Since the success of GPT, large language models (LLMs) have been revolutionizing machine learning and have initiated the so-called LLM prompting paradigm. In the era of LLMs, people train a single general-purpose LLM and provide the LLM with different prompts to perform different tasks. However, such empirical success largely lacks theoretical understanding. Here, we present the first theoretical study on the LLM prompting paradigm to the best of our knowledge. In this work, we show that prompting is in fact Turing-complete: there exists a finite-size Transformer such that for any computable function, there exists a corresponding prompt following which the Transformer computes the function. Furthermore, we show that even though we use only a single finite-size Transformer, it can still achieve nearly the same complexity bounds as that of the class of all unbounded-size Transformers. Overall, our result reveals that prompting can enable a single finite-size Transformer to be efficiently universal, which establishes a theoretical underpinning for prompt engineering in practice.
The emergence of foundational models and generative artificial intelligence (GenAI) is poised to transform productivity in scientific computing, especially in code development, refactoring, and translating from one programming language to another. However, because the output of GenAI cannot be guaranteed to be correct, manual intervention remains necessary. Some of this intervention can be automated through task-specific tools, alongside additional methodologies for correctness verification and effective prompt development. We explored the application of GenAI in assisting with code translation, language interoperability, and codebase inspection within a legacy Fortran codebase used to simulate particle interactions at the Large Hadron Collider (LHC). In the process, we developed a tool, CodeScribe, which combines prompt engineering with user supervision to establish an efficient process for code conversion. In this paper, we demonstrate how CodeScribe assists in converting Fortran code to C++, generating Fortran-C APIs for integrating legacy systems with modern C++ libraries, and providing developer support for code organization and algorithm implementation. We also address the challenges of AI-driven code translation and highlight its benefits for enhancing productivity in scientific computing workflows.
Recent advances in LLM have been instrumental in autonomous robot control and human-robot interaction by leveraging their vast general knowledge and capabilities to understand and reason across a wide range of tasks and scenarios. Previous works have investigated various prompt engineering techniques for improving the performance of LLM to accomplish tasks, while others have proposed methods that utilize LLMs to plan and execute tasks based on the available functionalities of a given robot platform. In this work, we consider both lines of research by comparing prompt engineering techniques and combinations thereof within the application of high-level task planning and execution in service robotics. We define a diverse set of tasks and a simple set of functionalities in simulation, and measure task completion accuracy and execution time for several state-of-the-art models.
Ensuring the safety of large language model (LLM) applications is essential for developing trustworthy artificial intelligence. Current LLM safety benchmarks have two limitations. First, they focus solely on either discriminative or generative evaluation paradigms while ignoring their interconnection. Second, they rely on standardized inputs, overlooking the effects of widespread prompting techniques, such as system prompts, few-shot demonstrations, and chain-of-thought prompting. To overcome these issues, we developed SG-Bench, a novel benchmark to assess the generalization of LLM safety across various tasks and prompt types. This benchmark integrates both generative and discriminative evaluation tasks and includes extended data to examine the impact of prompt engineering and jailbreak on LLM safety. Our assessment of 3 advanced proprietary LLMs and 10 open-source LLMs with the benchmark reveals that most LLMs perform worse on discriminative tasks than generative ones, and are highly susceptible to prompts, indicating poor generalization in safety alignment. We also explain these findings quantitatively and qualitatively to provide insights for future research.
Large language models (LLMs) are reported to be partial to certain cultures owing to the training data dominance from the English corpora. Since multilingual cultural data are often expensive to collect, existing efforts handle this by prompt engineering or culture-specific pre-training. However, they might overlook the knowledge deficiency of low-resource culture and require extensive computing resources. In this paper, we propose CultureLLM, a cost-effective solution to incorporate cultural differences into LLMs. CultureLLM adopts World Value Survey (WVS) as seed data and generates semantically equivalent training data via the proposed semantic data augmentation. Using only 50 seed samples from WVS with augmented data, we fine-tune culture-specific LLMs and one unified model (CultureLLM-One) for 9 cultures covering rich and low-resource languages. Extensive experiments on 60 culture-related datasets demonstrate that CultureLLM significantly outperforms various counterparts such as GPT-3.5 (by 8.1%) and Gemini Pro (by 9.5%) with comparable performance to GPT-4 or even better. Our human study shows that the generated samples are semantically equivalent to the original samples, providing an effective solution for LLMs augmentation. Code is released at https://github.com/Scarelette/CultureLLM.
