Bayesian Optimization with LLM-Based Acquisition Functions for Natural Language Preference Elicitation

Evaluating gpt-4 for zero-shot classification of bleeding and clotting events: Can large language models serve as second reviewers?

Generative large language models (LLMs) are a subset of transformers-based neural network architecture models. LLMs have successfully leveraged a combination of an increased number of parameters, improvements in computational efficiency, and large pre-training datasets to perform a wide spectrum of natural language processing (NLP) tasks. Using a few examples (few-shot) or no examples (zero-shot) for prompt-tuning has enabled LLMs to achieve state-of-the-art performance in a broad range of NLP applications. This article by the American Medical Informatics Association (AMIA) NLP Working Group characterizes the opportunities, challenges, and best practices for our community to leverage and advance the integration of LLMs in downstream NLP applications effectively. This can be accomplished through a variety of approaches, including augmented prompting, instruction prompt tuning, and reinforcement learning from human feedback (RLHF). Our focus is on making LLMs accessible to the broader biomedical informatics community, including clinicians and researchers who may be unfamiliar with NLP. Additionally, NLP practitioners may gain insight from the described best practices. We focus on 3 broad categories of NLP tasks, namely natural language understanding, natural language inferencing, and natural language generation. We review the emerging trends in prompt tuning, instruction fine-tuning, and evaluation metrics used for LLMs while drawing attention to several issues that impact biomedical NLP applications, including falsehoods in generated text (confabulation/hallucinations), toxicity, and dataset contamination leading to overfitting. We also review potential approaches to address some of these current challenges in LLMs, such as chain of thought prompting, and the phenomena of emergent capabilities observed in LLMs that can be leveraged to address complex NLP challenge in biomedical applications.

Large Language Models (LLMs) increasingly generate outputs that resemble introspection, including self-reference, epistemic modulation, and claims about their internal states. This study investigates whether such behaviors reflect consistent, underlying patterns or are merely surface-level generative artifacts.We evaluated five open-weight, stateless LLMs using a structured battery of 21 introspective prompts, each repeated ten times to yield 1,050 completions. These outputs were analyzed across four behavioral dimensions: surface-level similarity (token overlap via SequenceMatcher), semantic coherence (Sentence-BERT embeddings), inferential consistency (Natural Language Inference with a RoBERTa-large model), and diachronic continuity (stability across prompt repetitions). Although some models exhibited thematic stability, particularly on prompts concerning identity and consciousness, no model sustained a consistent self-representation over time. High contradiction rates emerged from a tension between mechanistic disclaimers and anthropomorphic phrasing. Following recent behavioral frameworks, we heuristically adopt the term pseudo-consciousness to describe structured yet non-experiential self-referential output in LLMs. This usage reflects a functionalist stance that avoids ontological commitments, focusing instead on behavioral regularities interpretable through Dennett’s intentional stance. The study contributes a reproducible framework for evaluating simulated introspection in LLMs and offers a graded taxonomy for classifying such reflexive output. Our findings carry significant implications for LLM interpretability, alignment, and user perception, highlighting the need for caution when attributing mental states to stateless generative systems based on linguistic fluency alone.

Interacting with Large Language Models (LLMs) via declarative queries is increasingly popular for tasks like question answering and data extraction, thanks to their ability to process vast unstructured data. However, LLMs often struggle with answering complex factual questions, exhibiting low precision and recall in the returned data. This challenge highlights that executing queries on LLMs remains a largely unexplored domain, where traditional data processing assumptions often fall short. Conventional query optimization, typically cost-driven, overlooks LLM-specific quality challenges such as contextual understanding. Just as new physical operators are designed to address the unique characteristics of LLMs, optimization must consider these quality challenges. Our results highlight that adhering strictly to conventional query optimization principles fails to generate the best plans in terms of result quality. To tackle this challenge, we present a novel approach to enhance SQL results by applying query optimization techniques specifically adapted for LLMs. We introduce a database system, GALOIS, that sits between the query and the LLM, effectively using the latter as a storage layer. We design alternative physical operators tailored for LLM-based query execution and adapt traditional optimization strategies to this novel context. For example, while pushing down operators in the query plan reduces execution cost (fewer calls to the model), it might complicate the call to the LLM and deteriorate result quality. Additionally, these models lack a traditional catalog for optimization, leading us to develop methods to dynamically gather such metadata during query execution. Our solution is compatible with any LLM and balances the trade-off between query result quality and execution cost. Experiments show up to 144% quality improvement over questions in Natural Language and 29% over direct SQL execution, highlighting the advantages of integrating database solutions with LLMs.

