Many less-resourced languages struggle with a lack of large, task-specific datasets that are required for solving relevant tasks with modern transformer-based large language models (LLMs). On the other hand, many linguistic resources, such as dictionaries, are rarely used in this context despite their large information contents. We show how LLMs can be used to extend existing language resources in less-resourced languages for two important tasks: word-sense disambiguation (WSD) and word-sense induction (WSI). We approach the two tasks through the related but much more accessible word-in-context (WiC) task where, given a pair of sentences and a target word, a classification model is tasked with predicting whether the sense of a given word differs between sentences. We demonstrate that a well-trained model for this task can distinguish between different word senses and can be adapted to solve the WSD and WSI tasks. The advantage of using the WiC task, instead of directly predicting senses, is that the WiC task does not need pre-constructed sense inventories with a sufficient number of examples for each sense, which are rarely available in less-resourced languages. We show that sentence pairs for the WiC task can be successfully generated from dictionary examples using LLMs. The resulting prediction models outperform existing models on WiC, WSD, and WSI tasks. We demonstrate our methodology on the Slovene language, where a monolingual dictionary is available, but word-sense resources are tiny.

As question answering (QA) systems advance alongside the rapid evolution of foundation models, the need for robust, adaptable, and large-scale evaluation benchmarks becomes increasingly critical. Traditional QA benchmarks are often static and publicly available, making them susceptible to data contamination and memorization by large language models (LLMs). Consequently, static benchmarks may overestimate model generalization and hinder a reliable assessment of real-world performance. In this work, we introduce Dynamic-KGQA, a scalable framework for generating adaptive QA datasets from knowledge graphs (KGs), designed to mitigate memorization risks while maintaining statistical consistency across iterations. Unlike fixed benchmarks, Dynamic-KGQA generates a new dataset variant on every run while preserving the underlying distribution, enabling fair and reproducible evaluations. Furthermore, our framework provides fine-grained control over dataset characteristics, supporting domain-specific and topic-focused QA dataset generation. Additionally, Dynamic-KGQA produces compact, semantically coherent subgraphs that facilitate both training and evaluation of KGQA models, enhancing their ability to leverage structured knowledge effectively. To align with existing evaluation protocols, we also provide static large-scale train/test/validation splits, ensuring comparability with prior methods. By introducing a dynamic, customizable benchmarking paradigm, Dynamic-KGQA enables a more rigorous and adaptable evaluation of QA systems.

Reasoning language models have shown an uncanny ability to improve performance at test-time by ``thinking longer''-that is, by generating longer chain-of-thought sequences and hence using more compute. However, the length of their chain-of-thought reasoning is not controllable, making it impossible to allocate test-time compute to achieve a desired level of performance. We introduce Length Controlled Policy Optimization (LCPO), a simple reinforcement learning method that optimizes for accuracy and adherence to user-specified length constraints. We use LCPO to train L1, a reasoning language model that produces outputs satisfying a length constraint given in its prompt. L1's length control allows for smoothly trading off computational cost and accuracy on a wide range of tasks, and outperforms the state-of-the-art S1 method for length control. Furthermore, we uncover an unexpected short chain-of-thought capability in models trained with LCPO. For instance, our 1.5B L1 model surpasses GPT-4o at equal reasoning lengths. Overall, LCPO enables precise control over reasoning length, allowing for fine-grained allocation of test-time compute and accuracy. We release code and models at https://www.cmu-l3.github.io/l1

Multi-entity question answering (MEQA) poses significant challenges for large language models (LLMs), which often struggle to consolidate scattered information across multiple documents. An example question might be "What is the distribution of IEEE Fellows among various fields of study?", which requires retrieving information from diverse sources e.g., Wikipedia pages. The effectiveness of current retrieval-augmented generation (RAG) methods is limited by the LLMs' capacity to aggregate insights from numerous pages. To address this gap, this paper introduces a structured RAG (SRAG) framework that systematically organizes extracted entities into relational tables (e.g., tabulating entities with schema columns like "name" and "field of study") and then apply table-based reasoning techniques. Our approach decouples retrieval and reasoning, enabling LLMs to focus on structured data analysis rather than raw text aggregation. Extensive experiments on Wikipedia-based multi-entity QA tasks demonstrate that SRAG significantly outperforms state-of-the-art long-context LLMs and RAG solutions, achieving a 29.6% improvement in accuracy. The results underscore the efficacy of structuring unstructured data to enhance LLMs' reasoning capabilities.

Despite recent advances in artificial intelligence (AI), it poses challenges to ensure personalized decision-making in tasks that are not considered in training datasets. To address this issue, we propose ValuePilot, a two-phase value-driven decision-making framework comprising a dataset generation toolkit DGT and a decision-making module DMM trained on the generated data. DGT is capable of generating scenarios based on value dimensions and closely mirroring real-world tasks, with automated filtering techniques and human curation to ensure the validity of the dataset. In the generated dataset, DMM learns to recognize the inherent values of scenarios, computes action feasibility and navigates the trade-offs between multiple value dimensions to make personalized decisions. Extensive experiments demonstrate that, given human value preferences, our DMM most closely aligns with human decisions, outperforming Claude-3.5-Sonnet, Gemini-2-flash, Llama-3.1-405b and GPT-4o. This research is a preliminary exploration of value-driven decision-making. We hope it will stimulate interest in value-driven decision-making and personalized decision-making within the community.