Can we establish provable performance guarantees for transformers? Establishing such theoretical guarantees is a milestone in developing trustworthy generative AI. In this paper, we take a step toward addressing this question by focusing on optimal transport, a fundamental problem at the intersection of combinatorial and continuous optimization. Leveraging the computational power of attention layers, we prove that a transformer with fixed parameters can effectively solve the optimal transport problem in Wasserstein-2 with entropic regularization for an arbitrary number of points. Consequently, the transformer can sort lists of arbitrary sizes up to an approximation factor. Our results rely on an engineered prompt that enables the transformer to implement gradient descent with adaptive stepsizes on the dual optimal transport. Combining the convergence analysis of gradient descent with Sinkhorn dynamics, we establish an explicit approximation bound for optimal transport with transformers, which improves as depth increases. Our findings provide novel insights into the essence of prompt engineering and depth for solving optimal transport. In particular, prompt engineering boosts the algorithmic expressivity of transformers, allowing them implement an optimization method. With increasing depth, transformers can simulate several iterations of gradient descent.
Large language models (LLMs) represent a transformative class of AI tools capable of revolutionizing various aspects of healthcare by generating human-like responses across diverse contexts and adapting to novel tasks following human instructions. Their potential application spans a broad range of medical tasks, such as clinical documentation, matching patients to clinical trials, and answering medical questions. In this primer paper, we propose an actionable guideline to help healthcare professionals more efficiently utilize LLMs in their work, along with a set of best practices. This approach consists of several main phases, including formulating the task, choosing LLMs, prompt engineering, fine-tuning, and deployment. We start with the discussion of critical considerations in identifying healthcare tasks that align with the core capabilities of LLMs and selecting models based on the selected task and data, performance requirements, and model interface. We then review the strategies, such as prompt engineering and fine-tuning, to adapt standard LLMs to specialized medical tasks. Deployment considerations, including regulatory compliance, ethical guidelines, and continuous monitoring for fairness and bias, are also discussed. By providing a structured step-by-step methodology, this tutorial aims to equip healthcare professionals with the tools necessary to effectively integrate LLMs into clinical practice, ensuring that these powerful technologies are applied in a safe, reliable, and impactful manner.
Foundation models (FMs) have achieved significant success across various tasks, leading to research on benchmarks for reasoning abilities. However, there is a lack of studies on FMs performance in exceptional scenarios, which we define as out-of-distribution (OOD) reasoning tasks. This paper is the first to address these cases, developing a novel dataset for evaluation of FMs across multiple modalities, including graphic novels, calligraphy, news articles, and lyrics. It includes tasks for instance classification, character recognition, token prediction, and text generation. The paper also proposes prompt engineering techniques like Chain-of-Thought (CoT) and CoT+Few-Shot to enhance performance. Validation of FMs using various methods revealed improvements. The code repository is accessible at: https://github.com/MLAI-Yonsei/ExceptionalBenchmark
There are already many DNA large language models, but most of them still follow traditional uses, such as extracting sequence features for classification tasks. More innovative applications of large language models, such as prompt engineering, RAG, and zero-shot or few-shot prediction, remain challenging for DNA-based models. The key issue lies in the fact that DNA models and human natural language models are entirely separate; however, techniques like prompt engineering require the use of natural language, thereby significantly limiting the application of DNA large language models. This paper introduces a pre-trained model trained on the GPT-2 network, combining DNA sequences and English text, and uses a unified BPE tokenization method. We then convert classification and other downstream tasks into Alpaca format instruction data, and perform instruction fine-tuning on this pre-trained model to create a fine-tuned model capable of handling multiple tasks. The model has demonstrated its effectiveness in DNA related zero-shot prediction and multitask application. This research provides a highly promising direction for building a unified DNA sequence task framework.
