Large-language models are capable of completing a variety of tasks, but remain unpredictable and intractable. Representation engineering seeks to resolve this problem through a new approach utilizing samples of contrasting inputs to detect and edit high-level representations of concepts such as honesty, harmfulness or power-seeking. We formalize the goals and methods of representation engineering to present a cohesive picture of work in this emerging discipline. We compare it with alternative approaches, such as mechanistic interpretability, prompt-engineering and fine-tuning. We outline risks such as performance decrease, compute time increases and steerability issues. We present a clear agenda for future research to build predictable, dynamic, safe and personalizable LLMs.
With rapid advancements in artificial intelligence, question-answering (Q&A) systems have become essential in intelligent search engines, virtual assistants, and customer service platforms. However, in dynamic domains like smart grids, conventional retrieval-augmented generation(RAG) Q&A systems face challenges such as inadequate retrieval quality, irrelevant responses, and inefficiencies in handling large-scale, real-time data streams. This paper proposes an optimized iterative retrieval-based Q&A framework called Chats-Grid tailored for smart grid environments. In the pre-retrieval phase, Chats-Grid advanced query expansion ensures comprehensive coverage of diverse data sources, including sensor readings, meter records, and control system parameters. During retrieval, Best Matching 25(BM25) sparse retrieval and BAAI General Embedding(BGE) dense retrieval in Chats-Grid are combined to process vast, heterogeneous datasets effectively. Post-retrieval, a fine-tuned large language model uses prompt engineering to assess relevance, filter irrelevant results, and reorder documents based on contextual accuracy. The model further generates precise, context-aware answers, adhering to quality criteria and employing a self-checking mechanism for enhanced reliability. Experimental results demonstrate Chats-Grid's superiority over state-of-the-art methods in fidelity, contextual recall, relevance, and accuracy by 2.37%, 2.19%, and 3.58% respectively. This framework advances smart grid management by improving decision-making and user interactions, fostering resilient and adaptive smart grid infrastructures.
Large language models (LLMs) present novel opportunities in public opinion research by predicting survey responses in advance during the early stages of survey design. Prior methods steer LLMs via descriptions of subpopulations as LLMs' input prompt, yet such prompt engineering approaches have struggled to faithfully predict the distribution of survey responses from human subjects. In this work, we propose directly fine-tuning LLMs to predict response distributions by leveraging unique structural characteristics of survey data. To enable fine-tuning, we curate SubPOP, a significantly scaled dataset of 3,362 questions and 70K subpopulation-response pairs from well-established public opinion surveys. We show that fine-tuning on SubPOP greatly improves the match between LLM predictions and human responses across various subpopulations, reducing the LLM-human gap by up to 46% compared to baselines, and achieves strong generalization to unseen surveys and subpopulations. Our findings highlight the potential of survey-based fine-tuning to improve opinion prediction for diverse, real-world subpopulations and therefore enable more efficient survey designs. Our code is available at https://github.com/JosephJeesungSuh/subpop.
Large language models (LLMs) have demonstrated increasingly sophisticated performance in medical and other fields of knowledge. Traditional methods of creating specialist LLMs require extensive fine-tuning and training of models on large datasets. Recently, prompt engineering, instead of fine-tuning, has shown potential to boost the performance of general foundation models. However, prompting methods such as chain-of-thought (CoT) may not be suitable for all subspecialty, and k-shot approaches may introduce irrelevant tokens into the context space. We present AutoMedPrompt, which explores the use of textual gradients to elicit medically relevant reasoning through system prompt optimization. AutoMedPrompt leverages TextGrad's automatic differentiation via text to improve the ability of general foundation LLMs. We evaluated AutoMedPrompt on Llama 3, an open-source LLM, using several QA benchmarks, including MedQA, PubMedQA, and the nephrology subspecialty-specific NephSAP. Our results show that prompting with textual gradients outperforms previous methods on open-source LLMs and surpasses proprietary models such as GPT-4, Claude 3 Opus, and Med-PaLM 2. AutoMedPrompt sets a new state-of-the-art (SOTA) performance on PubMedQA with an accuracy of 82.6$\%$, while also outperforming previous prompting strategies on open-sourced models for MedQA (77.7$\%$) and NephSAP (63.8$\%$).
