of scoring functions on the training setting, including randomness, which can partly be mitigated through ensemble scoring. While we do not find a general advantage of CL over uniform sampling, we observe that the ordering in which data is presented for CL-based training plays an important role in model performance. Furthermore, we find that the robustness of scoring functions across random seeds positively correlates with CL performance. Finally, we uncover that models trained with different CL strategies complement each other by boosting predictive power through late fusion, likely due to differences in the learnt concepts. Alongside our findings, we release the aucurriculum toolkit (https://github.com/autrainer/aucurriculum), implementing sample difficulty and CL-based training in a modular fashion.

Instruction tuning is a supervised fine-tuning approach that significantly improves the ability of large language models (LLMs) to follow human instructions. We propose SelfCodeAlign, the first fully transparent and permissive pipeline for self-aligning code LLMs without extensive human annotations or distillation. SelfCodeAlign employs the same base model for inference throughout the data generation process. It first extracts diverse coding concepts from high-quality seed snippets to generate new tasks. It then samples multiple responses per task, pairs each with test cases, and validates them in a sandbox environment. Finally, passing examples are selected for instruction tuning. In our primary experiments, we use SelfCodeAlign with CodeQwen1.5-7B to generate a dataset of 74k instruction-response pairs. Finetuning on this dataset leads to a model that achieves a 67.1 pass@1 on HumanEval+, surpassing CodeLlama-70B-Instruct despite being ten times smaller. Across all benchmarks, this finetuned model consistently outperforms the original version trained with OctoPack, the previous state-of-the-art method for instruction tuning without human annotations or distillation. Additionally, we show that SelfCodeAlign is effective across LLMs of various sizes, from 3B to 33B, and that the base models can benefit more from alignment with their own data distribution. We further validate each component's effectiveness in our pipeline, showing that SelfCodeAlign outperforms both direct distillation from GPT-4o and leading GPT-3.5-based distillation methods, such as OSS-Instruct and Evol-Instruct. SelfCodeAlign has also led to the creation of StarCoder2-Instruct, the first fully transparent, permissively licensed, and self-aligned code LLM that achieves state-of-the-art coding performance.

The level of detail of the feedback influences its effectiveness [80], and feedback can be given at many levels ranging from targeting how to work on and complete specific tasks to considering personal characteristics and behavior[26, 36, 59]. In teaching and learning programming, automated assessment systems have been a key tool for providing feedback at a scale already for more than a half a century [30, 36, 61]. Researchers have sought to automate step-by-step guidance [78], provide hints during the programming process [55], improve programming error messages [6], and aid in providing textual feedback by grouping similar code submissions together [23, 37, 58]. To support the understanding of how novices construct programs, researchers and educators have been collecting increasing amounts of data from students' programming process [31]. Such data can be collected at multiple granularities, ranging from final course assignment submissions to individual keystrokes from solving the assignments [31]. Programming process data has been, for example, used to play back how students construct their programs step by step or keystroke by keystroke to create a broader understanding of the process [27, 73, 83]. So far, despite shared efforts towards providing timely feedback to students[33], the potential of fine-grained programming process data for feedback purposes is still largely untapped. Large Language Models (LLMs) are a potential tool for realizing the transformation of programming process data into actionable feedback items. Within Computing Education Research, LLMs have broadened the horizon of what computing education researchers and practitioners can achieve[65], calling even for rethinking how computer science and programming is taught [16].

Per-example gradient norms are a vital ingredient for estimating gradient noise scale (GNS) with minimal variance. Observing the tensor contractions required to compute them, we propose a method with minimal FLOPs in 3D or greater tensor regimes by simultaneously computing the norms while computing the parameter gradients. Using this method we are able to observe the GNS of different layers at higher accuracy than previously possible. We find that the total GNS of contemporary transformer models is predicted well by the GNS of only the normalization layers. As a result, focusing only on the normalization layer, we develop a custom kernel to compute the per-example gradient norms while performing the LayerNorm backward pass with zero throughput overhead. Tracking GNS on only those layers, we are able to guide a practical batch size schedule that reduces training time by 18% on a Chinchilla-optimal language model.