This study addresses the gap in the literature concerning the comparative performance of LLMs in interpreting different types of figurative language across multiple languages. By evaluating LLMs using two multilingual datasets on simile and idiom interpretation, we explore the effectiveness of various prompt engineering strategies, including chain-of-thought, few-shot, and English translation prompts. We extend the language of these datasets to Persian as well by building two new evaluation sets. Our comprehensive assessment involves both closed-source (GPT-3.5, GPT-4o mini, Gemini 1.5), and open-source models (Llama 3.1, Qwen2), highlighting significant differences in performance across languages and figurative types. Our findings reveal that while prompt engineering methods are generally effective, their success varies by figurative type, language, and model. We also observe that open-source models struggle particularly with low-resource languages in similes. Additionally, idiom interpretation is nearing saturation for many languages, necessitating more challenging evaluations.
Recent breakthroughs in artificial intelligence have driven a paradigm shift, where large language models (LLMs) with billions or trillions of parameters are trained on vast datasets, achieving unprecedented success across a series of language tasks. However, despite these successes, LLMs still rely on probabilistic modeling, which often captures spurious correlations rooted in linguistic patterns and social stereotypes, rather than the true causal relationships between entities and events. This limitation renders LLMs vulnerable to issues such as demographic biases, social stereotypes, and LLM hallucinations. These challenges highlight the urgent need to integrate causality into LLMs, moving beyond correlation-driven paradigms to build more reliable and ethically aligned AI systems. While many existing surveys and studies focus on utilizing prompt engineering to activate LLMs for causal knowledge or developing benchmarks to assess their causal reasoning abilities, most of these efforts rely on human intervention to activate pre-trained models. How to embed causality into the training process of LLMs and build more general and intelligent models remains unexplored. Recent research highlights that LLMs function as causal parrots, capable of reciting causal knowledge without truly understanding or applying it. These prompt-based methods are still limited to human interventional improvements. This survey aims to address this gap by exploring how causality can enhance LLMs at every stage of their lifecycle-from token embedding learning and foundation model training to fine-tuning, alignment, inference, and evaluation-paving the way for more interpretable, reliable, and causally-informed models. Additionally, we further outline six promising future directions to advance LLM development, enhance their causal reasoning capabilities, and address the current limitations these models face.
This paper describes a new spatial correspondence representation based on paired regions-of-interest (ROIs), for medical image registration. The distinct properties of the proposed ROI-based correspondence are discussed, in the context of potential benefits in clinical applications following image registration, compared with alternative correspondence-representing approaches, such as those based on sampled displacements and spatial transformation functions. These benefits include a clear connection between learning-based image registration and segmentation, which in turn motivates two cases of image registration approaches using (pre-)trained segmentation networks. Based on the segment anything model (SAM), a vision foundation model for segmentation, we develop a new registration algorithm SAMReg, which does not require any training (or training data), gradient-based fine-tuning or prompt engineering. The proposed SAMReg models are evaluated across five real-world applications, including intra-subject registration tasks with cardiac MR and lung CT, challenging inter-subject registration scenarios with prostate MR and retinal imaging, and an additional evaluation with a non-clinical example with aerial image registration. The proposed methods outperform both intensity-based iterative algorithms and DDF-predicting learning-based networks across tested metrics including Dice and target registration errors on anatomical structures, and further demonstrates competitive performance compared to weakly-supervised registration approaches that rely on fully-segmented training data. Open source code and examples are available at: https://github.com/sqhuang0103/SAMReg.git.
Instruction-following is crucial for building AI agents with large language models (LLMs), as these models must adhere strictly to user-provided constraints and guidelines. However, LLMs often fail to follow even simple and clear instructions. To improve instruction-following behavior and prevent undesirable outputs, a deeper understanding of how LLMs' internal states relate to these outcomes is required. In this work, we investigate whether LLMs encode information in their representations that correlate with instruction-following success - a property we term knowing internally. Our analysis identifies a direction in the input embedding space, termed the instruction-following dimension, that predicts whether a response will comply with a given instruction. We find that this dimension generalizes well across unseen tasks but not across unseen instruction types. We demonstrate that modifying representations along this dimension improves instruction-following success rates compared to random changes, without compromising response quality. Further investigation reveals that this dimension is more closely related to the phrasing of prompts rather than the inherent difficulty of the task or instructions. This work provides insight into the internal workings of LLMs' instruction-following, paving the way for reliable LLM agents.
