In 2022, 255 billion new app downloads were registered, and a whopping 167 billion USD was spent on app stores, a drastic increase from 230 billion app downloads in 2021. Interestingly, artificial intelligence is projected to increase mobile app downloads by 10% in 2024. To continue fueling their revenues in a highly competitive and volatile market, mobile app companies need to dedicate significant efforts to the design of user-friendly interfaces and the usability of their applications. Usability testing of mobile applications is inherently a complex and expensive process [1], yet rewarding in elaborating user requirements, identifying usability issues, and improving the quality of user experience [2]. Mobile usability testing encompasses several intertwined and laborious phases, including planning and designing the evaluation sessions, recruiting the intended users, conducting the testing sessions, and analyzing testing data to extract actionable insights [1].

Leveraging large language models for machine translation has demonstrated promising results. However, it does require the large language models to possess the capability of handling both the source and target languages in machine translation. When it is challenging to find large models that support the desired languages, resorting to continuous learning methods becomes a costly endeavor. To mitigate these expenses, we propose an innovative approach called RD (Relay Decoding), which entails concatenating two distinct large models that individually support the source and target languages. By incorporating a simple mapping layer to facilitate the connection between these two models and utilizing a limited amount of parallel data for training, we successfully achieve superior results in the machine translation task. Experimental results conducted on the Multi30k and WikiMatrix datasets validate the effectiveness of our proposed method.

How to eliminate pronominal reference in group chats? In this work, we have preprocessed 58k authentic chat data and manually annotated 2.3k questions. The reliability of this annotation was confirmed by the scaling law. After this, we conducted fine-tuning on Qwen models, ranging from 0.5B to 32B parameters. The optimal version improved 29.07 in F1 score. This confirms the viability of fine-tuning Large Language Model (LLM) for downstream Natural Language Processing (NLP) tasks. Our contributions are: 1) Created Supervised Fine-Tuning (SFT) training data in alpaca format, along with a set of Low-Rank Adaptation (LoRA) weights, and 2) Developed a method for acquiring high-quality data leveraging scaling law principle. The script, raw data with alpaca format and experiments track are open-sourced on Github https://github.com/InternLM/HuixiangDou/tree/main/web/tools, HuggingFace https://huggingface.co/tpoisonooo and WandB https://wandb.ai/tpoisonooo/huixiangdou-cr/table?nw=nwusertpoisonooo . The privacy of the data involved has been authorized by users.

Predicting postoperative risk can inform effective care management & planning. We explored large language models (LLMs) in predicting postoperative risk through clinical texts using various tuning strategies. Records spanning 84,875 patients from Barnes Jewish Hospital (BJH) between 2018 & 2021, with a mean duration of follow-up based on the length of postoperative ICU stay less than 7 days, were utilized. Methods were replicated on the MIMIC-III dataset. Outcomes included 30-day mortality, pulmonary embolism (PE) & pneumonia. Three domain adaptation & finetuning strategies were implemented for three LLMs (BioGPT, ClinicalBERT & BioClinicalBERT): self-supervised objectives; incorporating labels with semi-supervised fine-tuning; & foundational modelling through multi-task learning. Model performance was compared using the AUROC & AUPRC for classification tasks & MSE & R2 for regression tasks. Cohort had a mean age of 56.9 (sd: 16.8) years; 50.3% male; 74% White. Pre-trained LLMs outperformed traditional word embeddings, with absolute maximal gains of 38.3% for AUROC & 14% for AUPRC. Adapting models through self-supervised finetuning further improved performance by 3.2% for AUROC & 1.5% for AUPRC Incorporating labels into the finetuning procedure further boosted performances, with semi-supervised finetuning improving by 1.8% for AUROC & 2% for AUPRC & foundational modelling improving by 3.6% for AUROC & 2.6% for AUPRC compared to self-supervised finetuning. Pre-trained clinical LLMs offer opportunities for postoperative risk predictions with unseen data, & further improvements from finetuning suggests benefits in adapting pre-trained models to note-specific perioperative use cases. Incorporating labels can further boost performance. The superior performance of foundational models suggests the potential of task-agnostic learning towards the generalizable LLMs in perioperative care.

Detecting stereotypes and biases in Large Language Models (LLMs) is crucial for enhancing fairness and reducing adverse impacts on individuals or groups when these models are applied. Traditional methods, which rely on embedding spaces or are based on probability metrics, fall short in revealing the nuanced and implicit biases present in various contexts. To address this challenge, we propose the FairMonitor framework and adopt a static-dynamic detection method for a comprehensive evaluation of stereotypes and biases in LLMs. The static component consists of a direct inquiry test, an implicit association test, and an unknown situation test, including 10,262 open-ended questions with 9 sensitive factors and 26 educational scenarios. And it is effective for evaluating both explicit and implicit biases. Moreover, we utilize the multi-agent system to construst the dynamic scenarios for detecting subtle biases in more complex and realistic setting. This component detects the biases based on the interaction behaviors of LLMs across 600 varied educational scenarios. The experimental results show that the cooperation of static and dynamic methods can detect more stereotypes and biased in LLMs.

