arXiv Computer Science @arxiv_cs@qoto.org

Evaluating large language models (LLMs) on their linguistic reasoning capabilities is an important task to understand the gaps in their skills that may surface during large-scale adoption. In this work, we investigate the abilities of such models to perform abstract multilingual reasoning through the lens of linguistic puzzles on extremely low-resource languages. As these translation tasks involve inductive and deductive reasoning from reference instances, we examine whether diverse auxiliary demonstrations can be automatically induced from seed exemplars, through analogical prompting. We employ a two-stage procedure, first generating analogical exemplars with a language model, and then applying them in-context along with provided target language exemplars. Our results on the modeLing dataset show that analogical prompting is effective in eliciting models' knowledge of language grammar similarities, boosting the performance of GPT-4o by as much as 8.1% and Llama-3.1-405B-Instruct by 5.9% over chain-of-thought approaches. These gains are attributable to the analogical demonstrations, both when self-generated as well as when produced by weaker multilingual models. Furthermore, we demonstrate that our method generalizes to other tasks present in Linguistics Olympiad competitions, achieving sizable improvements across all problem types and difficulty levels included in the LINGOLY dataset with GPT-4o. We also report several findings about interesting phenomena which drive linguistic reasoning performance, suggesting that such puzzles are a valuable benchmark for new reasoning methods.

While large language models, such as GPT and BERT, have already demonstrated unprecedented skills in everything from natural language processing to domain-specific applications, there came an unexplored phenomenon we term the Rosetta Paradox. The Rosetta Paradox characterizes the counterintuitive performance inversions across domains of knowledge. This paradox captures how such LLMs can excel in highly specialized fields but do poorly on tasks which require general, everyday knowledge. This paper formalizes the definition of the Rosetta Paradox and introduces a panoramic analysis framework that includes both a Domain Specificity Index (DSI) and a Performance Inversion Metric (PIM) for consistent quantification of domain-specific behavior in LLMs. We adopt this paradox and conduct a series of investigations through extensive experiments across diverse models and knowledge domains, ranging from rich technical areas to common-sense reasoning. Our findings indicate that the Rosetta Paradox is likely not a mere artifact of data distribution but an intrinsic architectural and emergent property of deep neural networks. We present comparative analyses across different model architectures, sizes, and training methodologies that shed light into the peculiar ways this paradox manifests itself and challenge the standard evaluation metrics.

In this paper, we conduct experiment to analyze whether models can classify offensive texts better with the help of sentiment. We conduct this experiment on the SemEval 2019 task 6, OLID, dataset. First, we utilize pre-trained language models to predict the sentiment of each instance. Later we pick the model that achieved the best performance on the OLID test set, and train it on the augmented OLID set to analyze the performance. Results show that utilizing sentiment increases the overall performance of the model.

This paper proposes a look ahead text understanding problem with look ahead section identification (LASI) as an example. This problem may appear in generative AI as well as human interactions, where we want to understand the direction of a developing text or conversation. We tackle the problem using transformer-based LLMs. We show that LASI is more challenging than classic section identification (SI). We argue that both bidirectional contextual information (e.g., BERT) and unidirectional predictive ability (e.g., GPT) will benefit the task. We propose two approaches to stitch together BERT and GPT. Experiments show that our approach outperforms the established models, especially when there is noise in the text (which is often the case for developing text in generative AI). Our paper sheds light on other look ahead text understanding tasks that are important to social media, such as look ahead sentiment classification, and points out the opportunities to leverage pre-trained LLMs through stitching.

Large Language Models (LLMs) show promising learning and reasoning abilities. Compared to other NLP tasks, multilingual and multi-label emotion evaluation tasks are under-explored in LLMs. In this paper, we present EthioEmo, a multi-label emotion classification dataset for four Ethiopian languages, namely, Amharic (amh), Afan Oromo (orm), Somali (som), and Tigrinya (tir). We perform extensive experiments with an additional English multi-label emotion dataset from SemEval 2018 Task 1. Our evaluation includes encoder-only, encoder-decoder, and decoder-only language models. We compare zero and few-shot approaches of LLMs to fine-tuning smaller language models. The results show that accurate multi-label emotion classification is still insufficient even for high-resource languages such as English, and there is a large gap between the performance of high-resource and low-resource languages. The results also show varying performance levels depending on the language and model type. EthioEmo is available publicly to further improve the understanding of emotions in language models and how people convey emotions through various languages.