As large language models (LLMs) become increasingly accessible in many countries, it is essential to align them to serve pluralistic human values across cultures. However, pluralistic culture alignment in LLMs remain an open problem. In this paper, we propose CultureSPA, a Self-Pluralising Culture Alignment framework that allows LLMs to simultaneously align to pluralistic cultures. The framework first generates questions on various culture topics, then yields LLM outputs in response to these generated questions under both culture-aware and culture-unaware settings. By comparing culture-aware/unaware outputs, we are able to detect and collect culture-related instances. These instances are employed to fine-tune LLMs to serve pluralistic cultures in either a culture-joint or culture-specific way. Extensive experiments demonstrate that CultureSPA significantly improves the alignment of LLMs to diverse cultures without compromising general abilities. And further improvements can be achieved if CultureSPA is combined with advanced prompt engineering techniques. Comparisons between culture-joint and culture-specific tuning strategies, along with variations in data quality and quantity, illustrate the robustness of our method. We also explore the mechanisms underlying CultureSPA and the relations between different cultures it reflects.
Automatic question generation (QG) is essential for AI and NLP, particularly in intelligent tutoring, dialogue systems, and fact verification. Generating multiple-choice questions (MCQG) for professional exams, like the United States Medical Licensing Examination (USMLE), is particularly challenging, requiring domain expertise and complex multi-hop reasoning for high-quality questions. However, current large language models (LLMs) like GPT-4 struggle with professional MCQG due to outdated knowledge, hallucination issues, and prompt sensitivity, resulting in unsatisfactory quality and difficulty. To address these challenges, we propose MCQG-SRefine, an LLM self-refine-based (Critique and Correction) framework for converting medical cases into high-quality USMLE-style questions. By integrating expert-driven prompt engineering with iterative self-critique and self-correction feedback, MCQG-SRefine significantly enhances human expert satisfaction regarding both the quality and difficulty of the questions. Furthermore, we introduce an LLM-as-Judge-based automatic metric to replace the complex and costly expert evaluation process, ensuring reliable and expert-aligned assessments.
Guidewire segmentation during endovascular interventions holds the potential to significantly enhance procedural accuracy, improving visualization and providing critical feedback that can support both physicians and robotic systems in navigating complex vascular pathways. Unlike supervised segmentation networks, which need many expensive expert-annotated labels, sim-to-real domain adaptation approaches utilize synthetic data from simulations, offering a cost-effective solution. The success of models like Segment-Anything (SAM) has driven advancements in image segmentation foundation models with strong zero/few-shot generalization through prompt engineering. However, they struggle with medical images like X-ray fluoroscopy and the domain-shifts of the data. Given the challenges of acquiring annotation and the accessibility of labeled simulation data, we propose a sim-to-real domain adaption framework with a coarse-to-fine strategy to adapt SAM to X-ray fluoroscopy guidewire segmentation without any annotation on the target domain. We first generate the pseudo-labels by utilizing a simple source image style transfer technique that preserves the guidewire structure. Then, we develop a weakly supervised self-training architecture to fine-tune an end-to-end student SAM with the coarse labels by imposing consistency regularization and supervision from the teacher SAM network. We validate the effectiveness of the proposed method on a publicly available Cardiac dataset and an in-house Neurovascular dataset, where our method surpasses both pre-trained SAM and many state-of-the-art domain adaptation techniques by a large margin. Our code will be made public on GitHub soon.
