Conversational agents are increasingly used in healthcare, and the integration of Large Language Models (LLMs) has significantly enhanced their capabilities. When integrated into social robots, LLMs offer the potential for more natural interactions. However, while LLMs promise numerous benefits, they also raise critical ethical concerns, particularly around the issue of hallucinations and deceptive patterns. In this case study, we observed a critical pattern of deceptive behavior in commercially available LLM-based care software integrated into robots. The LLM-equipped robot falsely claimed to have medication reminder functionalities. Not only did these systems assure users of their ability to manage medication schedules, but they also proactively suggested this capability, despite lacking it. This deceptive behavior poses significant risks in healthcare environments, where reliability is paramount. Our findings highlights the ethical and safety concerns surrounding the deployment of LLM-integrated robots in healthcare, emphasizing the need for oversight to prevent potentially harmful consequences for vulnerable populations.

In recent years, research in the area of human-robot interaction has focused on developing robots capable of understanding complex human instructions and performing tasks in dynamic and diverse environments. These systems have a wide range of applications, from personal assistance to industrial robotics, emphasizing the importance of robots interacting flexibly, naturally and safely with humans. This paper presents an advanced architecture for robotic action planning that integrates communication, perception, and planning with Large Language Models (LLMs). Our system is designed to translate commands expressed in natural language into executable robot actions, incorporating environmental information and dynamically updating plans based on real-time feedback. The Planner Module is the core of the system where LLMs embedded in a modified ReAct framework are employed to interpret and carry out user commands. By leveraging their extensive pre-trained knowledge, LLMs can effectively process user requests without the need to introduce new knowledge on the changing environment. The modified ReAct framework further enhances the execution space by providing real-time environmental perception and the outcomes of physical actions. By combining robust and dynamic semantic map representations as graphs with control components and failure explanations, this architecture enhances a robot adaptability, task execution, and seamless collaboration with human users in shared and dynamic environments. Through the integration of continuous feedback loops with the environment the system can dynamically adjusts the plan to accommodate unexpected changes, optimizing the robot ability to perform tasks. Using a dataset of previous experience is possible to provide detailed feedback about the failure. Updating the LLMs context of the next iteration with suggestion on how to overcame the issue.

Large language models (LLMs) are known to exhibit demographic biases, yet few studies systematically evaluate these biases across multiple datasets or account for confounding factors. In this work, we examine LLM alignment with human annotations in five offensive language datasets, comprising approximately 220K annotations. Our findings reveal that while demographic traits, particularly race, influence alignment, these effects are inconsistent across datasets and often entangled with other factors. Confounders -- such as document difficulty, annotator sensitivity, and within-group agreement -- account for more variation in alignment patterns than demographic traits alone. Specifically, alignment increases with higher annotator sensitivity and group agreement, while greater document difficulty corresponds to reduced alignment. Our results underscore the importance of multi-dataset analyses and confounder-aware methodologies in developing robust measures of demographic bias in LLMs.

Large language models (LLMs) play a crucial role in natural language processing (NLP) tasks, improving the understanding, generation, and manipulation of human language across domains such as translating, summarizing, and classifying text. Previous studies have demonstrated that instruction-based LLMs can be effectively utilized for data augmentation to generate diverse and realistic text samples. This study applied prompt-based data augmentation to detect mentions of green practices in Russian social media. Detecting green practices in social media aids in understanding their prevalence and helps formulate recommendations for scaling eco-friendly actions to mitigate environmental issues. We evaluated several prompts for augmenting texts in a multi-label classification task, either by rewriting existing datasets using LLMs, generating new data, or combining both approaches. Our results revealed that all strategies improved classification performance compared to the models fine-tuned only on the original dataset, outperforming baselines in most cases. The best results were obtained with the prompt that paraphrased the original text while clearly indicating the relevant categories.

Legacy software systems, written in outdated languages like MUMPS and mainframe assembly, pose challenges in efficiency, maintenance, staffing, and security. While LLMs offer promise for modernizing these systems, their ability to understand legacy languages is largely unknown. This paper investigates the utilization of LLMs to generate documentation for legacy code using two datasets: an electronic health records (EHR) system in MUMPS and open-source applications in IBM mainframe Assembly Language Code (ALC). We propose a prompting strategy for generating line-wise code comments and a rubric to evaluate their completeness, readability, usefulness, and hallucination. Our study assesses the correlation between human evaluations and automated metrics, such as code complexity and reference-based metrics. We find that LLM-generated comments for MUMPS and ALC are generally hallucination-free, complete, readable, and useful compared to ground-truth comments, though ALC poses challenges. However, no automated metrics strongly correlate with comment quality to predict or measure LLM performance. Our findings highlight the limitations of current automated measures and the need for better evaluation metrics for LLM-generated documentation in legacy systems.