The Wind Storage Integrated System with Power Smoothing Control (PSC) has emerged as a promising solution to ensure both efficient and reliable wind energy generation. However, existing PSC strategies overlook the intricate interplay and distinct control frequencies between batteries and wind turbines, and lack consideration of wake effect and battery degradation cost. In this paper, a novel coordinated control framework with hierarchical levels is devised to address these challenges effectively, which integrates the wake model and battery degradation model. In addition, after reformulating the problem as a Markov decision process, the multi-agent reinforcement learning method is introduced to overcome the bi-level characteristic of the problem. Moreover, a Physics-informed Neural Network-assisted Multi-agent Deep Deterministic Policy Gradient (PAMA-DDPG) algorithm is proposed to incorporate the power fluctuation differential equation and expedite the learning process. The effectiveness of the proposed methodology is evaluated through simulations conducted in four distinct scenarios using WindFarmSimulator (WFSim). The results demonstrate that the proposed algorithm facilitates approximately an 11% increase in total profit and a 19% decrease in power fluctuation compared to the traditional methods, thereby addressing the dual objectives of economic efficiency and grid-connected energy reliability.

The recent rise of semantic-style communications includes the development of goal-oriented communications (GOCOMs) remarkably efficient multimedia information transmissions. The concept of GO-COMS leverages advanced artificial intelligence (AI) tools to address the rising demand for bandwidth efficiency in applications, such as edge computing and Internet-of-Things (IoT). Unlike traditional communication systems focusing on source data accuracy, GO-COMs provide intelligent message delivery catering to the special needs critical to accomplishing downstream tasks at the receiver. In this work, we present a novel GO-COM framework, namely LaMI-GO that utilizes emerging generative AI for better quality-of-service (QoS) with ultra-high communication efficiency. Specifically, we design our LaMI-GO system backbone based on a latent diffusion model followed by a vector-quantized generative adversarial network (VQGAN) for efficient latent embedding and information representation. The system trains a common feature codebook the receiver side. Our experimental results demonstrate substantial improvement in perceptual quality, accuracy of downstream tasks, and bandwidth consumption over the state-of-the-art GOCOM systems and establish the power of our proposed LaMI-GO communication framework.

Capacitive pressure sensors have several advantages in areas such as robotics, automation, aerospace, biomedical and consumer electronics. We present mathematical modelling, finite element analysis (FEA), fabrication and experimental characterization of ultra-low cost and paper-based, touch-mode, flexible capacitive pressure sensor element using Do-It-Yourself (DIY) technology. The pressure sensing element is utilized to design large-area electronics skin for low-cost prosthetic hands. The presented sensor is characterized in normal, transition, touch and saturation modes. The sensor has higher sensitivity and linearity in touch mode operation from 10 to 40 kPa of applied pressure compared to the normal (0 to 8 kPa), transition (8 to 10 kPa) and saturation mode (after 40 kPa) with response time of 15.85 ms. Advantages of the presented sensor are higher sensitivity, linear response, less diaphragm area, less von Mises stress at the clamped edges region, low temperature drift, robust structure and less separation gap for large pressure measurement compared to normal mode capacitive pressure sensors. The linear range of pressure change is utilized for controlling the position of a servo motor for precise movement in robotic arm using wireless communication, which can be utilized for designing skin-like structure for low-cost prosthetic hands.