Since the advent of large language models (LLMs), prompt engineering has been a crucial step for eliciting desired responses for various Natural Language Processing (NLP) tasks. However, prompt engineering remains an impediment for end users due to rapid advances in models, tasks, and associated best practices. To mitigate this, Automatic Prompt Optimization (APO) techniques have recently emerged that use various automated techniques to help improve the performance of LLMs on various tasks. In this paper, we present a comprehensive survey summarizing the current progress and remaining challenges in this field. We provide a formal definition of APO, a 5-part unifying framework, and then proceed to rigorously categorize all relevant works based on their salient features therein. We hope to spur further research guided by our framework.
Accessing accurate medication insights is vital for enhancing patient safety, minimizing errors, and supporting clinical decision-making. However, healthcare professionals in Africa often rely on manual and time-consuming processes to retrieve drug information, exacerbated by limited access to pharmacists due to brain drain and healthcare disparities. This paper presents "Drug Insights," an open-source Retrieval-Augmented Generation (RAG) chatbot designed to streamline medication lookup for healthcare workers in Africa. By leveraging a corpus of Nigerian pharmaceutical data and advanced AI technologies, including Pinecone databases and GPT models, the system delivers accurate, context-specific responses with minimal hallucination. The chatbot integrates prompt engineering and S-BERT evaluation to optimize retrieval and response generation. Preliminary tests, including pharmacist feedback, affirm the tool's potential to improve drug information access while highlighting areas for enhancement, such as UI/UX refinement and extended corpus integration.
Code summarization is a critical task in natural language processing and software engineering, which aims to generate concise descriptions of source code. Recent advancements have improved the quality of these summaries, enhancing code readability and maintainability. However, the content of a repository or a class has not been considered in function code summarization. This study investigated the effectiveness of code summarization models beyond the function level, exploring the impact of class and repository contexts on the summary quality. The study involved revising benchmarks for evaluating models at class and repository levels, assessing baseline models, and evaluating LLMs with in-context learning to determine the enhancement of summary quality with additional context. The findings revealed that the fine-tuned state-of-the-art CodeT5+ base model excelled in code summarization, while incorporating few-shot learning and retrieved code chunks from RAG significantly enhanced the performance of LLMs in this task. Notably, the Deepseek Coder 1.3B and Starcoder2 15B models demonstrated substantial improvements in metrics such as BLEURT, METEOR, and BLEU-4 at both class and repository levels. Repository-level summarization exhibited promising potential but necessitates significant computational resources and gains from the inclusion of structured context. Lastly, we employed the recent SIDE code summarization metric in our evaluation. This study contributes to refining strategies for prompt engineering, few-shot learning, and RAG, addressing gaps in benchmarks for code summarization at various levels. Finally, we publish all study details, code, datasets, and results of evaluation in the GitHub repository available at https://github.com/kilimanj4r0/code-summarization-beyond-function-level.
Generative AI models, renowned for their ability to synthesize high-quality content, have sparked growing concerns over the improper generation of copyright-protected material. While recent studies have proposed various approaches to address copyright issues, the capability of large vision-language models (LVLMs) to detect copyright infringements remains largely unexplored. In this work, we focus on evaluating the copyright detection abilities of state-of-the-art LVLMs using a various set of image samples. Recognizing the absence of a comprehensive dataset that includes both IP-infringement samples and ambiguous non-infringement negative samples, we construct a benchmark dataset comprising positive samples that violate the copyright protection of well-known IP figures, as well as negative samples that resemble these figures but do not raise copyright concerns. This dataset is created using advanced prompt engineering techniques. We then evaluate leading LVLMs using our benchmark dataset. Our experimental results reveal that LVLMs are prone to overfitting, leading to the misclassification of some negative samples as IP-infringement cases. In the final section, we analyze these failure cases and propose potential solutions to mitigate the overfitting problem.
