Knowing that the generative capabilities of large language models (LLM) are sometimes hampered by tendencies to hallucinate or create non-factual responses, researchers have increasingly focused on methods to ground generated outputs in factual data. Retrieval Augmented Generation (RAG) has emerged as a key approach for integrating knowledge from data sources outside of the LLM's training set, including proprietary and up-to-date information. While many research papers explore various RAG strategies, their true efficacy is tested in real-world applications with actual data. The journey from conceiving an idea to actualizing it in the real world is a lengthy process. We present insights from the development and field-testing of a pilot project that integrates LLMs with RAG for information retrieval. Additionally, we examine the impacts on the information value chain, encompassing people, processes, and technology. Our aim is to identify the opportunities and challenges of implementing this emerging technology, particularly within the context of behavioral research in the information systems (IS) field. The contributions of this work include the development of best practices and recommendations for adopting this promising technology while ensuring compliance with industry regulations through a proposed AI governance model.

Large Language Models (LLMs) have excelled in multi-hop question-answering (M-QA) due to their advanced reasoning abilities. However, the impact of the inherent reasoning structures on LLM M-QA performance remains unclear, largely due to the absence of QA datasets that provide fine-grained reasoning structures. To address this gap, we introduce the Graph Reasoning-Structured Question Answering Dataset (GRS-QA), which includes both semantic contexts and reasoning structures for QA pairs. Unlike existing M-QA datasets, where different reasoning structures are entangled together, GRS-QA explicitly captures intricate reasoning pathways by constructing reasoning graphs, where nodes represent textual contexts and edges denote logical flows. These reasoning graphs of different structures enable a fine-grained evaluation of LLM reasoning capabilities across various reasoning structures. Our empirical analysis reveals that LLMs perform differently when handling questions with varying reasoning structures. This finding facilitates the exploration of textual structures as compared with semantics.

This paper presents a novel approach to building mission planners based on neural networks with Transformer architecture and Large Language Models (LLMs). This approach demonstrates the possibility of setting a task for a mobile robot and its successful execution without the use of perception algorithms, based only on the data coming from the camera. In this work, a success rate of more than 50\% was obtained for one of the basic actions for mobile robots. The proposed approach is of practical importance in the field of warehouse logistics robots, as in the future it may allow to eliminate the use of markings, LiDARs, beacons and other tools for robot orientation in space. In conclusion, this approach can be scaled for any type of robot and for any number of robots.

Self-alignment, whereby models learn to improve themselves without human annotation, is a rapidly growing research area. However, existing techniques often fail to improve complex reasoning tasks due to the difficulty of assigning correct rewards. An orthogonal approach that is known to improve correctness is self-consistency, a method applied at inference time based on multiple sampling in order to find the most consistent answer. In this work, we extend the self-consistency concept to help train models. We thus introduce self-consistency preference optimization (ScPO), which iteratively trains consistent answers to be preferred over inconsistent ones on unsupervised new problems. We show ScPO leads to large improvements over conventional reward model training on reasoning tasks such as GSM8K and MATH, closing the gap with supervised training with gold answers or preferences, and that combining ScPO with standard supervised learning improves results even further. On ZebraLogic, ScPO finetunes Llama-3 8B to be superior to Llama-3 70B, Gemma-2 27B, and Claude-3 Haiku.

Large language models (LLMs) are becoming a popular tool as they have significantly advanced in their capability to tackle a wide range of language-based tasks. However, LLMs applications are highly vulnerable to prompt injection attacks, which poses a critical problem. These attacks target LLMs applications through using carefully designed input prompts to divert the model from adhering to original instruction, thereby it could execute unintended actions. These manipulations pose serious security threats which potentially results in data leaks, biased outputs, or harmful responses. This project explores the security vulnerabilities in relation to prompt injection attacks. To detect whether a prompt is vulnerable or not, we follows two approaches: 1) a pre-trained LLM, and 2) a fine-tuned LLM. Then, we conduct a thorough analysis and comparison of the classification performance. Firstly, we use pre-trained XLM-RoBERTa model to detect prompt injections using test dataset without any fine-tuning and evaluate it by zero-shot classification. Then, this proposed work will apply supervised fine-tuning to this pre-trained LLM using a task-specific labeled dataset from deepset in huggingface, and this fine-tuned model achieves impressive results with 99.13\% accuracy, 100\% precision, 98.33\% recall and 99.15\% F1-score thorough rigorous experimentation and evaluation. We observe that our approach is highly efficient in detecting prompt injection attacks.