Large language models (LLMs) have demonstrated remarkable performance across a wide range of natural language processing (NLP) tasks. However, these models are often difficult to deploy due to significant computational requirements and resource constraints. Knowledge distillation (KD) is an effective technique for transferring the performance of larger LLMs to smaller models. Traditional KD methods primarily focus on the direct output of the teacher model, with little emphasis on the role of prompting during knowledge transfer. In this paper, we propose a set of novel response-priming prompting strategies applied in the knowledge distillation pipeline to enhance the performance of student models. Our approach fine-tunes a smaller Llama 3.1 8B Instruct model by distilling knowledge from a quantized Llama 3.1 405B Instruct teacher model. We apply LoRA optimization and evaluate on the GSM8K benchmark. Experimental results demonstrate that integrating reasoning-eliciting prompting into the proposed KD pipeline significantly improves student model performance, offering an efficient way to deploy powerful models in resource-constrained environments. We find that Ground Truth prompting results in a 55\% performance increase on GSM8K for a distilled Llama 3.1 8B Instruct compared to the same model distilled without prompting. A thorough investigation into the self-attention layers of the student models indicates that the more successful prompted models tend to exhibit certain positive behaviors inside their attention heads which can be tied to their increased accuracy. Our implementation can be found at https://github.com/alonso130r/knowledge-distillation.

Progress in AI is driven largely by the scale and quality of training data. Despite this, there is a deficit of empirical analysis examining the attributes of well-established datasets beyond text. In this work we conduct the largest and first-of-its-kind longitudinal audit across modalities--popular text, speech, and video datasets--from their detailed sourcing trends and use restrictions to their geographical and linguistic representation. Our manual analysis covers nearly 4000 public datasets between 1990-2024, spanning 608 languages, 798 sources, 659 organizations, and 67 countries. We find that multimodal machine learning applications have overwhelmingly turned to web-crawled, synthetic, and social media platforms, such as YouTube, for their training sets, eclipsing all other sources since 2019. Secondly, tracing the chain of dataset derivations we find that while less than 33% of datasets are restrictively licensed, over 80% of the source content in widely-used text, speech, and video datasets, carry non-commercial restrictions. Finally, counter to the rising number of languages and geographies represented in public AI training datasets, our audit demonstrates measures of relative geographical and multilingual representation have failed to significantly improve their coverage since 2013. We believe the breadth of our audit enables us to empirically examine trends in data sourcing, restrictions, and Western-centricity at an ecosystem-level, and that visibility into these questions are essential to progress in responsible AI. As a contribution to ongoing improvements in dataset transparency and responsible use, we release our entire multimodal audit, allowing practitioners to trace data provenance across text, speech, and video.

Superposition or Neuron Polysemanticity are important concepts in the field of interpretability and one might say they are these most intricately beautiful blockers in our path of decoding the Machine Learning black-box. The idea behind this paper is to examine whether it is possible to decode Superposition using Active Learning methods. While it seems that Superposition is an attempt to arrange more features in smaller space to better utilize the limited resources, it might be worth inspecting if Superposition is dependent on any other factors. This paper uses CIFAR-10 and Tiny ImageNet image datasets and the ResNet18 model and compares Baseline and Active Learning models and the presence of Superposition in them is inspected across multiple criteria, including t-SNE visualizations, cosine similarity histograms, Silhouette Scores, and Davies-Bouldin Indexes. Contrary to our expectations, the active learning model did not significantly outperform the baseline in terms of feature separation and overall accuracy. This suggests that non-informative sample selection and potential overfitting to uncertain samples may have hindered the active learning model's ability to generalize better suggesting more sophisticated approaches might be needed to decode superposition and potentially reduce it.

The complexity of laboratory environments requires solutions that simplify instrument interaction and enhance measurement automation. Traditional tools often require configuration, software, and programming skills, creating barriers to productivity. Previous approaches, including dedicated software suites and custom scripts, frequently fall short in providing user-friendly solutions that align with programming practices. We present LABIIUM, an AI-enhanced, zero-configuration measurement automation system designed to streamline experimental workflows and improve user productivity. LABIIUM integrates an AI assistant powered by Large Language Models (LLMs) to generate code. LABIIUM's Lab-Automation-Measurement Bridges (LAMBs) enable seamless instrument connectivity using standard tools such as VSCode and Python, eliminating setup overhead. To demonstrate its capabilities, we conducted experiments involving the measurement of the parametric transfer curve of a simple two-transistor inverting amplifier with a current source load. The AI assistant was evaluated using different prompt scenarios and compared with multiple models, including Claude Sonnet 3.5, Gemini Pro 1.5, and GPT-4o. An expert solution implementing the Gradient-Weighted Adaptive Stochastic Sampling (GWASS) method was used as a baseline. The solutions generated by the AI assistant were compared with the expert solution and a uniform linear sweep baseline with 10,000 points. The graph results show that the LLMs were able to successfully complete the most basic uniform sweep, but LLMs were unable to develop adaptive sweeping algorithms to compete with GWASS. The evaluation underscores LABIIUM's ability to enhance laboratory productivity and support digital transformation in research and industry, and emphasizes the future work required to improve LLM performance in Electronic Measurement Science Tasks.

