The use of Large language models (LLMs) to augment clinical decision support systems is a topic with rapidly growing interest, but current shortcomings such as hallucinations and lack of clear source citations make them unreliable for use in the clinical environment. This study evaluates Ask Avo, an LLM-derived software by AvoMD that incorporates a proprietary Language Model Augmented Retrieval (LMAR) system, in-built visual citation cues, and prompt engineering designed for interactions with physicians, against ChatGPT-4 in end-user experience for physicians in a simulated clinical scenario environment. Eight clinical questions derived from medical guideline documents in various specialties were prompted to both models by 62 study participants, with each response rated on trustworthiness, actionability, relevancy, comprehensiveness, and friendly format from 1 to 5. Ask Avo significantly outperformed ChatGPT-4 in all criteria: trustworthiness (4.52 vs. 3.34, p<0.001), actionability (4.41 vs. 3.19, p<0.001), relevancy (4.55 vs. 3.49, p<0.001), comprehensiveness (4.50 vs. 3.37, p<0.001), and friendly format (4.52 vs. 3.60, p<0.001). Our findings suggest that specialized LLMs designed with the needs of clinicians in mind can offer substantial improvements in user experience over general-purpose LLMs. Ask Avo's evidence-based approach tailored to clinician needs shows promise in the adoption of LLM-augmented clinical decision support software.

Large language models (LLMs) increasingly reach real-world applications, necessitating a better understanding of their behaviour. Their size and complexity complicate traditional assessment methods, causing the emergence of alternative approaches inspired by the field of psychology. Recent studies administering psychometric questionnaires to LLMs report human-like traits in LLMs, potentially influencing LLM behaviour. However, this approach suffers from a validity problem: it presupposes that these traits exist in LLMs and that they are measurable with tools designed for humans. Typical procedures rarely acknowledge the validity problem in LLMs, comparing and interpreting average LLM scores. This study investigates this problem by comparing latent structures of personality between humans and three LLMs using two validated personality questionnaires. Findings suggest that questionnaires designed for humans do not validly measure similar constructs in LLMs, and that these constructs may not exist in LLMs at all, highlighting the need for psychometric analyses of LLM responses to avoid chasing cognitive phantoms. Keywords: large language models, psychometrics, machine behaviour, latent variable modeling, validity

As mental health care systems worldwide struggle to meet demand, there is increasing focus on using language models to infer neuropsychiatric conditions or psychopathological traits from language production. Yet, so far, this research has only delivered solutions with limited clinical applicability, due to insufficient consideration of ethical questions crucial to ensuring the synergy between possible applications and model design. To accelerate progress towards clinically applicable models, our paper charts the ethical landscape of research on language-based inference of psychopathology and provides a practical tool for researchers to navigate it. We identify seven core ethical principles that should guide model development and deployment in this domain, translate them into ELLIPS, an ethical toolkit operationalizing these principles into questions that can guide researchers' choices with respect to data selection, architectures, evaluation, and model deployment, and provide a case study exemplifying its use. With this, we aim to facilitate the emergence of model technology with concrete potential for real-world applicability.

In the ever-expanding landscape of academic research, the proliferation of ideas presents a significant challenge for researchers: discerning valuable ideas from the less impactful ones. The ability to efficiently evaluate the potential of these ideas is crucial for the advancement of science and paper review. In this work, we focus on idea assessment, which aims to leverage the knowledge of large language models to assess the merit of scientific ideas. First, we investigate existing text evaluation research and define the problem of quantitative evaluation of ideas. Second, we curate and release a benchmark dataset from nearly four thousand manuscript papers with full texts, meticulously designed to train and evaluate the performance of different approaches to this task. Third, we establish a framework for quantifying the value of ideas by employing representations in a specific layer of large language models. Experimental results show that the scores predicted by our method are relatively consistent with those of humans. Our findings suggest that the representations of large language models hold more potential in quantifying the value of ideas than their generative outputs, demonstrating a promising avenue for automating the idea assessment process.

Traditional Semantic Table Interpretation (STI) methods rely primarily on the underlying table data to create semantic annotations. This year's SemTab challenge introduced the ``Metadata to KG'' track, which focuses on performing STI by using only metadata information, without access to the underlying data. In response to this new challenge, we introduce a new term: Column Vocabulary Association (CVA). This term refers to the task of semantic annotation of column headers solely based on metadata information. In this study, we evaluate the performance of various methods in executing the CVA task, including a Large Language Models (LLMs) and Retrieval Augmented Generation (RAG) approach, as well as a more traditional similarity approach with SemanticBERT. Our methodology uses a zero-shot setting, with no pretraining or examples passed to the Large Language Models (LLMs), as we aim to avoid a domain-specific setting. We investigate a total of 7 different LLMs, of which three commercial GPT models (i.e. gpt-3.5-turbo-0.125, gpt-4o and gpt-4-turbo) and four open source models (i.e. llama3-80b, llama3-7b, gemma-7b and mixtral-8x7b). We integrate this models with RAG systems, and we explore how variations in temperature settings affect performances. Moreover, we continue our investigation by performing the CVA task utilizing SemanticBERT, analyzing how various metadata information influence its performance. Initial findings indicate that LLMs generally perform well at temperatures below 1.0, achieving an accuracy of 100\% in certain cases. Nevertheless, our investigation also reveal that the nature of the data significantly influences CVA task outcomes. In fact, in cases where the input data and glossary are related (for example by being created by the same organizations) traditional methods appear to surpass the performance of LLMs.

