Large Language Models (LLMs) have shown promise in clinical applications through prompt engineering, allowing flexible clinical predictions. However, they struggle to produce reliable prediction probabilities, which are crucial for transparency and decision-making. While explicit prompts can lead LLMs to generate probability estimates, their numerical reasoning limitations raise concerns about reliability. We compared explicit probabilities from text generation to implicit probabilities derived from the likelihood of predicting the correct label token. Across six advanced open-source LLMs and five medical datasets, explicit probabilities consistently underperformed implicit probabilities in discrimination, precision, and recall. This discrepancy is more pronounced with smaller LLMs and imbalanced datasets, highlighting the need for cautious interpretation, improved probability estimation methods, and further research for clinical use of LLMs.
Large Language Models (LLMs) are increasingly attracting attention in various applications. Nonetheless, there is a growing concern as some users attempt to exploit these models for malicious purposes, including the synthesis of controlled substances and the propagation of disinformation. In an effort to mitigate such risks, the concept of "Alignment" technology has been developed. However, recent studies indicate that this alignment can be undermined using sophisticated prompt engineering or adversarial suffixes, a technique known as "Jailbreak." Our research takes cues from the human-like generate process of LLMs. We identify that while jailbreaking prompts may yield output logits similar to benign prompts, their initial embeddings within the model's latent space tend to be more analogous to those of malicious prompts. Leveraging this finding, we propose utilizing the early transformer outputs of LLMs as a means to detect malicious inputs, and terminate the generation immediately. Built upon this idea, we introduce a simple yet significant defense approach called EEG-Defender for LLMs. We conduct comprehensive experiments on ten jailbreak methods across three models. Our results demonstrate that EEG-Defender is capable of reducing the Attack Success Rate (ASR) by a significant margin, roughly 85\% in comparison with 50\% for the present SOTAs, with minimal impact on the utility and effectiveness of LLMs.
Large Vision-Language Models (LVLMs) have shown significant capability in vision-language understanding. However, one critical issue that persists in these models is sycophancy, which means models are unduly influenced by leading or deceptive prompts, resulting in biased outputs and hallucinations. Despite the progress in LVLMs, evaluating and mitigating sycophancy is yet much under-explored. In this work, we fill this gap by systematically analyzing sycophancy on various VL benchmarks with curated leading queries and further proposing a text contrastive decoding method for mitigation. While the specific sycophantic behavior varies significantly among models, our analysis reveals the severe deficiency of all LVLMs in resilience of sycophancy across various tasks. For improvement, we propose Leading Query Contrastive Decoding (LQCD), a model-agnostic method focusing on calibrating the LVLMs' over-reliance on leading cues by identifying and suppressing the probabilities of sycophancy tokens at the decoding stage. Extensive experiments show that LQCD effectively mitigate sycophancy, outperforming both prompt engineering methods and common methods for hallucination mitigation. We further demonstrate that LQCD does not hurt but even slightly improves LVLMs' responses to neutral queries, suggesting it being a more effective strategy for general-purpose decoding but not limited to sycophancy.
Large Language Models (LLMs) have seen increasing use in various software development tasks, especially in code generation. The most advanced recent methods attempt to incorporate feedback from code execution into prompts to help guide LLMs in generating correct code, in an iterative process. While effective, these methods could be costly and time-consuming due to numerous interactions with the LLM and the extensive token usage. To address this issue, we propose an alternative approach named Evolutionary Prompt Engineering for Code (EPiC), which leverages a lightweight evolutionary algorithm to evolve the original prompts toward better ones that produce high-quality code, with minimal interactions with LLM. Our evaluation against state-of-the-art (SOTA) LLM-based code generation models shows that EPiC outperforms all the baselines in terms of cost-effectiveness.
Prompt engineering has demonstrated remarkable success in enhancing the performance of large language models (LLMs) across diverse tasks. However, most existing prompt optimization methods only focus on the task-level performance, overlooking the importance of query-preferred prompts, which leads to suboptimal performances. Additionally, these methods rely heavily on frequent interactions with LLMs to obtain feedback for guiding the optimization process, incurring substantial redundant interaction costs. In this paper, we introduce Query-dependent Prompt Optimization (QPO), which leverages multi-loop offline reinforcement learning to iteratively fine-tune a small pretrained language model to generate optimal prompts tailored to the input queries, thus significantly improving the prompting effect on the large target LLM. We derive insights from offline prompting demonstration data, which already exists in large quantities as a by-product of benchmarking diverse prompts on open-sourced tasks, thereby circumventing the expenses of online interactions. Furthermore, we continuously augment the offline dataset with the generated prompts in each loop, as the prompts from the fine-tuned model are supposed to outperform the source prompts in the original dataset. These iterative loops bootstrap the model towards generating optimal prompts. Experiments on various LLM scales and diverse NLP and math tasks demonstrate the efficacy and cost-efficiency of our method in both zero-shot and few-shot scenarios.