--The rapid evolution of malware attacks calls for the development of innovative detection methods, especially in resource-constrained edge computing. Traditional detection techniques struggle to keep up with modern malware's sophistication and adaptability, prompting a shift towards advanced methodologies like those leveraging Large Language Models (LLMs) for enhanced malware detection. However, deploying LLMs for malware detection directly at edge devices raises several challenges, including ensuring accuracy in constrained environments and addressing edge devices' energy and computational limits. T o tackle these challenges, this paper proposes an architecture leveraging lightweight LLMs' strengths while addressing limitations like reduced accuracy and insufficient computational power . T o evaluate the effectiveness of the proposed lightweight LLM-based approach for edge computing, we perform an extensive experimental evaluation using several state-of-the-art lightweight LLMs. We test them with several publicly available datasets specifically designed for edge and IoT scenarios and different edge nodes with varying computational power and characteristics. In recent years, the rapid evolution of malware attacks has necessitated the development of innovative approaches for their detection, particularly in the resource-constrained edge computing domain. While foundational, traditional detection techniques have struggled to keep pace with modern malware's increasing sophistication and adaptability. This has prompted a shift towards exploring advanced methodologies, including using lightweight Large Language Models (LLMs), to enhance malware detection capabilities in edge environments. DistilGPT -2, and TinyT5 have emerged as promising solutions. These models leverage techniques such as distillation and pruning to significantly reduce their size and computational requirements, making them more suitable for edge-devices deployment. Despite their smaller footprint, these models retain much of their larger counterparts' pattern recognition and contextual understanding capabilities, allowing them to process and analyze complex, unstructured data streams effectively. In the context of malware detection, they offer the potential for improved accuracy, real-time adaptability, and continuous learning while addressing the strict energy, storage, and computational constraints of edge computing environments. However, deploying LLMs for malware detection in edge computing is not without challenges. Model performance: maintaining high accuracy under the constraints of edge environments remains a significant hurdle. While LLMs excel in natural language understanding and pattern recognition, their generalizability across diverse edge scenarios is often limited, particularly when faced with malware's dynamic and adaptive nature [1].

Clinical measurements such as blood pressures and respiration rates are critical in diagnosing and monitoring patient outcomes. It is an important component of biomedical data, which can be used to train transformer-based language models (LMs) for improving healthcare delivery. It is, however, unclear whether LMs can effectively interpret and use clinical measurements. We investigate two questions: First, can LMs effectively leverage clinical measurements to answer related medical questions? Second, how to enhance an LM's performance on medical question-answering (QA) tasks that involve measurements? We performed a case study on blood pressure readings (BPs), a vital sign routinely monitored by medical professionals. We evaluated the performance of four LMs: BERT, BioBERT, MedAlpaca, and GPT-3.5, on our newly developed dataset, BPQA (Blood Pressure Question Answering). BPQA contains $100$ medical QA pairs that were verified by medical students and designed to rely on BPs . We found that GPT-3.5 and MedAlpaca (larger and medium sized LMs) benefit more from the inclusion of BPs than BERT and BioBERT (small sized LMs). Further, augmenting measurements with labels improves the performance of BioBERT and Medalpaca (domain specific LMs), suggesting that retrieval may be useful for improving domain-specific LMs.

Retrieval-augmented generation (RAG) provides LLMs with relevant documents. Although previous studies noted that retrieving many documents can degrade performance, they did not isolate how the quantity of documents affects performance while controlling for context length. We evaluate various language models on custom datasets derived from a multi-hop QA task. We keep the context length and position of relevant information constant while varying the number of documents, and find that increasing the document count in RAG settings poses significant challenges for LLMs. Additionally, our results indicate that processing multiple documents is a separate challenge from handling long contexts.

Large Language Models (LLMs) have demonstrated remarkable capabilities in reasoning tasks, leading to their widespread deployment. However, recent studies have highlighted concerning biases in these models, particularly in their handling of dialectal variations like African American English (AAE). In this work, we systematically investigate dialectal disparities in LLM reasoning tasks. We develop an experimental framework comparing LLM performance given Standard American English (SAE) and AAE prompts, combining LLM-based dialect conversion with established linguistic analyses. We find that LLMs consistently produce less accurate responses and simpler reasoning chains and explanations for AAE inputs compared to equivalent SAE questions, with disparities most pronounced in social science and humanities domains. These findings highlight systematic differences in how LLMs process and reason about different language varieties, raising important questions about the development and deployment of these systems in our multilingual and multidialectal world. Our code repository is publicly available at https://github.com/Runtaozhou/dialect_bias_eval.

Many studies combine text and audio to capture multi-modal information but they overlook the model's generalization ability on new datasets. Introducing new datasets may affect the feature space of the original dataset, leading to catastrophic forgetting. Meanwhile, large model parameters can significantly impact training performance. To address these limitations, we introduce a novel task called Text-Audio Incremental Learning (TAIL) task for text-audio retrieval, and propose a new method, PTAT, Prompt Tuning for Audio-Text incremental learning. This method utilizes prompt tuning to optimize the model parameters while incorporating an audio-text similarity and feature distillation module to effectively mitigate catastrophic forgetting. We benchmark our method and previous incremental learning methods on AudioCaps, Clotho, BBC Sound Effects and Audioset datasets, and our method outperforms previous methods significantly, particularly demonstrating stronger resistance to forgetting on older datasets. Compared to the full-parameters Finetune (Sequential) method, our model only requires 2.42\% of its parameters, achieving 4.46\% higher performance.