Error correction (EC) models play a crucial role in refining Automatic Speech Recognition (ASR) transcriptions, enhancing the readability and quality of transcriptions. Without requiring access to the underlying code or model weights, EC can improve performance and provide domain adaptation for black-box ASR systems. This work investigates the use of large language models (LLMs) for error correction across diverse scenarios. 1-best ASR hypotheses are commonly used as the input to EC models. We propose building high-performance EC models using ASR N-best lists which should provide more contextual information for the correction process. Additionally, the generation process of a standard EC model is unrestricted in the sense that any output sequence can be generated. For some scenarios, such as unseen domains, this flexibility may impact performance. To address this, we introduce a constrained decoding approach based on the N-best list or an ASR lattice. Finally, most EC models are trained for a specific ASR system requiring retraining whenever the underlying ASR system is changed. This paper explores the ability of EC models to operate on the output of different ASR systems. This concept is further extended to zero-shot error correction using LLMs, such as ChatGPT. Experiments on three standard datasets demonstrate the efficacy of our proposed methods for both Transducer and attention-based encoder-decoder ASR systems. In addition, the proposed method can serve as an effective method for model ensembling.

Scientific research indicates that for every hour spent in direct patient care, physicians spend nearly two additional hours on administrative tasks, particularly on electronic health records (EHRs) and desk work. This excessive administrative burden not only reduces the time available for patient care but also contributes to physician burnout and inefficiencies in healthcare delivery. To address these challenges, this study introduces MediGen, a fine-tuned large language model (LLM) designed to automate the generation of medical reports from medical dialogues. By leveraging state-of-the-art methodologies for fine-tuning open-source pretrained models, including LLaMA3-8B, MediGen achieves high accuracy in transcribing and summarizing clinical interactions. The fine-tuned LLaMA3-8B model demonstrated promising results, achieving a ROUGE score of 58% and a BERTScore-F1 of 72%, indicating its effectiveness in generating accurate and clinically relevant medical reports. These findings suggest that MediGen has the potential to significantly reduce the administrative workload on physicians, improving both healthcare efficiency and physician well-being.

We present a novel method for symbolic regression (SR), the task of searching for compact programmatic hypotheses that best explain a dataset. The problem is commonly solved using genetic algorithms; we show that we can enhance such methods by inducing a library of abstract textual concepts. Our algorithm, called LaSR, uses zero-shot queries to a large language model (LLM) to discover and evolve concepts occurring in known high-performing hypotheses. We discover new hypotheses using a mix of standard evolutionary steps and LLM-guided steps (obtained through zero-shot LLM queries) conditioned on discovered concepts. Once discovered, hypotheses are used in a new round of concept abstraction and evolution. We validate LaSR on the Feynman equations, a popular SR benchmark, as well as a set of synthetic tasks. On these benchmarks, LaSR substantially outperforms a variety of state-of-the-art SR approaches based on deep learning and evolutionary algorithms. Moreover, we show that LaSR can be used to discover a novel and powerful scaling law for LLMs.

In recent years, vision-language models have achieved significant advancements, excelling in tasks once deemed challenging, such as optical character recognition and geometric problem-solving. Despite these impressive achievements, several critical issues remain unaddressed: 1) Proprietary models rarely disclose detailed information about their architectures. In contrast, while open-source models provide visibility into their training strategies, detailed ablations of these strategies are highly anticipated. Therefore, refining data schemes is essential for further enhancing model performance. To address these issues, we propose the following contributions in this paper: 1) We trained a robust baseline model, leveraging the latest technological advancements in vision-language models. Building upon existing advancements, we introduced effective improvements and conducted comprehensive ablation and validation for each technique incorporated into this strong baseline. This approach allowed us to train on a curated 1M dataset, resulting in highly competitive performance. Integrating these innovations, we obtained a model with 9B parameters, performing competitively with a series of existing state-of-the-art models. Additionally, these strategies we propose are efficient and relatively lightweight, allowing the community to adopt them easily for their models.