Knowledge graph completion (KGC) focuses on identifying missing triples in a knowledge graph (KG) , which is crucial for many downstream applications. Given the rapid development of large language models (LLMs), some LLM-based methods are proposed for KGC task. However, most of them focus on prompt engineering while overlooking the fact that finer-grained subgraph information can aid LLMs in generating more accurate answers. In this paper, we propose a novel completion framework called \textbf{G}enerative \textbf{S}ubgraph-based KGC (GS-KGC), which utilizes subgraph information as contextual reasoning and employs a QA approach to achieve the KGC task. This framework primarily includes a subgraph partitioning algorithm designed to generate negatives and neighbors. Specifically, negatives can encourage LLMs to generate a broader range of answers, while neighbors provide additional contextual insights for LLM reasoning. Furthermore, we found that GS-KGC can discover potential triples within the KGs and new facts beyond the KGs. Experiments conducted on four common KGC datasets highlight the advantages of the proposed GS-KGC, e.g., it shows a 5.6\% increase in Hits@3 compared to the LLM-based model CP-KGC on the FB15k-237N, and a 9.3\% increase over the LLM-based model TECHS on the ICEWS14.
The application of large-language models (LLMs) to digital hardware code generation is an emerging field, with most LLMs primarily trained on natural language and software code. Hardware code like Verilog constitutes a small portion of training data, and few hardware benchmarks exist. The open-source VerilogEval benchmark, released in November 2023, provided a consistent evaluation framework for LLMs on code completion tasks. Since then, both commercial and open models have seen significant development. In this work, we evaluate new commercial and open models since VerilogEval's original release-including GPT-4o, GPT-4 Turbo, Llama3.1 (8B/70B/405B), Llama3 70B, Mistral Large, DeepSeek Coder (33B and 6.7B), CodeGemma 7B, and RTL-Coder-against an improved VerilogEval benchmark suite. We find measurable improvements in state-of-the-art models: GPT-4o achieves a 63% pass rate on specification-to-RTL tasks. The recently released and open Llama3.1 405B achieves a 58% pass rate, almost matching GPT-4o, while the smaller domain-specific RTL-Coder 6.7B models achieve an impressive 34% pass rate. Additionally, we enhance VerilogEval's infrastructure by automatically classifying failures, introducing in-context learning support, and extending the tasks to specification-to-RTL translation. We find that prompt engineering remains crucial for achieving good pass rates and varies widely with model and task. A benchmark infrastructure that allows for prompt engineering and failure analysis is essential for continued model development and deployment.
Road traffic crashes result in millions of deaths annually and significant economic burdens, particularly on Low- and Middle-Income Countries (LMICs). Road safety assessments traditionally rely on human-labelled data, which is labour-intensive and time-consuming. While Convolutional Neural Networks (CNNs) have advanced automated road safety assessments, they typically demand large labelled datasets and often require fine-tuning for each new geographic context. This study explores whether Vision Language Models (VLMs) with zero-shot capability can overcome these limitations to serve as effective road safety assessors using the International Road Assessment Programme (iRAP) standard. Our approach, V-RoAst (Visual question answering for Road Assessment), leverages advanced VLMs, such as Gemini-1.5-flash and GPT-4o-mini, to analyse road safety attributes without requiring any labelled training data. By optimising prompt engineering and utilising crowdsourced imagery from Mapillary, V-RoAst provides a scalable, cost-effective, and automated solution for global road safety assessments. Preliminary results show that while VLMs achieve lower performance than CNN-based models, they are capable of Visual Question Answering (VQA) and show potential in predicting star ratings from crowdsourced imagery. However, their performance is poor when key visual features are absent in the imagery, emphasising the need for human labelling to address these gaps. Advancements in VLMs, alongside in-context learning such as chain-of-thought and few-shot learning, and parameter-efficient fine-tuning, present opportunities for improvement, making VLMs promising tools for road assessment tasks. Designed for resource-constrained stakeholders, this framework holds the potential to save lives and reduce economic burdens worldwide. Code and dataset are available at: https://github.com/PongNJ/V-RoAst.
