Token prediction stability remains a challenge in autoregressive generative models, where minor variations in early inference steps often lead to significant semantic drift over extended sequences. A structured modulation mechanism was introduced to regulate hidden state transitions, ensuring that latent representation trajectories remain aligned with prior contextual dependencies while preserving generative flexibility. The modulation framework was designed to function within transformer-based architectures, dynamically constraining representation evolution without imposing external memory dependencies or extensive architectural modifications. Empirical evaluations demonstrated that structured latent adjustments contributed to reductions in perplexity fluctuations, entropy variance, and lexical instability, improving coherence in long-form text generation. Gradient propagation stability was further analyzed, revealing that the modulation process led to smoother optimization pathways, mitigating erratic fluctuations in weight updates across successive inference steps. The computational efficiency of the modulation process was assessed, showing that its integration within transformer-based architectures introduced only marginal overhead while maintaining compatibility with existing optimization frameworks. The structured modulation constraints also influenced syntactic variation, preventing excessive repetition while maintaining balanced sentence length distributions. Comparative evaluations against baseline models reinforced the role of controlled latent state evolution in improving pronoun resolution, logical consistency, and contextual alignment across autoregressive text generation tasks.

O'Boyle 1, Sida Wang 2, Gabriel Synnaeve 2, Hugh Leather 2 1 University of Edinburgh 2 Meta AI A BSTRACT Code generation and understanding are critical capabilities for large language models (LLMs). Thus, most LLMs are pretrained and fine-tuned on code data. However, these datasets typically treat code as static strings and rarely exploit the dynamic information about their execution. Building upon previous work on trace modeling, we study Execution Tuning (E.T.), a training procedure in which we explicitly model real-world program execution traces without requiring manual test annotations. We train and evaluate models on different execution trace granularities (line and instruction-level) and strategies on the task of output prediction, obtaining 80% accuracy on CruxEval and MBPP, and showing the advantages of dynamic scratchpads (i.e., self-contained intermediate computations updated by the model rather than accumulated as a history of past computations) on long executions (up to 14k steps). Finally, we discuss E.T.'s practical applications. Current state-of-the-art general-purpose LLMs are thought to contain considerable proportions of code in their pretraining data (OpenAI et al., 2024), which is known to improve reasoning capabilities even in tasks seemingly unrelated to code (Aryabumi et al., 2024). However, datasets used to train code LLMs (such as Lozhkov et al. (2024)) typically treat code as static strings and rarely exploit the dynamic information about their execution. Executability is one of the key differences between code and natural language, and most code datasets neglect dimensions of the code domain such as reasoning over code execution, which in turn could lead to better code understanding. This fundamental limitation has sparked a renewed interest in modeling program executions, connecting with the pre-LLM neural program evaluation literature (Zaremba & Sutskever, 2014; Graves et al., 2014), which studied whether neural networks could learn to execute programs.

Electroencephalography provides a non-invasive window into brain activity, offering valuable insights for neurological research, brain-computer interfaces, and clinical diagnostics. However, the development of robust machine learning models for EEG analysis is hindered by the scarcity of large-scale, well-annotated datasets and the inherent variability of EEG signals across subjects and recording conditions. Inspired by the success of foundation models in natural language processing and computer vision, we propose the Large Cognition Model-a transformer-based foundation model designed to generalize across diverse EEG datasets and downstream tasks. Unlike traditional approaches, our proposed transformer-based architecture demonstrates strong generalization capabilities across datasets and tasks, even without pretraining, surpassing some existing EEG universal models on specific downstream applications. LCM leverages large-scale self-supervised learning techniques to capture universal EEG representations, enabling efficient fine-tuning for applications such as cognitive state decoding, disease classification, and neurofeedback systems. We introduce a novel architecture that integrates temporal and spectral attention mechanisms, optimizing the model's ability to extract meaningful features from raw EEG signals. Extensive evaluations demonstrate that LCM outperforms state-of-the-art approaches across multiple EEG benchmarks, exhibiting strong cross-subject and cross-task generalization. Our findings highlight the potential of pretrained EEG foundation models to accelerate advancements in neuroscience, personalized medicine, and BCI technology.