Human beings often experience stress, which can significantly influence their performance. This study explores whether Large Language Models (LLMs) exhibit stress responses similar to those of humans and whether their performance fluctuates under different stress-inducing prompts. To investigate this, we developed a novel set of prompts, termed StressPrompt, designed to induce varying levels of stress. These prompts were derived from established psychological frameworks and carefully calibrated based on ratings from human participants. We then applied these prompts to several LLMs to assess their responses across a range of tasks, including instruction-following, complex reasoning, and emotional intelligence. The findings suggest that LLMs, like humans, perform optimally under moderate stress, consistent with the Yerkes-Dodson law. Notably, their performance declines under both low and high-stress conditions. Our analysis further revealed that these StressPrompts significantly alter the internal states of LLMs, leading to changes in their neural representations that mirror human responses to stress. This research provides critical insights into the operational robustness and flexibility of LLMs, demonstrating the importance of designing AI systems capable of maintaining high performance in real-world scenarios where stress is prevalent, such as in customer service, healthcare, and emergency response contexts. Moreover, this study contributes to the broader AI research community by offering a new perspective on how LLMs handle different scenarios and their similarities to human cognition.

Large Language Models (LLMs) have increasingly demonstrated the ability to facilitate the development of multi-agent systems that allow the interpretation of thoughts and actions generated by each individual. Promising advancements have also been made in LLM-based interaction with existing worlds, particularly in interacting with simulated environments. This paper aims to integrate both aforementioned topics (agents & world interaction) into a single simulation where multiple agents can work together to solve a problem, modeling how groups of humans can often solve problems better than individuals. By showing whether LLMs demonstrate the synergy of human collaboration, it could lead to advancements in the applications of LLMs. We implemented two simulations: a physical studio apartment with two roommates, and another where agents collaborate to complete a programming task. We provide a multi-agent framework, discuss the performance of the agents in each simulation, and discuss potential future additions.

The internet has made it easier than ever before to encounter and spread conspiracy theories. And while some are harmless, others can be deeply damaging, sowing discord and even leading to unnecessary deaths. Now, researchers believe they've uncovered a new tool for combating false conspiracy theories: AI chatbots. Researchers from MIT Sloan and Cornell University found that chatting about a conspiracy theory with a large language model (LLM) reduced people's belief in it by about 20%--even among participants who claimed that their beliefs were important to their identity The findings could represent an important step forward in how we engage with and educate people who espouse baseless theories. Google's new tool lets large language models fact-check their responses The news: Google is releasing a tool called DataGemma that it hopes will help to reduce problems caused by AI'hallucinating', or making incorrect claims.

OpenAI has unveiled yet another artificial intelligence model. This one is called o1, and the company claims it can perform complex reasoning tasks more effectively than its predecessors. Apparently, o1 was trained to "spend more time thinking through problems before they respond." According to the company: "[the models] learn to refine their thinking process, try different strategies and recognize their mistakes." That more considered response means it's significantly slower at processing prompts than GPT-4o.

When a company triples in value in just a few months, as computer chip company Nvidia has, investors take notice. But regulators do too, because they know from experience how monopolies engage in illegal anti-competitive behavior that squashes competitors and manipulates the market to expand their dominance. The US Department of Justice (as well as other competition authorities and tech observers) suspects Nvidia has used such tactics to entrench its chips monopoly, and last month it was reported that the Department of Justice was opening an antitrust investigation. Before the pandemic, few beyond video game enthusiasts – whose top-of-the-line gaming computers and consoles are built on high-capacity Nvidia chips – had ever heard of the company. But thanks to the generative AI boom, Nvidia has become one of the fastest-growing companies ever, and its chips have powered every important AI milestone – including OpenAI's development of ChatGPT, which holds two-thirds of the AI business tools market.

Generative Artificial Intelligence (AI) models may carry societal transformation to an extent demanding a delicate balance between opportunity and risk. This manuscript is the first of a series of White Papers informing the development of IEEE-SA's p3995: `Standard for the Implementation of Safeguards, Controls, and Preventive Techniques for Artificial Intelligence (AI) Models', Chair: Marina Cort\^{e}s (https://standards.ieee.org/ieee/3395/11378/). In this first horizon-scanning we identify key attention areas for standards activities in AI. We examine different principles for regulatory efforts, and review notions of accountability, privacy, data rights and mis-use. As a safeguards standard we devote significant attention to the stability of global infrastructures and consider a possible overdependence on cloud computing that may result from densely coupled AI components. We review the recent cascade-failure-like Crowdstrike event in July 2024, as an illustration of potential impacts on critical infrastructures from AI-induced incidents in the (near) future. It is the first of a set of articles intended as White Papers informing the audience on the standard development. Upcoming articles will focus on regulatory initiatives, technology evolution and the role of AI in specific domains.