Adaptive Testing and Debugging of NLP Models

Large-scale language models (LLMs) have basically changed the limits of what can be achieved by natural language processing and this was the case of GPT-3 at its very first demonstration back in 2020. This study outlines in detail their journey. It goes through all the concepts of their architecture. Besides, it describes the training process. The article records the gradual increasing of their volumetry and the consequent differences of their properties along the way. Different methods of testing these models are also indicated. Besides, it refers to their application in various fields. Besides, this research work deals with the advent of multi-modal systems capable of autonomous decision-making. We have centered our work on the landmark research that has been published in the period of 2022–2024. We reckon the self-supervised pre-training, instruction tuning, preference optimization, and reasoning-directed reinforcement learning as four main areas that contributed to the development of LLMs. These approaches have converted LLMs to be no longer just the text generators but rather the most versatile AI systems that they are. Our focus is on their use in the medical field and bioinformatics. We address the challenge of explaining the functioning of large language models (LLMs). We tell the story of in-context learning. We discuss the development of LLMs-based agents. At the end, we are identifying the major limitations of the present-time and, simultaneously, suggesting a few ideas for the future in this fast-evolving area.

Large-scale language models, such as ChatGPT[3] and GPT-4[32], have demonstrated remarkable capabilities in generating human-like text for various applications. In this paper, we focus on two key aspects: (1) adapting open-source large language models (LLMs) for specific use cases like contract drafting using instruction tuning and parameter-efficient fine-tuning, and (2) analyzing the difference in ChatGPT’s behavior in single-role prompts compared to multi-role prompts for synthetic data generation tasks. We present a method for aligning open-source LLMs to follow instructions for customized contract drafting scenarios using parameter-efficient fine-tuning on synthetic data. Furthermore, we investigate the data quality of the synthetically generated instructions data by ChatGPT with single-role vs. multi-role prompts. Our findings reveal that the model performs better when given single-role prompts, highlighting the importance of strategically designing prompting strategy to generate better quality data using LLMs. By combining the insights from these two aspects, we explore potential implications and opportunities for enhancing generative AI solutions for practical implementations. The Contract Drafting model 1 and data 2 are released.

Background:Understanding complex biological pathways, including gene-gene interactions and gene regulatory networks, is critical for exploring disease mechanisms and drug development. Manual literature curation of biological pathways is useful but cannot keep up with the exponential growth of the literature. Large-scale language models (LLMs), notable for their vast parameter sizes and comprehensive training on extensive text corpora, have great potential in automated text mining of biological pathways.Method:This study assesses the effectiveness of 21 LLMs, including both API-based models and open-source models. The evaluation focused on two key aspects: gene regulatory relations (specifically, ‘activation’, ‘inhibition’, and ‘phosphorylation’) and KEGG pathway component recognition. The performance of these models was analyzed using statistical metrics such as precision, recall, F1 scores, and the Jaccard similarity index.Results:Our results indicated a significant disparity in model performance. Among the API-based models, ChatGPT-4 and Claude-Pro showed superior performance, with an F1 score of 0.4448 and 0.4386 for the gene regulatory relation prediction, and a Jaccard similarity index of 0.2778 and 0.2657 for the KEGG pathway prediction, respectively. Open-source models lagged their API-based counterparts, where Falcon-180b-chat and llama1–7b led with the highest performance in gene regulatory relations (F1 of 0.2787 and 0.1923, respectively) and KEGG pathway recognition (Jaccard similarity index of 0.2237 and 0. 2207, respectively).Conclusion:LLMs are valuable in biomedical research, especially in gene network analysis and pathway mapping. However, their effectiveness varies, necessitating careful model selection. This work also provided a case study and insight into using LLMs as knowledge graphs.

A wide variety of natural language tasks are currently being addressed with large-scale language models (LLMs).These models are usually trained with a very large amount of unsupervised text data and adapted to perform a downstream natural language task using methods like fine-tuning, calibration or in-context learning.In this work, we propose an approach to adapt the prior class distribution to perform text classification tasks without the need for labelled samples and only a few in-domain sample queries.The proposed approach treats the LLM as a black box, adding a stage where the model posteriors are calibrated to the task.Results show that these methods outperform the un-adapted model for different number of training shots in the prompt and a previous approach where calibration is performed without using any adaptation data.