This paper introduces Text2Net, an innovative text-based network simulation engine that leverages natural language processing (NLP) and large language models (LLMs) to transform plain-text descriptions of network topologies into dynamic, interactive simulations. Text2Net simplifies the process of configuring network simulations, eliminating the need for users to master vendor-specific syntaxes or navigate complex graphical interfaces. Through qualitative and quantitative evaluations, we demonstrate Text2Net's ability to significantly reduce the time and effort required to deploy network scenarios compared to traditional simulators like EVE-NG. By automating repetitive tasks and enabling intuitive interaction, Text2Net enhances accessibility for students, educators, and professionals. The system facilitates hands-on learning experiences for students that bridge the gap between theoretical knowledge and practical application. The results showcase its scalability across various network complexities, marking a significant step toward revolutionizing network education and professional use cases, such as proof-of-concept testing.

Metonymy plays an important role in our daily communication. People naturally think about things using their most salient properties or commonly related concepts. For example, by saying "The bus decided to skip our stop today," we actually mean that the bus driver made the decision, not the bus. Prior work on metonymy resolution has mainly focused on named entities. However, metonymy involving common nouns (such as desk, baby, and school) is also a frequent and challenging phenomenon. We argue that NLP systems should be capable of identifying the metonymic use of common nouns in context. We create a new metonymy dataset ConMeC, which consists of 6,000 sentences, where each sentence is paired with a target common noun and annotated by humans to indicate whether that common noun is used metonymically or not in that context. We also introduce a chain-of-thought based prompting method for detecting metonymy using large language models (LLMs). We evaluate our LLM-based pipeline, as well as a supervised BERT model on our dataset and three other metonymy datasets. Our experimental results demonstrate that LLMs could achieve performance comparable to the supervised BERT model on well-defined metonymy categories, while still struggling with instances requiring nuanced semantic understanding. Our dataset is publicly available at: https://github.com/SaptGhosh/ConMeC.

Recently, large language models (LLMs) have been deployed to tackle various software engineering (SE) tasks like code generation, significantly advancing the automation of SE tasks. However, assessing the quality of these LLM-generated code and text remains challenging. The commonly used Pass@k metric necessitates extensive unit tests and configured environments, demands a high labor cost, and is not suitable for evaluating LLM-generated text. Conventional metrics like BLEU, which measure only lexical rather than semantic similarity, have also come under scrutiny. In response, a new trend has emerged to employ LLMs for automated evaluation, known as LLM-as-a-judge. These LLM-as-a-judge methods are claimed to better mimic human assessment than conventional metrics without relying on high-quality reference answers. Nevertheless, their exact human alignment in SE tasks remains unexplored. In this paper, we empirically explore LLM-as-a-judge methods for evaluating SE tasks, focusing on their alignment with human judgments. We select seven LLM-as-a-judge methods that utilize general-purpose LLMs, alongside two LLMs specifically fine-tuned for evaluation. After generating and manually scoring LLM responses on three recent SE datasets of code translation, code generation, and code summarization, we then prompt these methods to evaluate each response. Finally, we compare the scores generated by these methods with human evaluation. The results indicate that output-based methods reach the highest Pearson correlation of 81.32 and 68.51 with human scores in code translation and generation, achieving near-human evaluation, noticeably outperforming ChrF++, one of the best conventional metrics, at 34.23 and 64.92. Such output-based methods prompt LLMs to output judgments directly, and exhibit more balanced score distributions that resemble human score patterns. Finally, we provide...