Clients wishing to implement generative AI in the domain of IT Support and AIOps face two critical issues: domain coverage and model size constraints due to model choice limitations. Clients might choose to not use larger proprietary models such as GPT-4 due to cost and privacy concerns and so are limited to smaller models with potentially less domain coverage that do not generalize to the client's domain. Retrieval augmented generation is a common solution that addresses both of these issues: a retrieval system first retrieves the necessary domain knowledge which a smaller generative model leverages as context for generation. We present a system developed for a client in the IT Support domain for support case solution recommendation that combines retrieval augmented generation (RAG) for answer generation with an encoder-only model for classification and a generative large language model for query generation. We cover architecture details, data collection and annotation, development journey and preliminary validations, expected final deployment process and evaluation plans, and finally lessons learned.

As Asia's richest man, Mukesh Ambani, addressed his shareholders during a much-anticipated yearly address last Thursday, he also unveiled "JioBrain," a suite of artificial intelligence (AI) tools and applications that he says will transform a spate of businesses in energy, textiles, telecommunications and more that form his multinational conglomerate, Reliance Industries. "By perfecting JioBrain within Reliance, we will create a powerful AI service platform that we can offer to other enterprises as well," Ambani said during his speech. The Reliance Chairman's latest offering comes as India emerges as a crucial player in the global AI ecosystem, boasting a high-powered IT industry worth 250 billion, which serves many of the world's banks, manufacturers and firms. As the world's most populous country, India also has a robust workforce population with nearly 5 million programmers at a time when AI talent is in short supply globally, with analysts predicting that India's AI services could be worth 17 billion by 2027, according to a recent report by Nasscom and BCG. Puneet Chandok, the President of Microsoft India & South Asia, points to research that finds India has one of the highest AI adoption rates among knowledge workers, with 92% using generative AI at work--significantly higher than the global average of 75%.

Google's AI-powered Photos upgrades are beginning to trickle in. Ask Photos, the Gemini-powered chatbot that lets you get ultra-specific and conversational with your photo searches, is launching in early access for select users in the US. In addition, the improved search for more descriptive Google Photos queries begins rolling out today for all English-speaking users. The upgraded search in Google Photos lets you use more descriptive queries. For example, while you could have searched for "lake" before, you can now enter "kayaking on a lake surrounded by mountains."

To overcome the burden on the memory size and bandwidth due to ever-increasing size of large language models (LLMs), aggressive weight quantization has been recently studied, while lacking research on quantizing activations. In this paper, we present a hardware-software co-design method that results in an energy-efficient LLM accelerator, named OPAL, for generation tasks. First of all, a novel activation quantization method that leverages the microscaling data format while preserving several outliers per sub-tensor block (e.g., four out of 128 elements) is proposed. Second, on top of preserving outliers, mixed precision is utilized that sets 5-bit for inputs to sensitive layers in the decoder block of an LLM, while keeping inputs to less sensitive layers to 3-bit. Finally, we present the OPAL hardware architecture that consists of FP units for handling outliers and vectorized INT multipliers for dominant non-outlier related operations. In addition, OPAL uses log2-based approximation on softmax operations that only requires shift and subtraction to maximize power efficiency. As a result, we are able to improve the energy efficiency by 1.6~2.2x, and reduce the area by 2.4~3.1x with negligible accuracy loss, i.e., <1 perplexity increase.

Causal language modeling (CLM) serves as the foundational framework underpinning remarkable successes of recent large language models (LLMs). Despite its success, the training approach for next word prediction poses a potential risk of causing the model to overly focus on local dependencies within a sentence. While prior studies have been introduced to predict future N words simultaneously, they were primarily applied to tasks such as masked language modeling (MLM) and neural machine translation (NMT). In this study, we introduce a simple N-gram prediction framework for the CLM task. Moreover, we introduce word difference representation (WDR) as a surrogate and contextualized target representation during model training on the basis of N-gram prediction framework. To further enhance the quality of next word prediction, we propose an ensemble method that incorporates the future N words' prediction results. Empirical evaluations across multiple benchmark datasets encompassing CLM and NMT tasks demonstrate the significant advantages of our proposed methods over the conventional CLM.