In this paper, we introduce ACAT-G, an interactive dialogue learning framework that incorporates constant human feedback into fine-tuning language models in order to assist conditioned dialog generation. The system takes in a limited amount of input from a human and generates personalized response corresponding to the context of the conversation within natural dialog time-frame. By combining inspirations from online learning, reinforcement learning, and large scale language models, we expect this project to provide a foundation for human-in-the-loop conditional dialog generation tasks.

Purpose This study aims to explore the integration of large language models (LLMs) and vision-language models (VLMs) in robotics, highlighting their potential benefits and the safety challenges they introduce, including robustness issues, adversarial vulnerabilities, privacy concerns and ethical implications. Design/methodology/approach This survey conducts a comprehensive analysis of the safety risks associated with LLM- and VLM-powered robotic systems. The authors review existing literature, analyze key challenges, evaluate current mitigation strategies and propose future research directions. Findings The study identifies that ensuring the safety of LLM-/VLM-driven robots requires a multi-faceted approach. While current mitigation strategies address certain risks, gaps remain in real-time monitoring, adversarial robustness and ethical safeguards. Originality/value This study offers a structured and comprehensive overview of the safety challenges in LLM-/VLM-driven robotics. It contributes to ongoing discussions by integrating technical, ethical and regulatory perspectives to guide future advancements in safe and responsible artificial intelligence-driven robotics.

Biases in language and their reflection in language models have attracted researchers' attention, particularly with the growth of large language models (LLMs). However, many questions on the links between language models and people’s biased attitudes remain unanswered. In the current study we focus on gender–career bias to examine the extent to which language models can be used to model behavioural responses in the Gender–Career Implicit Association Test (IAT). We provide a systematic evaluation of a range of language models, including n-gram, count vector, predict (word2vec), and Large Language Models (LLMs), to determine how well they capture people’s behaviour in the IAT. We compared response time data from over 800,000 participants against 25 language models, with a total of 675 model variants. We find that many language models, including large language models (LLMs), correlated well with human behavior. While results support previous findings for both predict and count model families, we observed that performance of LLMs was consistently different from that of simpler predict models, particularly in terms of the direction and strength of correlations with reaction time and bias. This divergence may indicate successful attempts to mitigate bias in LLMs while preserving other aspects of linguistic information. Our findings reinforce the idea that societal biases are generally encoded in language, but that large language models can exhibit behaviors different to classical language models.

With large-scale language models demonstrating superior capabilities in a wide range of downstream natural language processing tasks, the future trajectory of research in the field of text categorization faces increasing uncertainty. In this evolving paradigm of open-ended language modeling, where task delimitations are increasingly blurred, a pressing question arises: to what extent has text classification advanced under the full potential of large language model (LLM)? To address this pivotal inquiry, we introduce recurrent generative pre-trained transformer (RGPT), an adaptive boosting framework meticulously designed to craft a dedicated LLM for text classification. RGPT constructs a sequence of base learners by dynamically modulating the training data distribution and iteratively fine-tuning LLMs. These base learners are then progressively integrated, leveraging historical prediction trajectories to form a highly specialized text classification model. Extensive empirical evaluations demonstrate that RGPT surpasses eight state-of-the-art pretrained language models and seven cutting-edge LLMs across four benchmark datasets, achieving an average performance gain of 2.90%.