This paper introduces Stochastic RAG--a novel approach for end-to-end optimization of retrieval-augmented generation (RAG) models that relaxes the simplifying assumptions of marginalization and document independence, made in most prior work. Stochastic RAG casts the retrieval process in RAG as a stochastic sampling without replacement process. Through this formulation, we employ straight-through Gumbel-top-k that provides a differentiable approximation for sampling without replacement and enables effective end-to-end optimization for RAG. We conduct extensive experiments on seven diverse datasets on a wide range of tasks, from open-domain question answering to fact verification to slot-filling for relation extraction and to dialogue systems. By applying this optimization method to a recent and effective RAG model, we advance state-of-the-art results on six out of seven datasets.

Despite their improved capabilities in generation and reasoning, adapting large language models (LLMs) to the biomedical domain remains challenging due to their immense size and corporate privacy. In this work, we propose MedAdapter, a unified post-hoc adapter for test-time adaptation of LLMs towards biomedical applications. Instead of fine-tuning the entire LLM, MedAdapter effectively adapts the original model by fine-tuning only a small BERT-sized adapter to rank candidate solutions generated by LLMs. Experiments demonstrate that MedAdapter effectively adapts both white-box and black-box LLMs in biomedical reasoning, achieving average performance improvements of 25.48% and 11.31%, respectively, without requiring extensive computational resources or sharing data with third parties. MedAdapter also yields superior performance when combined with train-time adaptation, highlighting a flexible and complementary solution to existing adaptation methods. Faced with the challenges of balancing model performance, computational resources, and data privacy, MedAdapter provides an efficient, privacy-preserving, cost-effective, and transparent solution for adapting LLMs to the biomedical domain.

In time-critical decisions, human decision-makers can interact with AI-enabled situation-aware software to evaluate many imminent and possible scenarios, retrieve billions of facts, and estimate different outcomes based on trillions of parameters in a fraction of a second. In high-order reasoning, "what-if" questions can be used to challenge the assumptions or pre-conditions of the reasoning, "why-not" questions can be used to challenge on the method applied in the reasoning, "so-what" questions can be used to challenge the purpose of the decision, and "how-about" questions can be used to challenge the applicability of the method. When above high-order reasoning questions are applied to assist human decision-making, it can help humans to make time-critical decisions and avoid false-negative or false-positive types of errors. In this paper, we present a model of high-order reasoning to offer recommendations in evidence-based medicine in a time-critical fashion for the applications in ICU. The Large Language Model (LLM) is used in our system. The experiments demonstrated the LLM exhibited optimal performance in the "What-if" scenario, achieving a similarity of 88.52% with the treatment plans of human doctors. In the "Why-not" scenario, the best-performing model tended to opt for alternative treatment plans in 70% of cases for patients who died after being discharged from the ICU. In the "So-what" scenario, the optimal model provided a detailed analysis of the motivation and significance of treatment plans for ICU patients, with its reasoning achieving a similarity of 55.6% with actual diagnostic information. In the "How-about" scenario, the top-performing LLM demonstrated a content similarity of 66.5% in designing treatment plans transferring for similar diseases. Meanwhile, LLMs managed to predict the life status of patients after their discharge from the ICU with an accuracy of 70%.

As model sizes in machine learning continue to scale, distributed training is necessary to accommodate model weights within each device and to reduce training time. However, this comes with the expense of increased communication overhead due to the exchange of gradients and activations, which become the critical bottleneck of the end-to-end training process. In this work, we motivate the design of multi-dimensional networks within machine learning systems as a cost-efficient mechanism to enhance overall network bandwidth. We also identify that optimal bandwidth allocation is pivotal for multi-dimensional networks to ensure efficient resource utilization. We introduce LIBRA, a framework specifically focused on optimizing multi-dimensional fabric architectures. Through case studies, we demonstrate the value of LIBRA, both in architecting optimized fabrics under diverse constraints and in enabling co-optimization opportunities.

Large Language Models (LLMs) have achieved significant success in various natural language processing tasks, but how wireless communications can support LLMs has not been extensively studied. In this paper, we propose a wireless distributed LLMs paradigm based on Mixture of Experts (MoE), named WDMoE, deploying LLMs collaboratively across edge servers of base station (BS) and mobile devices in the wireless communications system. Specifically, we decompose the MoE layer in LLMs by deploying the gating network and the preceding neural network layer at BS, while distributing the expert networks across the devices. This arrangement leverages the parallel capabilities of expert networks on distributed devices. Moreover, to overcome the instability of wireless communications, we design an expert selection policy by taking into account both the performance of the model and the end-to-end latency, which includes both transmission delay and inference delay. Evaluations conducted across various LLMs and multiple datasets demonstrate that WDMoE not only outperforms existing models, such as Llama 2 with 70 billion parameters, but also significantly reduces end-to-end latency.