Traditional methods for making software deployment decisions in the automotive industry typically rely on manual analysis of tabular software test data. These methods often lead to higher costs and delays in the software release cycle due to their labor-intensive nature. Large Language Models (LLMs) present a promising solution to these challenges. However, their application generally demands multiple rounds of human-driven prompt engineering, which limits their practical deployment, particularly for industrial end-users who need reliable and efficient results. In this paper, we propose GoNoGo, an LLM agent system designed to streamline automotive software deployment while meeting both functional requirements and practical industrial constraints. Unlike previous systems, GoNoGo is specifically tailored to address domain-specific and risk-sensitive systems. We evaluate GoNoGo's performance across different task difficulties using zero-shot and few-shot examples taken from industrial practice. Our results show that GoNoGo achieves a 100% success rate for tasks up to Level 2 difficulty with 3-shot examples, and maintains high performance even for more complex tasks. We find that GoNoGo effectively automates decision-making for simpler tasks, significantly reducing the need for manual intervention. In summary, GoNoGo represents an efficient and user-friendly LLM-based solution currently employed in our industrial partner's company to assist with software release decision-making, supporting more informed and timely decisions in the release process for risk-sensitive vehicle systems.
This study evaluates the performance of Large Language Models (LLMs) as an Artificial Intelligence-based tutor for a university course. In particular, different advanced techniques are utilized, such as prompt engineering, Retrieval-Augmented-Generation (RAG), and fine-tuning. We assessed the different models and applied techniques using common similarity metrics like BLEU-4, ROUGE, and BERTScore, complemented by a small human evaluation of helpfulness and trustworthiness. Our findings indicate that RAG combined with prompt engineering significantly enhances model responses and produces better factual answers. In the context of education, RAG appears as an ideal technique as it is based on enriching the input of the model with additional information and material which usually is already present for a university course. Fine-tuning, on the other hand, can produce quite small, still strong expert models, but poses the danger of overfitting. Our study further asks how we measure performance of LLMs and how well current measurements represent correctness or relevance? We find high correlation on similarity metrics and a bias of most of these metrics towards shorter responses. Overall, our research points to both the potential and challenges of integrating LLMs in educational settings, suggesting a need for balanced training approaches and advanced evaluation frameworks.
Affective Computing (AC), integrating computer science, psychology, and cognitive science knowledge, aims to enable machines to recognize, interpret, and simulate human emotions.To create more value, AC can be applied to diverse scenarios, including social media, finance, healthcare, education, etc. Affective Computing (AC) includes two mainstream tasks, i.e., Affective Understanding (AU) and Affective Generation (AG). Fine-tuning Pre-trained Language Models (PLMs) for AU tasks has succeeded considerably. However, these models lack generalization ability, requiring specialized models for specific tasks. Additionally, traditional PLMs face challenges in AG, particularly in generating diverse and emotionally rich responses. The emergence of Large Language Models (LLMs), such as the ChatGPT series and LLaMA models, brings new opportunities and challenges, catalyzing a paradigm shift in AC. LLMs possess capabilities of in-context learning, common sense reasoning, and advanced sequence generation, which present unprecedented opportunities for AU. To provide a comprehensive overview of AC in the LLMs era from an NLP perspective, we summarize the development of LLMs research in this field, aiming to offer new insights. Specifically, we first summarize the traditional tasks related to AC and introduce the preliminary study based on LLMs. Subsequently, we outline the relevant techniques of popular LLMs to improve AC tasks, including Instruction Tuning and Prompt Engineering. For Instruction Tuning, we discuss full parameter fine-tuning and parameter-efficient methods such as LoRA, P-Tuning, and Prompt Tuning. In Prompt Engineering, we examine Zero-shot, Few-shot, Chain of Thought (CoT), and Agent-based methods for AU and AG. To clearly understand the performance of LLMs on different Affective Computing tasks, we further summarize the existing benchmarks and evaluation methods.
The analysis of students' emotions and behaviors is crucial for enhancing learning outcomes and personalizing educational experiences. Traditional methods often rely on intrusive visual and physiological data collection, posing privacy concerns and scalability issues. This paper proposes a novel method leveraging large language models (LLMs) and prompt engineering to analyze textual data from students. Our approach utilizes tailored prompts to guide LLMs in detecting emotional and engagement states, providing a non-intrusive and scalable solution. We conducted experiments using Qwen, ChatGPT, Claude2, and GPT-4, comparing our method against baseline models and chain-of-thought (CoT) prompting. Results demonstrate that our method significantly outperforms the baselines in both accuracy and contextual understanding. This study highlights the potential of LLMs combined with prompt engineering to offer practical and effective tools for educational emotion and behavior analysis.