The subject of the study is the analysis and improvement of methods for determining the relevance of project names to the information content of purchases using large language models. The object of the study is a database containing the names of projects and purchases in the field of electric power industry, collected from open sources. The author examines in detail such aspects of the topic as the use of TF-IDF and cosine similarity metrics for primary data filtering, and also describes in detail the integration and evaluation of the effectiveness of large language models such as GigaChat, GPT-3.5, and GPT-4 in text data matching tasks. Special attention is paid to the methods of clarifying the similarity of names based on reflection introduced into the prompta of large language models, which makes it possible to increase the accuracy of data comparison. The study uses TF-IDF and cosine similarity methods for primary data analysis, as well as large GigaChat, GPT-3.5 and GPT-4 language models for detailed verification of the relevance of project names and purchases, including reflection in model prompta to improve the accuracy of results. The novelty of the research lies in the development of a combined approach to determining the relevance of project names and purchases, combining traditional methods of processing text information (TF-IDF, cosine similarity) with the capabilities of large language models. A special contribution of the author to the research of the topic is the proposed methodology for improving the accuracy of data comparison by clarifying the results of primary selection using GPT-3.5 and GPT-4 models with optimized prompta, including reflection. The main conclusions of the study are confirmation of the prospects of using the developed approach in the tasks of information support for procurement processes and project implementation, as well as the possibility of using the results obtained for the development of text data mining systems in various sectors of the economy. The study showed that the use of language models makes it possible to improve the value of the F2 measure to 0.65, which indicates a significant improvement in the quality of data comparison compared with basic methods.

The paper studies the problem of software code migration during the transition from the old version of the SAP ERP 6.0 system to modern ERP platforms, in particular SAP S/4HANA. The necessity of automation of the migration process using artificial intelligence methods and tools is substantiated. A comprehensive analysis of existing academic and industrial case studies confirmed the feasibility of using large language models for code migration. A number of advantages of the approach based on large language models are revealed, in particular, the ability to handle various migration scenarios. The key risks and limitations common in the enterprise environment are highlighted, including data security, privacy, high cost of API calls and limited knowledge of models regarding the subject area. A method is developed for selecting a large open source language model that can be safely used in the enterprise landscape, thereby mitigating the risks associated with cloud solutions. The method is based on the developed system of criteria, including: model size, context window size, license type, support for fine-tuning training, focus on code quality (measured using a reference dataset), support for model quantization and community support. The hybrid AHP-TOPSIS method is proposed for systematic ranking of candidate models. The AHP method was used to check the weights of the criteria, while TOPSIS was used to rank the models based on their proximity to the ideal solution. Based on the developed method, three large language models were selected: Qwen 2.5 Coder 14B, DeepSeek-Coder-V2 16B and Llama 3.1 8B. A comprehensive testing plan for the selected models was developed for further experimental studies. The scientific novelty of the work lies in the development of a method for selecting large language models for custom code migration tasks, which differs from the existing system of model selection criteria and the use of a hybrid AHP-TOPSIS approach for ranking candidate models. The practical value of the work is that the developed method allows you to select a model taking into account the constraints of the corporate environment and information security requirements, which will increase the level of automation in the migration of AVAP when switching to new versions of ERP systems from SAP SE. The developed method can be applied to the selection of large language models when upgrading any large computer systems developed in both open source and proprietary programming languages.

Large Language Models (LLMs) have enormous potential in healthcare, but we also need to be careful and implement strong safety measures. These advanced computer systems can understand complex medical questions written in everyday language and often provide accurate medical information. This article explores how the field has evolved, from the first language models to the LLMs we have now, specifically designed or adjusted for use in the medical world. We explore how LLMs can make important language-related tasks in healthcare more efficient and effective, such as identifying medical terms, understanding how different pieces of information are connected, drawing conclusions from written text, sorting documents, and answering medical queries. We also shed light on new and exciting ways LLMs can use more than just text, like combining written information with images or other types of data. We compare some of the best recent LLMs and discuss how they can be used in everyday medical situations. We also measure how well these models perform in the biomedical field, explaining what each measurement tells us and where it falls short. Lastly, by discussing the biggest hurdles LLMs face in healthcare—things like generating incorrect information (hallucinations), unfair biases, protecting patient privacy, making sure the models are dependable, and fitting these new tools into how doctors and nurses already work. We also provide a roadmap for future research. We aim to present a clear and fair picture of what LLMs can offer healthcare right now and what's necessary to use them safely and dependably. This includes explaining how researchers are working to make these models easier for doctors and patients to understand. We followed the PRISMA research method to guide our review of the field, from early language models to current LLMs adapted for clinical use.