Now that we have so much information available, recommender systems are becoming more and more important in many different areas. Traditional methods are very popular because they work well, but they have problems with the cold-start problem and data sparsity. Large language models (LLMs) are a new breakthrough for recommender systems because they can understand and generate text in natural language. This study suggests a better recommendation method that uses both collaborative filtering and LLMs. This method combines the strengths of both methods, using collaborative filtering to model user preferences and LLMs to improve understanding of user and item information. This improves the accuracy and variety of recommendations. In this paper, we start by explaining the basic ideas behind collaborative filtering and LLMs. Then, we design a recommendation system that combines the two and test how well it works. The results show that the hybrid model based on collaborative filtering and LLM significantly improves accuracy, recall and user satisfaction, demonstrating its potential in complex recommendation scenarios.

We propose a memory-efficient finetuning algorithm for large language models (LLMs) that supports finetuning LLMs with 65B parameters in 2/3/4-bit precision on as little as one 24GB GPU. Our method, modular low-rank adaptation (ModuLoRA), integrates any user-specified weight quantizer with finetuning via low-rank adapters (LoRAs). Our approach relies on a simple quantization-agnostic backward pass that adaptively materializes low-precision LLM weights from a custom black-box quantization module. This approach enables finetuning 2-bit and 3-bit LLMs for the first time-leveraging state-of-the-art 2-bit QuIP# quantization and 3-bit OPTQ quantization-outperforming finetuning that relies on less sophisticated 4-bit and 8-bit methods. In our experiments, ModuLoRA attains competitive performance on text classification, natural language inference, and instruction following tasks using significantly less memory than existing approaches, and we also surpass the state-of-the-art ROUGE score on a popular summarization task. We release ModuLoRA together with a series of low-precision models as part of LLMTools, a user-friendly library for quantizing, running, and finetuning LLMs on consumer GPUs.

Large language models (LLMs) are increasingly adopted in educational contexts to provide personalized support to students and teachers. The unprecedented capacity of LLM‐based applications to understand and generate natural language can potentially improve instructional effectiveness and learning outcomes, but the integration of LLMs in education technology has renewed concerns over algorithmic bias, which may exacerbate educational inequalities. Building on prior work that mapped the traditional machine learning life cycle, we provide a framework of the LLM life cycle from the initial development of LLMs to customizing pre‐trained models for various applications in educational settings. We explain each step in the LLM life cycle and identify potential sources of bias that may arise in the context of education. We discuss why current measures of bias from traditional machine learning fail to transfer to LLM‐generated text (eg, tutoring conversations) because text encodings are high‐dimensional, there can be multiple correct responses, and tailoring responses may be pedagogically desirable rather than unfair. The proposed framework clarifies the complex nature of bias in LLM applications and provides practical guidance for their evaluation to promote educational equity. Practitioner notes What is already known about this topic The life cycle of traditional machine learning (ML) applications which focus on predicting labels is well understood. Biases are known to enter in traditional ML applications at various points in the life cycle, and methods to measure and mitigate these biases have been developed and tested. Large language models (LLMs) and other forms of generative artificial intelligence (GenAI) are increasingly adopted in education technologies (EdTech), but current evaluation approaches are not specific to the domain of education. What this paper adds A holistic perspective of the LLM life cycle with domain‐specific examples in education to highlight opportunities and challenges for incorporating natural language understanding (NLU) and natural language generation (NLG) into EdTech. Potential sources of bias are identified in each step of the LLM life cycle and discussed in the context of education. A framework for understanding where to expect potential harms of LLMs for students, teachers, and other users of GenAI technology in education, which can guide approaches to bias measurement and mitigation. Implications for practice and/or policy Education practitioners and policymakers should be aware that biases can originate from a multitude of steps in the LLM life cycle, and the life cycle perspective offers them a heuristic for asking technology developers to explain each step to assess the risk of bias. Measuring the biases of systems that use LLMs in education is more complex than with traditional ML, in large part because the evaluation of natural language generation is highly context‐dependent (eg, what counts as good feedback on an assignment varies). EdTech developers can play an important role in collecting and curating datasets for the evaluation and benchmarking of LLM applications moving forward.