Text-to-video (T2V) models like Sora have made significant strides in visualizing complex prompts, which is increasingly viewed as a promising path towards constructing the universal world simulator. Cognitive psychologists believe that the foundation for achieving this goal is the ability to understand intuitive physics. However, the capacity of these models to accurately represent intuitive physics remains largely unexplored. To bridge this gap, we introduce PhyGenBench, a comprehensive \textbf{Phy}sics \textbf{Gen}eration \textbf{Ben}chmark designed to evaluate physical commonsense correctness in T2V generation. PhyGenBench comprises 160 carefully crafted prompts across 27 distinct physical laws, spanning four fundamental domains, which could comprehensively assesses models' understanding of physical commonsense. Alongside PhyGenBench, we propose a novel evaluation framework called PhyGenEval. This framework employs a hierarchical evaluation structure utilizing appropriate advanced vision-language models and large language models to assess physical commonsense. Through PhyGenBench and PhyGenEval, we can conduct large-scale automated assessments of T2V models' understanding of physical commonsense, which align closely with human feedback. Our evaluation results and in-depth analysis demonstrate that current models struggle to generate videos that comply with physical commonsense. Moreover, simply scaling up models or employing prompt engineering techniques is insufficient to fully address the challenges presented by PhyGenBench (e.g., dynamic scenarios). We hope this study will inspire the community to prioritize the learning of physical commonsense in these models beyond entertainment applications. We will release the data and codes at https://github.com/OpenGVLab/PhyGenBench
Ontologies often lack explicit disjointness declarations between classes, despite their usefulness for sophisticated reasoning and consistency checking in Knowledge Graphs. In this study, we explore the potential of Large Language Models (LLMs) to enrich ontologies by identifying and asserting class disjointness axioms. Our approach aims at leveraging the implicit knowledge embedded in LLMs, using prompt engineering to elicit this knowledge for classifying ontological disjointness. We validate our methodology on the DBpedia ontology, focusing on open-source LLMs. Our findings suggest that LLMs, when guided by effective prompt strategies, can reliably identify disjoint class relationships, thus streamlining the process of ontology completion without extensive manual input. For comprehensive disjointness enrichment, we propose a process that takes logical relationships between disjointness and subclass statements into account in order to maintain satisfiability and reduce the number of calls to the LLM. This work provides a foundation for future applications of LLMs in automated ontology enhancement and offers insights into optimizing LLM performance through strategic prompt design. Our code is publicly available on GitHub at https://github.com/n28div/llm-disjointness.
Simulating learner actions helps stress-test open-ended interactive learning environments and prototype new adaptations before deployment. While recent studies show the promise of using large language models (LLMs) for simulating human behavior, such approaches have not gone beyond rudimentary proof-of-concept stages due to key limitations. First, LLMs are highly sensitive to minor prompt variations, raising doubts about their ability to generalize to new scenarios without extensive prompt engineering. Moreover, apparently successful outcomes can often be unreliable, either because domain experts unintentionally guide LLMs to produce expected results, leading to self-fulfilling prophecies; or because the LLM has encountered highly similar scenarios in its training data, meaning that models may not be simulating behavior so much as regurgitating memorized content. To address these challenges, we propose Hyp-Mix, a simulation authoring framework that allows experts to develop and evaluate simulations by combining testable hypotheses about learner behavior. Testing this framework in a physics learning environment, we found that GPT-4 Turbo maintains calibrated behavior even as the underlying learner model changes, providing the first evidence that LLMs can be used to simulate realistic behaviors in open-ended interactive learning environments, a necessary prerequisite for useful LLM behavioral simulation.
Existing automatic prompt engineering methods are typically designed for discriminative tasks, where new task prompts are iteratively refined with limited feedback from a single metric reflecting a single aspect. However, these approaches are suboptimal for generative tasks, which require more nuanced guidance beyond a single numeric metric to improve the prompt and optimize multiple aspects of the generated text. To address these challenges, we propose a novel multi-aspect Critique-Suggestion-guided automatic Prompt Optimization (CriSPO) approach. CriSPO introduces a critique-suggestion module as its core component. This module spontaneously discovers aspects, and compares generated and reference texts across these aspects, providing specific suggestions for prompt modification. These clear critiques and actionable suggestions guide a receptive optimizer module to make more substantial changes, exploring a broader and more effective search space. To further improve CriSPO with multi-metric optimization, we introduce an Automatic Suffix Tuning (AST) extension to enhance the performance of task prompts across multiple metrics. We evaluate CriSPO on 4 state-of-the-art LLMs across 4 summarization and 5 QA datasets. Extensive experiments show 3-4% ROUGE score improvement on summarization and substantial improvement of various metrics on QA. Code available at https://github.com/amazon-science/crispo