The application of deep learning to tabular data remains an ongoing challenge, with tree-based models such as XGBoost consistently outperforming neural network methods in most real-world scenarios. Recent advances in Large Language Models (LLMs) highlight their ability to generalize to new tasks via few-shot or one-shot prompting, yet questions remain about their utility in structured, tabular domains—particularly for resource-efficient Small Language Models (SLMs). In this work, we systematically evaluate the effectiveness of both large and small transformer-based language models for tabular classification tasks using few-shot strategies. Our approach investigates input serialization schemes and prompt engineering to maximize performance in low-data regimes. Experiments on benchmark datasets—including Diabetes, Heart Failure, and German Credit Risk—demonstrate that well-designed SLMs can approach, and occasionally match, the performance of much larger models, substantially reducing the need for extensive labeled data and retraining. However, further advances are required for language models to consistently rival the strongest tree-ensemble baselines. Our findings support the idea that SLMs, when properly prompted, offer a promising, flexible, and label-efficient alternative for automating and dynamizing machine learning pipelines on tabular data.

Most traditional AI safety research has approached AI models as machines and centered on algorithm-focused attacks developed by security experts. As large language models (LLMs) become increasingly common and competent, non-expert users can also impose risks during daily interactions. This paper introduces a new perspective on jailbreaking LLMs as human-like communicators to explore this overlooked intersection between everyday language interaction and AI safety. Specifically, we study how to persuade LLMs to jailbreak them. First, we propose a persuasion taxonomy derived from decades of social science research. Then we apply the taxonomy to automatically generate interpretable persuasive adversarial prompts (PAP) to jailbreak LLMs. Results show that persuasion significantly increases the jailbreak performance across all risk categories: PAP consistently achieves an attack success rate of over 92% on Llama 2-7b Chat, GPT-3.5, and GPT-4 in 10 trials, surpassing recent algorithm-focused attacks. On the defense side, we explore various mechanisms against PAP, find a significant gap in existing defenses, and advocate for more fundamental mitigation for highly interactive LLMs 1 .

In this work, we study the impact of Large-scale Language Models (LLM) on Automated Speech Recognition (ASR) of YouTube videos, which we use as a source for long-form ASR. We demonstrate up to 8% relative reduction in Word Error Eate (WER) on US English (en-us) and code-switched Indian English (en-in) long-form ASR test sets and a reduction of up to 30% relative on Salient Term Error Rate (STER) over a strong first-pass baseline that uses a maximum-entropy based language model. Improved lattice processing that results in a lattice with a proper (non-tree) digraph topology and carrying context from the 1-best hypothesis of the previous segment(s) results in significant wins in rescoring with LLMs. We also find that the gains in performance from the combination of LLMs trained on vast quantities of available data (such as C4 [1]) and conventional neural LMs is additive and significantly outperforms a strong first-pass baseline with a maximum entropy LM.

Several recent works seek to develop foundation models specifically for medical applications, adapting general-purpose large language models (LLMs) and vision-language models (VLMs) via continued pretraining on publicly available biomedical corpora.These works typically claim that such domain-adaptive pretraining (DAPT) improves performance on downstream medical tasks, such as answering medical licensing exam questions.In this paper, we compare seven public "medical" LLMs and two VLMs against their corresponding base models, arriving at a different conclusion: all medical VLMs and nearly all medical LLMs fail to consistently improve over their base models in the zero-/few-shot prompting regime for medical question-answering (QA) tasks.For instance, across the tasks and model pairs we consider in the 3-shot setting, medical LLMs only outperform their base models in 12.1% of cases, reach a (statistical) tie in 49.8% of cases, and are significantly worse than their base models in the remaining 38.2% of cases.Our conclusions are based on (i) comparing each medical model head-to-head, directly against the corresponding base model; (ii) optimizing the prompts for each model separately; and (iii) accounting for statistical uncertainty in comparisons.While these basic practices are not consistently adopted in the literature, our ablations show that they substantially impact conclusions.Our findings suggest that state-of-the-art generaldomain models may already exhibit strong medical knowledge and reasoning capabilities, and offer recommendations to strengthen the conclusions of future studies.