Accurate query-product relevance labeling is indispensable to generate ground truth dataset for search ranking in e-commerce. Traditional approaches for annotating query-product pairs rely on human-based labeling services, which is expensive, time-consuming and prone to errors. In this work, we explore the application of Large Language Models (LLMs) to automate query-product relevance labeling for large-scale e-commerce search. We use several publicly available and proprietary LLMs for this task, and conducted experiments on two open-source datasets and an in-house e-commerce search dataset. Using prompt engineering techniques such as Chain-of-Thought (CoT) prompting, In-context Learning (ICL), and Retrieval Augmented Generation (RAG) with Maximum Marginal Relevance (MMR), we show that LLM's performance has the potential to approach human-level accuracy on this task in a fraction of the time and cost required by human-labelers, thereby suggesting that our approach is more efficient than the conventional methods. We have generated query-product relevance labels using LLMs at scale, and are using them for evaluating improvements to our search algorithms. Our work demonstrates the potential of LLMs to improve query-product relevance thus enhancing e-commerce search user experience. More importantly, this scalable alternative to human-annotation has significant implications for information retrieval domains including search and recommendation systems, where relevance scoring is crucial for optimizing the ranking of products and content to improve customer engagement and other conversion metrics.
Large language models (LLMs) are increasingly deployed with hierarchical instruction schemes, where certain instructions (e.g., system-level directives) are expected to take precedence over others (e.g., user messages). Yet, we lack a systematic understanding of how effectively these hierarchical control mechanisms work. We introduce a systematic evaluation framework based on constraint prioritization to assess how well LLMs enforce instruction hierarchies. Our experiments across six state-of-the-art LLMs reveal that models struggle with consistent instruction prioritization, even for simple formatting conflicts. We find that the widely-adopted system/user prompt separation fails to establish a reliable instruction hierarchy, and models exhibit strong inherent biases toward certain constraint types regardless of their priority designation. While controlled prompt engineering and model fine-tuning show modest improvements, our results indicate that instruction hierarchy enforcement is not robustly realized, calling for deeper architectural innovations beyond surface-level modifications.
Existing navigation decision support systems often perform poorly when handling non-predefined navigation scenarios. Leveraging the generalization capabilities of large language model (LLM) in handling unknown scenarios, this research proposes a dual-core framework for LLM applications to address this issue. Firstly, through ReAct-based prompt engineering, a larger LLM core decomposes intricate navigation tasks into manageable sub-tasks, which autonomously invoke corresponding external tools to gather relevant information, using this feedback to mitigate the risk of LLM hallucinations. Subsequently, a fine-tuned and compact LLM core, acting like a first-mate is designed to process such information and unstructured external data, then to generates context-aware recommendations, ultimately delivering lookout insights and navigation hints that adhere to the International Regulations for Preventing Collisions at Sea (COLREGs) and other rules. Extensive experiments demonstrate the proposed framework not only excels in traditional ship collision avoidance tasks but also adapts effectively to unstructured, non-predefined, and unpredictable scenarios. A comparative analysis with DeepSeek-R1, GPT-4o and other SOTA models highlights the efficacy and rationality of the proposed framework. This research bridges the gap between conventional navigation systems and LLMs, offering a framework to enhance safety and operational efficiency across diverse navigation applications.
Web crawling is a critical technique for extracting online data, yet it poses challenges due to webpage diversity and anti-scraping mechanisms. This study investigates the integration of generative AI tools Claude AI (Sonnet 3.5) and ChatGPT4.0 with prompt engineering to automate web scraping. Using two prompts, PROMPT I (general inference, tested on Yahoo News) and PROMPT II (element-specific, tested on Coupons.com), we evaluate the code quality and performance of AI-generated scripts. Claude AI consistently outperformed ChatGPT-4.0 in script quality and adaptability, as confirmed by predefined evaluation metrics, including functionality, readability, modularity, and robustness. Performance data were collected through manual testing and structured scoring by three evaluators. Visualizations further illustrate Claude AI's superiority. Anti-scraping solutions, including undetected_chromedriver, Selenium, and fake_useragent, were incorporated to enhance performance. This paper demonstrates how generative AI combined with prompt engineering can simplify and improve web scraping workflows.
