Chain-of-Thought (CoT) reasoning has enabled Large Language Model (LLM) to achieve remarkable performance in various NLP tasks, including arithmetic problem-solving. However, this success does not generalize to small language model (sLM) like T5, due to their limited capacity and absence of emergent abilities associated with larger models. Recent works to enhance sLM through knowledge distillation have yielded some improvements but still face significant limitations, particularly high ambiguity from the variability in natural language expressions and substantial computational costs. In this paper, we investigate why sLM perform poorly on arithmetic reasoning tasks and hypothesize that natural language format variability introduces high ambiguity for these smaller models. Based on this hypothesis, we conduct experiments with equation-only format, which is a reasoning format that unifies arithmetic reasoning previously expressed in natural language formats into mathematical equations. Experiment results demonstrate that equation-only format effectively boosts the arithmetic reasoning abilities of sLM, especially in very small models like T5-Tiny.

Large Language Models (LLMs) have demonstrated significant capabilities across numerous application domains. A key challenge is to keep these models updated with latest available information, which limits the true potential of these models for the end-applications. Although, there have been numerous attempts for LLMs Knowledge Editing (KE), i.e., to edit the LLMs prior knowledge and in turn test it via Multi-hop Question Answering (MQA), yet so far these studies are primarily focused on English language. To bridge this gap, in this paper we propose: Multi-hop Questioning Answering under Knowledge Editing for Arabic Language (MQA-KEAL). MQA-KEAL stores knowledge edits as structured knowledge units in the external memory. In order to solve multi-hop question, it first uses task-decomposition to decompose the question into smaller sub-problems. Later for each sub-problem, it iteratively queries the external memory and/or target LLM in order to generate the final response. In addition, we also contribute MQUAKE-AR (Arabic translation of English benchmark MQUAKE), as well as a new benchmark MQA-AEVAL for rigorous performance evaluation of MQA under KE for Arabic language. Experimentation evaluation reveals MQA-KEAL outperforms the baseline models by a significant margin.

Foundation models for natural language processing, powered by the transformer architecture, exhibit remarkable in-context learning (ICL) capabilities, allowing pre-trained models to adapt to downstream tasks using few-shot prompts without updating their weights. Recently, transformer-based foundation models have also emerged as versatile tools for solving scientific problems, particularly in the realm of partial differential equations (PDEs). However, the theoretical foundations of the ICL capabilities in these scientific models remain largely unexplored. This work develops a rigorous error analysis for transformer-based ICL applied to solution operators associated with a family of linear elliptic PDEs. We first demonstrate that a linear transformer, defined by a linear self-attention layer, can provably learn in-context to invert linear systems arising from the spatial discretization of PDEs. This is achieved by deriving theoretical scaling laws for the prediction risk of the proposed linear transformers in terms of spatial discretization size, the number of training tasks, and the lengths of prompts used during training and inference. These scaling laws also enable us to establish quantitative error bounds for learning PDE solutions. Furthermore, we quantify the adaptability of the pre-trained transformer on downstream PDE tasks that experience distribution shifts in both tasks (represented by PDE coefficients) and input covariates (represented by the source term). To analyze task distribution shifts, we introduce a novel concept of task diversity and characterize the transformer's prediction error in terms of the magnitude of task shift, assuming sufficient diversity in the pre-training tasks. We also establish sufficient conditions to ensure task diversity. Finally, we validate the ICL-capabilities of transformers through extensive numerical experiments.

In this paper, we study format biases in reinforcement learning from human feedback (RLHF). We observe that many widely-used preference models, including human evaluators, GPT-4, and top-ranking models on the RewardBench benchmark, exhibit strong biases towards specific format patterns, such as lists, links, bold text, and emojis. Furthermore, large language models (LLMs) can exploit these biases to achieve higher rankings on popular benchmarks like AlpacaEval and LMSYS Chatbot Arena. One notable example of this is verbosity bias, where current preference models favor longer responses that appear more comprehensive, even when their quality is equal to or lower than shorter, competing responses. However, format biases beyond verbosity remain largely underexplored in the literature. In this work, we extend the study of biases in preference learning beyond the commonly recognized length bias, offering a comprehensive analysis of a wider range of format biases. Additionally, we show that with a small amount of biased data (less than 1%), we can inject significant bias into the reward model. Moreover, these format biases can also be easily exploited by downstream alignment algorithms, such as best-of-n sampling and online iterative DPO, as it is usually easier to manipulate the format than to improve the quality of responses. Our findings emphasize the need to disentangle format and content both for designing alignment algorithms and evaluating models.