Web-scale pre-training datasets are the cornerstone of LLMs' success. However, text data curated from the internet inevitably contains random noise caused by decoding errors or unregulated web content. In contrast to previous works that focus on low quality or synthetic data, our study \textbf{provides the first systematic investigation into such random noise through a cohesive ``What-Why-How'' framework.} Surprisingly, we observed that the resulting increase in next-token prediction (NTP) loss was significantly lower than the proportion of random noise. We provide a theoretical justification for this phenomenon, which also elucidates the success of multilingual models. On the other hand, experiments show that the model's performance in downstream tasks is not based solely on the NTP loss, which means that random noise may result in degraded downstream performance. To address the potential adverse effects, we introduce a novel plug-and-play Local Gradient Matching loss, which explicitly enhances the denoising capability of the downstream task head by aligning the gradient of normal and perturbed features without requiring knowledge of the model's parameters. Additional experiments on 8 language and 14 vision benchmarks further validate its effectiveness.

Accurate and efficient diagnosis in online medical consultations remains a challenge for current large language models. These models often rely on single-turn interactions and lack the ability to refine their predictions through follow-up questions. Additionally, their responses frequently contain complex medical terminology, making them less accessible to non-medical users and creating barriers to effective communication. In this paper, we introduce Ask Patients with Patience (APP), the first multi-turn dialogue that enables LLMs to iteratively refine diagnoses based on grounded reasoning. By integrating medical guidelines and entropy minimization, APP improves both diagnostic accuracy and efficiency. Furthermore, it features human-centric communication that bridges the gap between user comprehension and medical terminology, significantly enhancing user accessibility and engagement. We evaluated APP using a subset of the ReMeDi dataset, comparing it with single-turn and traditional multi-turn LLM baselines. APP achieved higher similarity scores in diagnosis predictions, demonstrating better alignment with ground truth diagnoses. Entropy analysis showed that APP reduces diagnostic uncertainty more rapidly across iterations, increasing confidence in its predictions. APP also excels in user accessibility and empathy, further bridging the gap between complex medical language and user understanding. Code will be released at: https://github.com/SuperMedIntel/AskPatients.

Current and foreseeable GenAI models are not capable of achieving artificial general intelligence because they are burdened with anthropogenic debt. They depend heavily on human input to provide well-structured problems, architecture, and training data. They cast every problem as a language pattern learning problem and are thus not capable of the kind of autonomy needed to achieve artificial general intelligence. Current models succeed at their tasks because people solve most of the problems to which these models are directed, leaving only simple computations for the model to perform, such as gradient descent. Another barrier is the need to recognize that there are multiple kinds of problems, some of which cannot be solved by available computational methods (for example, "insight problems"). Current methods for evaluating models (benchmarks and tests) are not adequate to identify the generality of the solutions, because it is impossible to infer the means by which a problem was solved from the fact of its solution. A test could be passed, for example, by a test-specific or a test-general method. It is a logical fallacy (affirming the consequent) to infer a method of solution from the observation of success.

Debating over conflicting issues is a necessary first step towards resolving conflicts. However, intrinsic perspectives of an arguer are difficult to overcome by persuasive argumentation skills. Proceeding from a debate to a deliberative process, where we can identify actionable options for resolving a conflict requires a deeper analysis of arguments and the perspectives they are grounded in - as it is only from there that one can derive mutually agreeable resolution steps. In this work we develop a framework for a deliberative analysis of arguments in a computational argumentation setup. We conduct a fine-grained analysis of perspectivized stances expressed in the arguments of different arguers or stakeholders on a given issue, aiming not only to identify their opposing views, but also shared perspectives arising from their attitudes, values or needs. We formalize this analysis in Perspectivized Stance Vectors that characterize the individual perspectivized stances of all arguers on a given issue. We construct these vectors by determining issue- and argument-specific concepts, and predict an arguer's stance relative to each of them. The vectors allow us to measure a modulated (dis)agreement between arguers, structured by perspectives, which allows us to identify actionable points for conflict resolution, as a first step towards deliberation.