Multilingual large language models (LLMs) aim towards robust natural language understanding across diverse languages, yet their performance significantly degrades on low-resource languages. This work explores whether existing techniques to identify language-specific neurons can be leveraged to enhance cross-lingual task performance of lowresource languages. We conduct detailed experiments covering existing language-specific neuron identification techniques (such as Language Activation Probability Entropy and activation probability-based thresholding) and neuron-specific LoRA fine-tuning with models like Llama 3.1 and Mistral Nemo. We find that such neuron-specific interventions are insufficient to yield cross-lingual improvements on downstream tasks (XNLI, XQuAD) in lowresource languages. This study highlights the challenges in achieving cross-lingual generalization and provides critical insights for multilingual LLMs.

As large language models have shown remarkable capabilities in conversing via natural language, the question arises as to how LLMs could potentially assist chemical engineers in research and industry with domain-specific tasks. We generate dynamic chemical reactor models in Modelica code format from textual descriptions as user input. We fine-tune Llama 3.1 8B Instruct on synthetically generated Modelica code for different reactor scenarios. We compare the performance of our fine-tuned model to the baseline Llama 3.1 8B Instruct model and GPT4o. We manually assess the models' predictions regarding the syntactic and semantic accuracy of the generated dynamic models. We find that considerable improvements are achieved by the fine-tuned model with respect to both the semantic and the syntactic accuracy of the Modelica models. However, the fine-tuned model lacks a satisfactory ability to generalize to unseen scenarios compared to GPT4o.

Large Language Models (LLMs) have demonstrated remarkable capabilities, yet their transition to real-world applications reveals a critical limitation: the inability to adapt to individual preferences while maintaining alignment with universal human values. Current alignment techniques adopt a one-size-fits-all approach that fails to accommodate users' diverse backgrounds and needs. This paper presents the first comprehensive survey of personalized alignment-a paradigm that enables LLMs to adapt their behavior within ethical boundaries based on individual preferences. We propose a unified framework comprising preference memory management, personalized generation, and feedback-based alignment, systematically analyzing implementation approaches and evaluating their effectiveness across various scenarios. By examining current techniques, potential risks, and future challenges, this survey provides a structured foundation for developing more adaptable and ethically-aligned LLMs.

An important question today is whether a given text was used to train a large language model (LLM). A \emph{completion} test is often employed: check if the LLM completes a sufficiently complex text. This, however, requires a ground-truth definition of membership; most commonly, it is defined as a member based on the $n$-gram overlap between the target text and any text in the dataset. In this work, we demonstrate that this $n$-gram based membership definition can be effectively gamed. We study scenarios where sequences are \emph{non-members} for a given $n$ and we find that completion tests still succeed. We find many natural cases of this phenomenon by retraining LLMs from scratch after removing all training samples that were completed; these cases include exact duplicates, near-duplicates, and even short overlaps. They showcase that it is difficult to find a single viable choice of $n$ for membership definitions. Using these insights, we design adversarial datasets that can cause a given target sequence to be completed without containing it, for any reasonable choice of $n$. Our findings highlight the inadequacy of $n$-gram membership, suggesting membership definitions fail to account for auxiliary information available to the training algorithm.

Patients are increasingly turning to online health Q&A communities for social support to improve their well-being. However, when this support received does not align with their specific needs, it may prove ineffective or even detrimental. This necessitates a model capable of identifying the social support needs in questions. However, training such a model is challenging due to the scarcity and class imbalance issues of labeled data. To overcome these challenges, we follow the computational design science paradigm to develop a novel framework, Hybrid Approach for SOcial Support need classification (HA-SOS). HA-SOS integrates an answer-enhanced semi-supervised learning approach, a text data augmentation technique leveraging large language models (LLMs) with reliability- and diversity-aware sample selection mechanism, and a unified training process to automatically label social support needs in questions. Extensive empirical evaluations demonstrate that HA-SOS significantly outperforms existing question classification models and alternative semi-supervised learning approaches. This research contributes to the literature on social support, question classification, semi-supervised learning, and text data augmentation. In practice, our HA-SOS framework facilitates online Q&A platform managers and answerers to better understand users' social support needs, enabling them to provide timely, personalized answers and interventions.

The meaning conveyed by a sentence often depends on the context in which it appears. Despite the progress of sentence embedding methods, it remains unclear how to best modify a sentence embedding conditioned on its context. To address this problem, we propose Condition-Aware Sentence Embeddings (CASE), an efficient and accurate method to create an embedding for a sentence under a given condition. First, CASE creates an embedding for the condition using a Large Language Model (LLM), where the sentence influences the attention scores computed for the tokens in the condition during pooling. Next, a supervised nonlinear projection is learned to reduce the dimensionality of the LLM-based text embeddings. We show that CASE significantly outperforms previously proposed Conditional Semantic Textual Similarity (C-STS) methods on an existing standard benchmark dataset. We find that subtracting the condition embedding consistently improves the C-STS performance of LLM-based text embeddings. Moreover, we propose a supervised dimensionality reduction method that not only reduces the dimensionality of LLM-based embeddings but also significantly improves their performance.