Background and Aims Large language models (LLMs) have gained significant attention in the field of natural language processing (NLP), marking a shift from traditional techniques like Term Frequency-Inverse Document Frequency (TF-IDF). We developed a traditional NLP model to predict arteriovenous fistula (AVF) failure within next 30 days using clinical notes. The goal of this analysis was to investigate whether LLMs would outperform traditional NLP techniques, specifically in the context of predicting AVF failure within the next 30 days using clinical notes. Method We defined AVF failure as the change in status from active to permanently unusable status or temporarily unusable status. We used data from a large kidney care network from January 2021 to December 2021. Two models were created using LLMs and traditional TF-IDF technique. We used “distilbert-base-uncased”, a distilled version of BERT base model [1], and compared its performance with traditional TF-IDF-based NLP techniques. The dataset was randomly divided into 60% training, 20% validation and 20% test dataset. The test data, comprising of unseen patients’ data was used to evaluate the performance of the model. Both models were evaluated using metrics such as area under the receiver operating curve (AUROC), accuracy, sensitivity, and specificity. Results The incidence of 30 days AVF failure rate was 2.3% in the population. Both LLMs and traditional showed similar overall performance as summarized in Table 1. Notably, LLMs showed marginally better performance in certain evaluation metrics. Both models had same AUROC of 0.64 on test data. The accuracy and balanced accuracy for LLMs were 72.9% and 59.7%, respectively, compared to 70.9% and 59.6% for the traditional TF-IDF approach. In terms of specificity, LLMs scored 73.2%, slightly higher than the 71.2% observed for traditional NLP methods. However, LLMs had a lower sensitivity of 46.1% compared to 48% for traditional NLP. However, it is worth noting that training on LLMs took considerably longer than TF-IDF. Moreover, it also used higher computational resources such as utilization of graphics processing units (GPU) instances in cloud-based services, leading to higher cost. Conclusion In our study, we discovered that advanced LLMs perform comparably to traditional TF-IDF modeling techniques in predicting the failure of AVF. Both models demonstrated identical AUROC. While specificity was higher in LLMs compared to traditional NLP, sensitivity was higher in traditional NLP compared to LLMs. LLM was fine-tuned with a limited dataset, which could have influenced its performance to be similar to that of traditional NLP methods. This finding suggests that while LLMs may excel in certain scenarios, such as performing in-depth sentiment analysis of patient data for complex tasks, their effectiveness is highly dependent on the specific use case. It is crucial to weigh the benefits against the resources required for LLMs, as they can be significantly more resource-intensive and costly compared to traditional TF-IDF methods. This highlights the importance of a use-case-driven approach in selecting the appropriate NLP technique for healthcare applications.

Introduction Game theory has long served as a foundational tool in cybersecurity to test, predict, and design strategic interactions between attackers and defenders. The recent advent of Large Language Models (LLMs) offers new tools and challenges for the security of computer systems. In this work, we investigate whether classical game-theoretic frameworks can effectively capture the behaviors of LLM-driven actors and bots. Methods Using a reproducible framework for game-theoretic LLM agents, we investigate two canonical scenarios—the one-shot zero-sum game and the dynamic Prisoner's Dilemma—and we test whether LLMs converge to expected outcomes or exhibit deviations due to embedded biases. We experiments on four state-of-the-art LLMs and five natural languages (English, French, Arabic, Vietnamese, and Mandarin Chinese) to assess linguistic sensitivity. Results For both games, we observe that the final payoffs are influenced by agents characteristics such as personality traits or knowledge of repeated rounds. We also uncover an unexpected sensitivity of the final payoffs to the choice of languages, which should warn against indiscriminate application of LLMs in cybersecurity applications and call for in-depth studies, as LLMs may behave differently when deployed in different countries. We also employ quantitative metrics to evaluate the internal consistency and cross-language stability of LLM agents. Discussion In addition to uncovering unexpected behaviors requiring attention by scholars and practitioners, our work can help guide the selection of the most stable LLMs and optimizing models for secure applications.

Cross-category recommendation systems aim to suggest items to users from various categories, enhancing the user experience by broadening their exposure to diverse products or services. Large Language Models (LLMs) offer a promising avenue for improving the effectiveness of such systems. LLMs, trained on vast datasets, excel at understanding complex relationships between different categories of products by analysing patterns in user interactions, preferences, and item descriptions. By leveraging natural language understanding, these models can identify similarities and connections between disparate product categories, enabling more personalized and relevant cross-category recommendations. This approach goes beyond traditional recommendation algorithms that typically focus on a single category or rely heavily on collaborative filtering techniques. Instead, LLMs can process and integrate information from multiple domains, making it easier to suggest complementary products from different categories that users may not have initially considered. Additionally, LLMs can interpret contextual information, such as user reviews and sentiment analysis, to further refine recommendations based on the user's unique preferences and behavioural patterns. The potential of LLMs in cross-category recommendations opens new possibilities for e-commerce, entertainment, and other industries where personalized experiences are key to user engagement and satisfaction. As these models continue to evolve, they offer the promise of more intelligent and comprehensive recommendation systems that can better meet the needs of users by offering diverse and relevant suggestions across categories. These abstract outlines the key role of LLMs in advancing cross-category recommendation systems, highlighting their capacity to improve personalization and broaden the scope of recommendations.