Recently, an increasing number of news organizations have integrated artificial intelligence (AI) into their workflows, leading to a further influx of AI technologists and data workers into the news industry. This has initiated cross-functional collaborations between these professionals and journalists. While prior research has explored the impact of AI-related roles entering the news industry, there is a lack of studies on how cross-functional collaboration unfolds between AI professionals and journalists. Through interviews with 17 journalists, 6 AI technologists, and 3 AI workers with cross-functional experience from leading news organizations, we investigate the current practices, challenges, and opportunities for cross-functional collaboration around AI in today's news industry. We first study how journalists and AI professionals perceive existing cross-collaboration strategies. We further explore the challenges of cross-functional collaboration and provide recommendations for enhancing future cross-functional collaboration around AI in the news industry.

The role of large language models (LLMs) in education is an increasing area of interest today, considering the new opportunities they offer for teaching, learning, and assessment. This cutting-edge tutorial provides an overview of the educational applications of NLP and the impact that the recent advances in LLMs have had on this field. We will discuss the key challenges and opportunities presented by LLMs, grounding them in the context of four major educational applications: reading, writing, and speaking skills, and intelligent tutoring systems (ITS). This COLING 2025 tutorial is designed for researchers and practitioners interested in the educational applications of NLP and the role LLMs have to play in this area. It is the first of its kind to address this timely topic.

Keyphrase selection plays a pivotal role within the domain of scholarly texts, facilitating efficient information retrieval, summarization, and indexing. In this work, we explored how to apply fine-tuned generative transformer-based models to the specific task of keyphrase selection within Russian scientific texts. We experimented with four distinct generative models, such as ruT5, ruGPT, mT5, and mBART, and evaluated their performance in both in-domain and cross-domain settings. The experiments were conducted on the texts of Russian scientific abstracts from four domains: mathematics & computer science, history, medicine, and linguistics. The use of generative models, namely mBART, led to gains in in-domain performance (up to 4.9% in BERTScore, 9.0% in ROUGE-1, and 12.2% in F1-score) over three keyphrase extraction baselines for the Russian language. Although the results for cross-domain usage were significantly lower, they still demonstrated the capability to surpass baseline performances in several cases, underscoring the promising potential for further exploration and refinement in this research field.

The recent success of large language models (LLMs) and the scaling law has led to a widespread adoption of larger models. Particularly in the healthcare industry, there is an increasing demand for locally operated LLMs due to security concerns. However, the majority of high quality open-source LLMs have a size of 70B parameters, imposing significant financial burdens on users for GPU preparation and operation. To overcome these issues, we present a medical adaptation based on the recent 7B models, which enables the operation in low computational resources. We compare the performance on medical question-answering benchmarks in two languages (Japanese and English), demonstrating that its scores reach parity with or surpass those of currently existing medical LLMs that are ten times larger. We find that fine-tuning an English-centric base model on Japanese medical dataset improves the score in both language, supporting the effect of cross-lingual knowledge transfer. We hope that this study will alleviate financial challenges, serving as a stepping stone for clinical institutions to practically utilize LLMs locally. Our evaluation code is available at https://huggingface.co/stardust-coder/jmedllm-7b-v1.

Tables, figures, and listings (TFLs) are essential tools for summarizing clinical trial data. Creation of TFLs for reporting activities is often a time-consuming task encountered routinely during the execution of clinical trials. This study explored the use of large language models (LLMs) to automate the generation of TFLs through prompt engineering and few-shot transfer learning. Using public clinical trial data in ADaM format, our results demonstrated that LLMs can efficiently generate TFLs with prompt instructions, showcasing their potential in this domain. Furthermore, we developed a conservational agent named "Clinical Trial TFL Generation Agent": An app that matches user queries to predefined prompts that produce customized programs to generate specific pre-defined TFLs. 1 Introduction In the pharmaceutical industry, submission of a clinical study report (CSR) is part of the drug approval process with health authorities.

While there has been a lot of research recently on robots in household environments, at the present time, most robots in existence can be found on shop floors, and most interactions between humans and robots happen there. ``Collaborative robots'' (cobots) designed to work alongside humans on assembly lines traditionally require expert programming, limiting ability to make changes, or manual guidance, limiting expressivity of the resulting programs. To address these limitations, we explore using Large Language Models (LLMs), and in particular, their abilities of doing in-context learning, for conversational code generation. As a first step, we define RATS, the ``Repetitive Assembly Task'', a 2D building task designed to lay the foundation for simulating industry assembly scenarios. In this task, a `programmer' instructs a cobot, using natural language, on how a certain assembly is to be built; that is, the programmer induces a program, through natural language. We create a dataset that pairs target structures with various example instructions (human-authored, template-based, and model-generated) and example code. With this, we systematically evaluate the capabilities of state-of-the-art LLMs for synthesising this kind of code, given in-context examples. Evaluating in a simulated environment, we find that LLMs are capable of generating accurate `first order code' (instruction sequences), but have problems producing `higher-order code' (abstractions such as functions, or use of loops).