The generative capabilities of LLM models offer opportunities for accelerating tasks but raise concerns about the authenticity of the knowledge they produce. To address these concerns, we present a computational approach that evaluates the factual accuracy of biomedical knowledge generated by an LLM. Our approach consists of two processes: generating disease-centric associations and verifying these associations using the semantic framework of biomedical ontologies. Using ChatGPT as the selected LLM, we designed prompt-engineering processes to establish linkages between diseases and related drugs, symptoms, and genes, and assessed consistency across multiple ChatGPT models (e.g., GPT-turbo, GPT-4, etc.). Experimental results demonstrate high accuracy in identifying disease terms (88%-97%), drug names (90%-91%), and genetic information (88%-98%). However, symptom term identification was notably lower (49%-61%), due to the informal and verbose nature of symptom descriptions, which hindered effective semantic matching with the formal language of specialized ontologies. Verification of associations reveals literature coverage rates of 89%-91% for disease-drug and disease-gene pairs, while symptom-related associations exhibit lower coverage (49%-62%).
The escalating volume of collected healthcare textual data presents a unique challenge for automated Multi-Label Text Classification (MLTC), which is primarily due to the scarcity of annotated texts for training and their nuanced nature. Traditional machine learning models often fail to fully capture the array of expressed topics. However, Large Language Models (LLMs) have demonstrated remarkable effectiveness across numerous Natural Language Processing (NLP) tasks in various domains, which show impressive computational efficiency and suitability for unsupervised learning through prompt engineering. Consequently, these LLMs promise an effective MLTC of medical narratives. However, when dealing with various labels, different prompts can be relevant depending on the topic. To address these challenges, the proposed approach, QUAD-LLM-MLTC, leverages the strengths of four LLMs: GPT-4o, BERT, PEGASUS, and BART. QUAD-LLM-MLTC operates in a sequential pipeline in which BERT extracts key tokens, PEGASUS augments textual data, GPT-4o classifies, and BART provides topics' assignment probabilities, which results in four classifications, all in a 0-shot setting. The outputs are then combined using ensemble learning and processed through a meta-classifier to produce the final MLTC result. The approach is evaluated using three samples of annotated texts, which contrast it with traditional and single-model methods. The results show significant improvements across the majority of the topics in the classification's F1 score and consistency (F1 and Micro-F1 scores of 78.17% and 80.16% with standard deviations of 0.025 and 0.011, respectively). This research advances MLTC using LLMs and provides an efficient and scalable solution to rapidly categorize healthcare-related text data without further training.
This paper describes our submissions to the TREC 2024 PLABA track with the aim to simplify biomedical abstracts for a K8-level audience (13-14 years old students). We tested three approaches using OpenAI's gpt-4o and gpt-4o-mini models: baseline prompt engineering, a two-AI agent approach, and fine-tuning. Adaptations were evaluated using qualitative metrics (5-point Likert scales for simplicity, accuracy, completeness, and brevity) and quantitative readability scores (Flesch-Kincaid grade level, SMOG Index). Results indicated that the two-agent approach and baseline prompt engineering with gpt-4o-mini models show superior qualitative performance, while fine-tuned models excelled in accuracy and completeness but were less simple. The evaluation results demonstrated that prompt engineering with gpt-4o-mini outperforms iterative improvement strategies via two-agent approach as well as fine-tuning with gpt-4o. We intend to expand our investigation of the results and explore advanced evaluations.
Large language models (LLMs) have achieved remarkable performance in generating human-like text and solving reasoning tasks of moderate complexity, such as question-answering and mathematical problem-solving. However, their capabilities in tasks requiring deeper cognitive skills, such as common-sense understanding and abstract reasoning, remain under-explored. In this paper, we systematically evaluate abstract common-sense reasoning in LLMs using the ConceptNet knowledge graph. We propose two prompting approaches: instruct prompting, where models predict plausible semantic relationships based on provided definitions, and few-shot prompting, where models identify relations using examples as guidance. Our experiments with the gpt-4o-mini model show that in instruct prompting, consistent performance is obtained when ranking multiple relations but with substantial decline when the model is restricted to predicting only one relation. In few-shot prompting, the model's accuracy improves significantly when selecting from five relations rather than the full set, although with notable bias toward certain relations. These results suggest significant gaps still, even in commercially used LLMs' abstract common-sense reasoning abilities, compared to human-level understanding. However, the findings also highlight the promise of careful prompt engineering, based on selective retrieval, for obtaining better performance.