In the field of Natural Language Processing (NLP), Large Language Models (LLMs) have shown great potential in document-level event extraction tasks, but existing methods face challenges in the design of prompts. To address this issue, we propose an optimization strategy called "Definition-driven Document-level Event Extraction (DDEE)." By adjusting the length of the prompt and enhancing the clarity of heuristics, we have significantly improved the event extraction performance of LLMs. We used data balancing techniques to solve the long-tail effect problem, enhancing the model's generalization ability for event types. At the same time, we refined the prompt to ensure it is both concise and comprehensive, adapting to the sensitivity of LLMs to the style of prompts. In addition, the introduction of structured heuristic methods and strict limiting conditions has improved the precision of event and argument role extraction. These strategies not only solve the prompt engineering problems of LLMs in document-level event extraction but also promote the development of event extraction technology, providing new research perspectives for other tasks in the NLP field.
Recent trends in Generative AI have emerged towards fine-tuning foundational large language models (LLMs) to create domain-specific LLMs for automation and chatbot-like applications. Specialized applications for analytics-heavy domains such as Financial report generation require specific writing styles that comprise compound and creative sentences with minimized hallucinations. In this work, we explore the self-corrective auto-regressive qualities of LLMs to learn creativity in writing styles with minimal prompting. We propose a novel two-stage fine-tuning (FT) strategy wherein in the first stage public domain financial reports are used to train for writing styles while allowing the LLM to hallucinate. In the second stage the examples of hallucinations are manually corrected and further used to fine-tune the LLM. The finally trained LLM learns to generate specific financial report sections using minimal instructions and tabular data inputs while ensuring low fine-tuning costs. Our proposed two-stage fine-tuning boosts the accuracy of financial questions answering by two-folds while reducing hallucinations by over 50%. Also, the fine-tuned model has lower perplexity, improved ROUGE, TER and BLEU scores, higher creativity and knowledge density with lower uncertainty and cross entropy than base LLMs. Thus, the proposed framework can be generalized to train creativity in LLMs by first allowing them to hallucinate.
Prompts are how humans communicate with LLMs. Informative prompts are essential for guiding LLMs to produce the desired output. However, prompt engineering is often tedious and time-consuming, requiring significant expertise, limiting its widespread use. We propose Conversational Prompt Engineering (CPE), a user-friendly tool that helps users create personalized prompts for their specific tasks. CPE uses a chat model to briefly interact with users, helping them articulate their output preferences and integrating these into the prompt. The process includes two main stages: first, the model uses user-provided unlabeled data to generate data-driven questions and utilize user responses to shape the initial instruction. Then, the model shares the outputs generated by the instruction and uses user feedback to further refine the instruction and the outputs. The final result is a few-shot prompt, where the outputs approved by the user serve as few-shot examples. A user study on summarization tasks demonstrates the value of CPE in creating personalized, high-performing prompts. The results suggest that the zero-shot prompt obtained is comparable to its - much longer - few-shot counterpart, indicating significant savings in scenarios involving repetitive tasks with large text volumes.
Automated Short Answer Scoring (ASAS) is a critical component in educational assessment. While traditional ASAS systems relied on rule-based algorithms or complex deep learning methods, recent advancements in Generative Language Models (GLMs) offer new opportunities for improvement. This study explores the application of GLMs to ASAS, leveraging their off-the-shelf capabilities and performance in various domains. We propose a novel pipeline that combines vector databases, transformer-based encoders, and GLMs to enhance short answer scoring accuracy. Our approach stores training responses in a vector database, retrieves semantically similar responses during inference, and employs a GLM to analyze these responses and determine appropriate scores. We further optimize the system through fine-tuned retrieval processes and prompt engineering. Evaluation on the SemEval 2013 dataset demonstrates a significant improvement on the SCIENTSBANK 3-way and 2-way tasks compared to existing methods, highlighting the potential of GLMs in advancing ASAS technology.
Traditional base station siting (BSS) methods rely heavily on drive testing and user feedback, which are laborious and require extensive expertise in communication, networking, and optimization. As large language models (LLMs) and their associated technologies advance, particularly in the realms of prompt engineering and agent engineering, network optimization will witness a revolutionary approach. This approach entails the strategic use of well-crafted prompts to infuse human experience and knowledge into these sophisticated LLMs, and the deployment of autonomous agents as a communication bridge to seamlessly connect the machine language based LLMs with human users using natural language. Furthermore, our proposed framework incorporates retrieval-augmented generation (RAG) to enhance the system's ability to acquire domain-specific knowledge and generate solutions, thereby enabling the customization and optimization of the BSS process. This integration represents the future paradigm of artificial intelligence (AI) as a service and AI for more ease. This research first develops a novel LLM-empowered BSS optimization framework, and heuristically proposes three different potential implementations: the strategies based on Prompt-optimized LLM (PoL), LLM-empowered autonomous BSS agent (LaBa), and Cooperative multiple LLM-based autonomous BSS agents (CLaBa). Through evaluation on real-world data, the experiments demonstrate that prompt-assisted LLMs and LLM-based agents can generate more efficient and reliable network deployments, noticeably enhancing the efficiency of BSS optimization and reducing trivial manual participation.