With consistent growth in Indian Economy, Initial Public Offerings (IPOs) have become a popular avenue for investment. With the modern technology simplifying investments, more investors are interested in making data driven decisions while subscribing for IPOs. In this paper, we describe a machine learning and natural language processing based approach for estimating if an IPO will be successful. We have extensively studied the impact of various facts mentioned in IPO filing prospectus, macroeconomic factors, market conditions, Grey Market Price, etc. on the success of an IPO. We created two new datasets relating to the IPOs of Indian companies. Finally, we investigated how information from multiple modalities (texts, images, numbers, and categorical features) can be used for estimating the direction and underpricing with respect to opening, high and closing prices of stocks on the IPO listing day.

Emergency communication systems face disruptions due to packet loss, bandwidth constraints, poor signal quality, delays, and jitter in VoIP systems, leading to degraded real-time service quality. Victims in distress often struggle to convey critical information due to panic, speech disorders, and background noise, further complicating dispatchers' ability to assess situations accurately. Staffing shortages in emergency centers exacerbate delays in coordination and assistance. This paper proposes leveraging Large Language Models (LLMs) to address these challenges by reconstructing incomplete speech, filling contextual gaps, and prioritizing calls based on severity. The system integrates real-time transcription with Retrieval-Augmented Generation (RAG) to generate contextual responses, using Twilio and AssemblyAI APIs for seamless implementation. Evaluation shows high precision, favorable BLEU and ROUGE scores, and alignment with real-world needs, demonstrating the model's potential to optimize emergency response workflows and prioritize critical cases effectively.

We present a novel approach to generating mathematical conjectures using Large Language Models (LLMs). Focusing on the solubilizer, a relatively recent construct in group theory, we demonstrate how LLMs such as ChatGPT, Gemini, and Claude can be leveraged to generate conjectures. These conjectures are pruned by allowing the LLMs to generate counterexamples. Our results indicate that LLMs are capable of producing original conjectures that, while not groundbreaking, are either plausible or falsifiable via counterexamples, though they exhibit limitations in code execution.

Foundation Models (FMs) trained on Electronic Health Records (EHRs) have achieved state-of-the-art results on numerous clinical prediction tasks. However, most existing EHR FMs have context windows of <1k tokens. This prevents them from modeling full patient EHRs which can exceed 10k's of events. Recent advancements in subquadratic long-context architectures (e.g., Mamba) offer a promising solution. However, their application to EHR data has not been well-studied. We address this gap by presenting the first systematic evaluation of the effect of context length on modeling EHR data. We find that longer context models improve predictive performance -- our Mamba-based model surpasses the prior state-of-the-art on 9/14 tasks on the EHRSHOT prediction benchmark. For clinical applications, however, model performance alone is insufficient -- robustness to the unique properties of EHR is crucial. Thus, we also evaluate models across three previously underexplored properties of EHR data: (1) the prevalence of "copy-forwarded" diagnoses which creates artificial repetition of tokens within EHR sequences; (2) the irregular time intervals between EHR events which can lead to a wide range of timespans within a context window; and (3) the natural increase in disease complexity over time which makes later tokens in the EHR harder to predict than earlier ones. Stratifying our EHRSHOT results, we find that higher levels of each property correlate negatively with model performance, but that longer context models are more robust to more extreme levels of these properties. Our work highlights the potential for using long-context architectures to model EHR data, and offers a case study for identifying new challenges in modeling sequential data motivated by domains outside of natural language. We release our models and code at: https://github.com/som-shahlab/long_context_clues