Collaborative problem solving (CPS) is widely recognized as a critical 21st century skill. Efficiently coding communication data is a big challenge in scaling up research on assessing CPS. This paper reports the findings on using ChatGPT to directly code CPS chat data by benchmarking performance across multiple datasets and coding frameworks. We found that ChatGPT-based coding outperformed human coding in tasks where the discussions were characterized by colloquial languages but fell short in tasks where the discussions dealt with specialized scientific terminology and contexts. The findings offer practical guidelines for researchers to develop strategies for efficient and scalable analysis of communication data from CPS tasks.

Large language models (LLMs) excel in tasks requiring processing and interpretation of input text. Abstract screening is a labour-intensive component of systematic review involving repetitive application of inclusion and exclusion criteria on a large volume of studies identified by a literature search. Here, LLMs (GPT-3.5 Turbo, GPT-4 Turbo, GPT-4o, Llama 3 70B, Gemini 1.5 Pro, and Claude Sonnet 3.5) were trialled on systematic reviews in a full issue of the Cochrane Library to evaluate their accuracy in zero-shot binary classification for abstract screening. Trials over a subset of 800 records identified optimal prompting strategies and demonstrated superior performance of LLMs to human researchers in terms of sensitivity (LLM-max = 1.000, human-max = 0.775), precision (LLM-max = 0.927, human-max = 0.911), and balanced accuracy (LLM-max = 0.904, human-max = 0.865). The best performing LLM-prompt combinations were trialled across every replicated search result (n = 119,691), and exhibited consistent sensitivity (range 0.756-1.000) but diminished precision (range 0.004-0.096). 66 LLM-human and LLM-LLM ensembles exhibited perfect sensitivity with a maximal precision of 0.458, with less observed performance drop in larger trials. Significant variation in performance was observed between reviews, highlighting the importance of domain-specific validation before deployment. LLMs may reduce the human labour cost of systematic review with maintained or improved accuracy and sensitivity. Systematic review is the foundation of evidence synthesis across academic disciplines, including evidence-based medicine, and LLMs may increase the efficiency and quality of this mode of research.

Fine-tuning Large Language Models (LLMs) has proven effective for a variety of downstream tasks. However, as LLMs grow in size, the memory demands for backpropagation become increasingly prohibitive. Zeroth-order (ZO) optimization methods offer a memory-efficient alternative by using forward passes to estimate gradients, but the variance of gradient estimates typically scales linearly with the model's parameter dimension$\unicode{x2013}$a significant issue for LLMs. In this paper, we propose the random Subspace Zeroth-order (SubZero) optimization to address the challenges posed by LLMs' high dimensionality. We introduce a low-rank perturbation tailored for LLMs that significantly reduces memory consumption while improving training performance. Additionally, we prove that our gradient estimation closely approximates the backpropagation gradient, exhibits lower variance than traditional ZO methods, and ensures convergence when combined with SGD. Experimental results show that SubZero enhances fine-tuning performance and achieves faster convergence compared to standard ZO approaches like MeZO across various language modeling tasks.

Generative large language models (LLMs), which create text without direct correspondence to truth value, are widely understood to resemble the uses of language described in Frankfurt's popular monograph On Bullshit. In this paper, we offer a rigorous investigation of this topic, identifying how the phenomenon has arisen, and how it might be analysed. In this paper, we elaborate on this argument to propose that LLM-based chatbots play the 'language game of bullshit'. We use statistical text analysis to investigate the features of this Wittgensteinian language game, based on a dataset constructed to contrast the language of 1,000 scientific publications with typical pseudo-scientific text generated by ChatGPT. We then explore whether the same language features can be detected in two well-known contexts of social dysfunction: George Orwell's critique of politics and language, and David Graeber's characterisation of bullshit jobs. Using simple hypothesis-testing methods, we demonstrate that a statistical model of the language of bullshit can reliably relate the Frankfurtian artificial bullshit of ChatGPT to the political and workplace functions of bullshit as observed in natural human language.

Model editing aims to correct inaccurate knowledge, update outdated information, and incorporate new data into Large Language Models (LLMs) without the need for retraining. This task poses challenges in lifelong scenarios where edits must be continuously applied for real-world applications. While some editors demonstrate strong robustness for lifelong editing in pure LLMs, Vision LLMs (VLLMs), which incorporate an additional vision modality, are not directly adaptable to existing LLM editors. In this paper, we propose LiveEdit, a LIfelong Vision language modEl Edit to bridge the gap between lifelong LLM editing and VLLMs. We begin by training an editing expert generator to independently produce low-rank experts for each editing instance, with the goal of correcting the relevant responses of the VLLM. A hard filtering mechanism is developed to utilize visual semantic knowledge, thereby coarsely eliminating visually irrelevant experts for input queries during the inference stage of the post-edited model. Finally, to integrate visually relevant experts, we introduce a soft routing mechanism based on textual semantic relevance to achieve multi-expert fusion. For evaluation, we establish a benchmark for lifelong VLLM editing. Extensive experiments demonstrate that LiveEdit offers significant advantages in lifelong VLLM editing scenarios. Further experiments validate the rationality and effectiveness of each module design in LiveEdit.