Large language models (LLMs) have traditionally been aligned through one-size-fits-all approaches that assume uniform human preferences, fundamentally overlooking the diversity in user values and needs. This paper introduces a comprehensive framework for scalable personalized alignment of LLMs. We establish a systematic preference space characterizing psychological and behavioral dimensions, alongside diverse persona representations for robust preference inference in real-world scenarios. Building upon this foundation, we introduce \textsc{AlignX}, a large-scale dataset of over 1.3 million personalized preference examples, and develop two complementary alignment approaches: \textit{in-context alignment} directly conditioning on persona representations and \textit{preference-bridged alignment} modeling intermediate preference distributions. Extensive experiments demonstrate substantial improvements over existing methods, with an average 17.06\% accuracy gain across four benchmarks while exhibiting a strong adaptation capability to novel preferences, robustness to limited user data, and precise preference controllability. These results validate our framework's effectiveness, advancing toward truly user-adaptive AI systems.

Programming language and library choices are crucial to software reliability and security. Poor or inconsistent choices can lead to increased technical debt, security vulnerabilities, and even catastrophic failures in safety-critical systems. As Large Language Models (LLMs) play an increasing role in code generation, it is essential to understand how they make these decisions. However, little is known about their preferences when selecting programming languages and libraries for different coding tasks. To fill this gap, this study provides the first in-depth investigation into LLM preferences for programming languages and libraries used when generating code. We assess the preferences of eight diverse LLMs by prompting them to complete various coding tasks, including widely-studied benchmarks and the more practical task of generating the initial structural code for new projects (a crucial step that often determines a project's language or library choices). Our findings reveal that LLMs heavily favour Python when solving language-agnostic problems, using it in 90%-97% of cases for benchmark tasks. Even when generating initial project code where Python is not a suitable language, it remains the most-used language in 58% of instances. Moreover, LLMs contradict their own language recommendations in 83% of project initialisation tasks, raising concerns about their reliability in guiding language selection. Similar biases toward well-established libraries further create serious discoverability challenges for newer open-source projects. These results highlight the need to improve LLMs' adaptability to diverse programming contexts and to develop mechanisms for mitigating programming language and library bias.

Artificial intelligence systems based on large language models (LLMs) are increasingly used as agents that interact with users and with the world. To do so successfully, LLMs need to construct internal representations of the world and form probabilistic beliefs about those representations. To provide a user with personalized recommendations, for example, the LLM needs to gradually infer the user's preferences, over the course of multiple interactions. To evaluate whether contemporary LLMs are able to do so, we use the Bayesian inference framework from probability theory, which lays out the optimal way to update an agent's beliefs as it receives new information. We first show that the LLMs do not update their beliefs as expected from the Bayesian framework, and that consequently their predictions do not improve as expected as more information becomes available, even less so than we find is the case for humans. To address this issue, we teach the LLMs to reason in a Bayesian manner by training them to mimic the predictions of an optimal Bayesian model. We find that this approach not only significantly improves the LLM's performance on the particular recommendation task it is trained on, but also enables generalization to other tasks. This suggests that this method endows the LLM with broader Bayesian reasoning skills. More generally, our results indicate that LLMs can learn about reasoning strategies effectively and generalize those skills to new domains, which in part explains LLMs' empirical success.

This study provides the first comprehensive assessment of consistency and reproducibility in Large Language Model (LLM) outputs in finance and accounting research. We evaluate how consistently LLMs produce outputs given identical inputs through extensive experimentation with 50 independent runs across five common tasks: classification, sentiment analysis, summarization, text generation, and prediction. Using three OpenAI models (GPT-3.5-turbo, GPT-4o-mini, and GPT-4o), we generate over 3.4 million outputs from diverse financial source texts and data, covering MD&As, FOMC statements, finance news articles, earnings call transcripts, and financial statements. Our findings reveal substantial but task-dependent consistency, with binary classification and sentiment analysis achieving near-perfect reproducibility, while complex tasks show greater variability. More advanced models do not consistently demonstrate better consistency and reproducibility, with task-specific patterns emerging. LLMs significantly outperform expert human annotators in consistency and maintain high agreement even where human experts significantly disagree. We further find that simple aggregation strategies across 3-5 runs dramatically improve consistency. Simulation analysis reveals that despite measurable inconsistency in LLM outputs, downstream statistical inferences remain remarkably robust. These findings address concerns about what we term "G-hacking," the selective reporting of favorable outcomes from multiple Generative AI runs, by demonstrating that such risks are relatively low for finance and accounting tasks.