This work investigates the ability of open Large Language Models (LLMs) to predict citation intent through in-context learning and fine-tuning. Unlike traditional approaches relying on domain-specific pre-trained models like SciBERT, we demonstrate that general-purpose LLMs can be adapted to this task with minimal task-specific data. We evaluate twelve model variations across five prominent open LLM families using zero-, one-, few-, and many-shot prompting. Our experimental study identifies the top-performing model and prompting parameters through extensive in-context learning experiments. We then demonstrate the significant impact of task-specific adaptation by fine-tuning this model, achieving a relative F1-score improvement of 8% on the SciCite dataset and 4.3% on the ACL-ARC dataset compared to the instruction-tuned baseline. These findings provide valuable insights for model selection and prompt engineering. Additionally, we make our end-to-end evaluation framework and models openly available for future use.
In recent years, Large Language Models have garnered significant attention for their strong performance in various natural language tasks, such as machine translation and question answering. These models demonstrate an impressive ability to generalize across diverse tasks. However, their effectiveness in tackling domain-specific tasks, such as financial sentiment analysis and monetary policy understanding, remains a topic of debate, as these tasks often require specialized knowledge and precise reasoning. To address such challenges, researchers design various prompts to unlock the models' abilities. By carefully crafting input prompts, researchers can guide these models to produce more accurate responses. Consequently, prompt engineering has become a key focus of study. Despite the advancements in both models and prompt engineering, the relationship between the two-specifically, how prompt design impacts models' ability to perform domain-specific tasks-remains underexplored. This paper aims to bridge this research gap.
The Fourth Industrial Revolution (4IR) technologies, such as cloud computing, machine learning, and AI, have improved productivity but introduced challenges in workforce training and reskilling. This is critical given existing workforce shortages, especially in marginalized communities like Underrepresented Minorities (URM), who often lack access to quality education. Addressing these challenges, this research presents gAI-PT4I4, a Generative AI-based Personalized Tutor for Industrial 4.0, designed to personalize 4IR experiential learning. gAI-PT4I4 employs sentiment analysis to assess student comprehension, leveraging generative AI and finite automaton to tailor learning experiences. The framework integrates low-fidelity Digital Twins for VR-based training, featuring an Interactive Tutor - a generative AI assistant providing real-time guidance via audio and text. It uses zero-shot sentiment analysis with LLMs and prompt engineering, achieving 86\% accuracy in classifying student-teacher interactions as positive or negative. Additionally, retrieval-augmented generation (RAG) enables personalized learning content grounded in domain-specific knowledge. To adapt training dynamically, finite automaton structures exercises into states of increasing difficulty, requiring 80\% task-performance accuracy for progression. Experimental evaluation with 22 volunteers showed improved accuracy exceeding 80\%, reducing training time. Finally, this paper introduces a Multi-Fidelity Digital Twin model, aligning Digital Twin complexity with Bloom's Taxonomy and Kirkpatrick's model, providing a scalable educational framework.
While Large Language Models (LLMs) have emerged as promising tools for evaluating Natural Language Generation (NLG) tasks, their effectiveness is limited by their inability to appropriately weigh the importance of different topics, often overemphasizing minor details while undervaluing critical information, leading to misleading assessments. Our work proposes an efficient prompt design mechanism to address this specific limitation and provide a case study. Through strategic prompt engineering that incorporates explicit importance weighting mechanisms, we enhance using LLM-as-a-Judge ability to prioritize relevant information effectively, as demonstrated by an average improvement of 6% in the Human Alignment Rate (HAR) metric.