The rapid evolution of software development necessitates enhanced safety measures. Extracting information about software failures from companies is becoming increasingly more available through news articles. This research utilizes the Failure Analysis Investigation with LLMs (FAIL) model to extract industry-specific information. Although the FAIL model's database is rich in information, it could benefit from further categorization and industry-specific insights to further assist software engineers. In previous work news articles were collected from reputable sources and categorized by incidents inside a database. Prompt engineering and Large Language Models (LLMs) were then applied to extract relevant information regarding the software failure. This research extends these methods by categorizing articles into specific domains and types of software failures. The results are visually represented through graphs. The analysis shows that throughout the database some software failures occur significantly more often in specific industries. This categorization provides a valuable resource for software engineers and companies to identify and address common failures. This research highlights the synergy between software engineering and Large Language Models (LLMs) to automate and enhance the analysis of software failures. By transforming data from the database into an industry specific model, we provide a valuable resource that can be used to identify common vulnerabilities, predict potential risks, and implement proactive measures for preventing software failures. Leveraging the power of the current FAIL database and data visualization, we aim to provide an avenue for safer and more secure software in the future.
Foundation models have had a big impact in recent years and billions of dollars are being invested in them in the current AI boom. The more popular ones, such as Chat-GPT, are trained on large amounts of Internet data. However, it is becoming apparent that this data is likely to be exhausted soon, and technology companies are looking for new sources of data to train the next generation of foundation models. Reinforcement learning, RAG, prompt engineering and cognitive modelling are often used to fine-tune and augment the behaviour of foundation models. These techniques have been used to replicate people, such as Caryn Marjorie. These chatbots are not based on people's actual emotional and physiological responses to their environment, so they are, at best, a surface-level approximation to the characters they are imitating. To address these issues, we have developed a recording rig that captures what the wearer is seeing and hearing as well as their skin conductance (GSR), facial expression and brain state (14 channel EEG). AI algorithms are used to process this data into a rich picture of the environment and internal states of the subject. Foundation models trained on this data could replicate human behaviour much more accurately than the personality models that have been developed so far. This type of model has many potential applications, including recommendation, personal assistance, GAN systems, dating and recruitment. This paper gives some background to this work and describes the recording rig and preliminary tests of its functionality. It then suggests how a new type of foundation model could be created from the data captured by the rig and outlines some applications. Data gathering and model training are expensive, so we are currently working on the launch of a start-up that could raise funds for the next stage of the project.
Large language models (LLMs) are fundamentally transforming human-facing applications in the health and well-being domains: boosting patient engagement, accelerating clinical decision-making, and facilitating medical education. Although state-of-the-art LLMs have shown superior performance in several conversational applications, evaluations within nutrition and diet applications are still insufficient. In this paper, we propose to employ the Registered Dietitian (RD) exam to conduct a standard and comprehensive evaluation of state-of-the-art LLMs, GPT-4o, Claude 3.5 Sonnet, and Gemini 1.5 Pro, assessing both accuracy and consistency in nutrition queries. Our evaluation includes 1050 RD exam questions encompassing several nutrition topics and proficiency levels. In addition, for the first time, we examine the impact of Zero-Shot (ZS), Chain of Thought (CoT), Chain of Thought with Self Consistency (CoT-SC), and Retrieval Augmented Prompting (RAP) on both accuracy and consistency of the responses. Our findings revealed that while these LLMs obtained acceptable overall performance, their results varied considerably with different prompts and question domains. GPT-4o with CoT-SC prompting outperformed the other approaches, whereas Gemini 1.5 Pro with ZS recorded the highest consistency. For GPT-4o and Claude 3.5, CoT improved the accuracy, and CoT-SC improved both accuracy and consistency. RAP was particularly effective for GPT-4o to answer Expert level questions. Consequently, choosing the appropriate LLM and prompting technique, tailored to the proficiency level and specific domain, can mitigate errors and potential risks in diet and nutrition chatbots.