DialogueLLM: Context and emotion knowledge-tuned large language models for emotion recognition in conversations.

Natural language inference (NLI) is a subfield of natural language processing (NLP) that aims to identify the contextual relationship between premise and hypothesis sentences. While high-resource languages like English benefit from robust and rich NLI datasets, creating similar datasets for low-resource languages is challenging due to the cost and complexity of manual annotation. Although translation of existing datasets offers a practical solution, direct translation of domain-specific datasets presents unique challenges, particularly in handling abbreviations, metric conversions, and cultural alignment. This study introduces a pipeline for translating a medical NLI dataset into Turkish, which is a low-resource language. Our approach employs fine-tuning the Llama-3.1 model with selected samples from the Medical Abbreviation dataset (MeDAL) to extract and resolve medical abbreviations. Consequently, NLI pairs are refined with extracted abbreviations and subjected to metric correction. Later, the processed sentences are then translated using Facebook's No Language Left Behind (NLLB) translation model. To ensure quality, we conducted comprehensive evaluations using both machine learning models and medical expert review. Our results show that BERTurk achieved 75.17% accuracy on TurkMedNLI test data and 76.30% on the normalized test set, while BioBERTurk demonstrated comparable performance with 75.59% accuracy on test data and 72.29% on the normalized dataset. Medical experts further validated the translations through manual assessment of sampled sentences. This work demonstrates the effectiveness of large language models in adapting domain-specific datasets for low-resource languages, establishing a foundation for future research in multilingual biomedical NLP.

The task of textual entailment holds significant importance when dealing with clinical data, as it serves as a foundational component for extracting and synthesizing medical information from vast amounts of unstructured text.To investigate the consistency with which Natural Language Inference (NLI) models capture semantic phenomena critical for intricate inference within clinical NLI contexts, SemEval-2024 has organized a shared task focused on NLI for Clinical Trials (NLI4CT).This task provides participants with a dataset annotated by humans for the purpose of model training and requires the submission of the results on test data for evaluation.We engaged in this shared task2 at SemEval-2024, employing a diverse set of solutions, with a particular emphasis on leveraging a Large Language Model (LLM) based zero-shot inference approach to address the challenge.

In this paper, we introduce an innovative approach to handling the multi-armed bandit (MAB) problem in non-stationary environments, harnessing the predictive power of large language models (LLMs). With the realization that traditional bandit strategies, including epsilon-greedy and upper confidence bound (UCB), may struggle in the face of dynamic changes, we propose a strategy informed by LLMs that offers dynamic guidance on exploration versus exploitation, contingent on the current state of the bandits. We bring forward a new non-stationary bandit model with fluctuating reward distributions and illustrate how LLMs can be employed to guide the choice of bandit amid this variability. Experimental outcomes illustrate the potential of our LLM-informed strategy, demonstrating its adaptability to the fluctuating nature of the bandit problem, while maintaining competitive performance against conventional strategies. This study provides key insights into the capabilities of LLMs in enhancing decision-making processes in dynamic and uncertain scenarios.

Conversational recommender systems (CRSs) aim to capture user preferences and provide personalized recommendations through interactive natural language interaction. The recent advent of large language models (LLMs) has revolutionized human engagement in natural conversation, driven by their extensive world knowledge and remarkable natural language understanding and generation capabilities. However, introducing LLMs into CRSs presents new technical challenges. Directly prompting LLMs for recommendation generation requires understanding a large and evolving item corpus, as well as grounding the generated recommendations in the real item space. On the other hand, generating recommendations based on external recommendation engines or directly integrating their suggestions into responses may constrain the overall performance of LLMs, since these engines generally have inferior representation abilities compared to LLMs. To address these challenges, we propose an end-to-end large-scale CRS model, named as ReFICR, a novel LLM-enhanced conversational recommender that empowers a retrievable large language model to perform conversational recommendation by following retrieval and generation instructions through lightweight tuning. By decomposing the complex CRS task into multiple subtasks, we formulate these subtasks into two types of instruction formats: retrieval and generation. The hidden states of ReFICR are utilized for generating text embeddings for retrieval, and simultaneously ReFICR is fine-tuned to handle generation subtasks. We optimize the contrastive objective to enhance text embeddings for retrieval and jointly fine-tune the large language model objective for generation. Our experimental results on public datasets demonstrate that ReFICR significantly outperforms baselines in terms of recommendation accuracy and response quality. Our code is publicly available at the link: https://github.com/yt556677/ReFICR.