The classification of genetic variants, particularly Variants of Uncertain Significance (VUS), poses a significant challenge in clinical genetics and precision medicine. Large Language Models (LLMs) have emerged as transformative tools in this realm. These models can uncover intricate patterns and predictive insights that traditional methods might miss, thus enhancing the predictive accuracy of genetic variant pathogenicity. This study investigates the integration of state-of-the-art LLMs, including GPN-MSA, ESM1b, and AlphaMissense, which leverage DNA and protein sequence data alongside structural insights to form a comprehensive analytical framework for variant classification. Our approach evaluates these integrated models using the well-annotated ProteinGym and ClinVar datasets, setting new benchmarks in classification performance. The models were rigorously tested on a set of challenging variants, demonstrating substantial improvements over existing state-of-the-art tools, especially in handling ambiguous and clinically uncertain variants. The results of this research underline the efficacy of combining multiple modeling approaches to significantly refine the accuracy and reliability of genetic variant classification systems. These findings support the deployment of these advanced computational models in clinical environments, where they can significantly enhance the diagnostic processes for genetic disorders, ultimately pushing the boundaries of personalized medicine by offering more detailed and actionable genetic insights.

This study aimed to develop a system that provides vibrotactile feedback corresponding to the emotional content of text when a communication robot speaks. We used OpenAI's "GPT-4o Mini" for emotion estimation, extracting valence and arousal values from the text. The amplitude and frequency of vibrotactile stimulation using sine waves were controlled on the basis of estimated emotional values. We assembled a palm-sized tactile display to present these vibrotactile stimuli. In the experiment, participants listened to the robot's speech while holding the device and then evaluated their psychological state. The results suggested that the communication accompanied by the vibrotactile feedback could influence psychological states and intimacy levels.

Toxicity classification in textual content remains a significant problem. Data with labels from a single annotator fall short of capturing the diversity of human perspectives. Therefore, there is a growing need to incorporate crowdsourced annotations for training an effective toxicity classifier. Additionally, the standard approach to training a classifier using empirical risk minimization (ERM) may fail to address the potential shifts between the training set and testing set due to exploiting spurious correlations. This work introduces a novel bi-level optimization framework that integrates crowdsourced annotations with the soft-labeling technique and optimizes the soft-label weights by Group Distributionally Robust Optimization (GroupDRO) to enhance the robustness against out-of-distribution (OOD) risk. We theoretically prove the convergence of our bi-level optimization algorithm. Experimental results demonstrate that our approach outperforms existing baseline methods in terms of both average and worst-group accuracy, confirming its effectiveness in leveraging crowdsourced annotations to achieve more effective and robust toxicity classification.

Translation of code-mixed texts to formal English allow a wider audience to understand these code-mixed languages, and facilitate downstream analysis applications such as sentiment analysis. In this work, we look at translating Singlish, which is colloquial Singaporean English, to formal standard English. Singlish is formed through the code-mixing of multiple Asian languages and dialects. We analysed the presence of other Asian languages and variants which can facilitate translation. Our dataset is short message texts, written as informal communication between Singlish speakers. We use a multi-step prompting scheme on five Large Language Models (LLMs) for language detection and translation. Our analysis show that LLMs do not perform well in this task, and we describe the challenges involved in translation of code-mixed languages. We also release our dataset in this link https://github.com/luoqichan/singlish.

It is now a common business practice to buy access to large language model (LLM) inference rather than self-host, because of significant upfront hardware infrastructure and energy costs. However, as a buyer, there is no mechanism to verify the authenticity of the advertised service including the serving hardware platform, e.g. that it is actually being served using an NVIDIA H100. Furthermore, there are reports suggesting that model providers may deliver models that differ slightly from the advertised ones, often to make them run on less expensive hardware. That way, a client pays premium for a capable model access on more expensive hardware, yet ends up being served by a (potentially less capable) cheaper model on cheaper hardware. In this paper we introduce \textit{\textbf{hardware and software platform inference (HSPI)}} -- a method for identifying the underlying \GPU{} architecture and software stack of a (black-box) machine learning model solely based on its input-output behavior. Our method leverages the inherent differences of various \GPU{} architectures and compilers to distinguish between different \GPU{} types and software stacks. By analyzing the numerical patterns in the model's outputs, we propose a classification framework capable of accurately identifying the \GPU{} used for model inference as well as the underlying software configuration. Our findings demonstrate the feasibility of inferring \GPU{} type from black-box models. We evaluate HSPI against models served on different real hardware and find that in a white-box setting we can distinguish between different \GPU{}s with between $83.9\%$ and $100\%$ accuracy. Even in a black-box setting we are able to achieve results that are up to three times higher than random guess accuracy.