Empowering large language models (LLMs) with chemical intelligence remains a challenge due to the scarcity of high-quality, domain-specific instruction-response datasets and the misalignment of existing synthetic data generation pipelines with the inherently hierarchical and rule-governed structure of chemical information. To address this, we propose ChemOrch, a framework that synthesizes chemically grounded instruction-response pairs through a two-stage process: task-controlled instruction generation and tool-aware response construction. ChemOrch enables controllable diversity and levels of difficulty for the generated tasks, and ensures response precision through tool planning and distillation, and tool-based self-repair mechanisms. The effectiveness of ChemOrch is evaluated based on: 1) the high quality of generated instruction data, demonstrating superior diversity and strong alignment with chemical constraints; 2) the reliable generation of evaluation tasks that more effectively reveal LLM weaknesses in chemistry; and 3) the significant improvement of LLM chemistry capabilities when the generated instruction data are used for fine-tuning. Our work thus represents a critical step toward scalable and verifiable chemical intelligence in LLMs.

Authorship representation (AR) learning, which models an author's unique writing style, has demonstrated strong performance in authorship attribution tasks. However, prior research has primarily focused on monolingual settings-mostly in English-leaving the potential benefits of multilingual AR models underexplored. We introduce a novel method for multilingual AR learning that incorporates two key innovations: probabilistic content masking, which encourages the model to focus on stylistically indicative words rather than content-specific words, and language-aware batching, which improves contrastive learning by reducing cross-lingual interference. Our model is trained on over 4.5 million authors across 36 languages and 13 domains. It consistently outperforms monolingual baselines in 21 out of 22 non-English languages, achieving an average Recall@8 improvement of 4.85%, with a maximum gain of 15.91% in a single language. Furthermore, it exhibits stronger cross-lingual and cross-domain generalization compared to a monolingual model trained solely on English. Our analysis confirms the effectiveness of both proposed techniques, highlighting their critical roles in the model's improved performance.

Millimeter-wave (mmWave) sensing technology holds significant value in human-centric applications, yet the high costs associated with data acquisition and annotation limit its widespread adoption in our daily lives. Concurrently, the rapid evolution of large language models (LLMs) has opened up opportunities for addressing complex human needs. This paper presents mmExpert, an innovative mmWave understanding framework consisting of a data generation flywheel that leverages LLMs to automate the generation of synthetic mmWave radar datasets for specific application scenarios, thereby training models capable of zero-shot generalization in real-world environments. Extensive experiments demonstrate that the data synthesized by mmExpert significantly enhances the performance of downstream models and facilitates the successful deployment of large models for mmWave understanding.

Multimodal vision-language models (VLMs) have made substantial progress in various tasks that require a combined understanding of visual and textual content, particularly in cultural understanding tasks, with the emergence of new cultural datasets. However, these datasets frequently fall short of providing cultural reasoning while underrepresenting many cultures. In this paper, we introduce the Seeing Culture Benchmark (SCB), focusing on cultural reasoning with a novel approach that requires VLMs to reason on culturally rich images in two stages: i) selecting the correct visual option with multiple-choice visual question answering (VQA), and ii) segmenting the relevant cultural artifact as evidence of reasoning. Visual options in the first stage are systematically organized into three types: those originating from the same country, those from different countries, or a mixed group. Notably, all options are derived from a singular category for each type. Progression to the second stage occurs only after a correct visual option is chosen. The SCB benchmark comprises 1,065 images that capture 138 cultural artifacts across five categories from seven Southeast Asia countries, whose diverse cultures are often overlooked, accompanied by 3,178 questions, of which 1,093 are unique and meticulously curated by human annotators. Our evaluation of various VLMs reveals the complexities involved in cross-modal cultural reasoning and highlights the disparity between visual reasoning and spatial grounding in culturally nuanced scenarios. The SCB serves as a crucial benchmark for identifying these shortcomings, thereby guiding future developments in the field of cultural reasoning. https://github.com/buraksatar/SeeingCulture

When existing retrieval-augmented generation (RAG) solutions are intended to be used for new knowledge domains, it is necessary to update their encoders, which are taken to be pre-trained large language models (LLMs). However, fully fine-tuning these large models is compute-and memory-intensive, and even infeasible when deployed on resource-constrained edge devices. We propose a novel encoder architecture in this work that addresses this limitation by using a frozen small language model (SLM), which satisfies the memory constraints of edge devices, and inserting a small adapter network before the transformer blocks of the SLM. The train-able adapter takes the token embeddings of the new corpus and learns to produce enhanced soft embeddings for it, while requiring significantly less compute power to update than full fine-tuning. We further propose a novel retrieval mechanism by attaching a classifier head to the SLM encoder, which is trained to learn a similarity mapping of the input embeddings to their corresponding documents. Finally, to enable the online fine-tuning of both (i) the encoder soft embeddings and (ii) the classifier-as-retriever on edge devices, we adopt federated learning (FL) and differential privacy (DP) to achieve an efficient, privacy-preserving, and product-grade training solution. We conduct a theoretical analysis of our methodology, establishing convergence guarantees under mild assumptions on gradient variance when deployed for general smooth non-convex loss functions. Through extensive numerical experiments, we demonstrate (i) the efficacy of obtaining soft em-beddings to enhance the encoder, (ii) training a classifier to improve the retriever, and (iii) the role of FL in achieving speedup.

Retrieval-Augmented Generation (RAG) has significantly mitigated the hallucinations of Large Language Models (LLMs) by grounding the generation with external knowledge. Recent extensions of RAG to graph-based retrieval offer a promising direction, leveraging the structural knowledge for multi-hop reasoning. However, existing graph RAG typically decouples retrieval and reasoning processes, which prevents the retriever from adapting to the reasoning needs of the LLM. They also struggle with scalability when performing multi-hop expansion over large-scale graphs, or depend heavily on annotated ground-truth entities, which are often unavailable in open-domain settings. To address these challenges, we propose a novel graph retriever trained end-to-end with LLM, which features an attention-based growing and pruning mechanism, adaptively navigating multi-hop relevant entities while filtering out noise. Within the extracted subgraph, structural knowledge and semantic features are encoded via soft tokens and the verbalized graph, respectively, which are infused into the LLM together, thereby enhancing its reasoning capability and facilitating interactive joint training of the graph retriever and the LLM reasoner. Experimental results across three QA benchmarks show that our approach consistently achieves state-of-the-art performance, validating the strength of joint graph-LLM optimization for complex reasoning tasks. Notably, our framework eliminates the need for predefined ground-truth entities by directly optimizing the retriever using LLM logits as implicit feedback, making it especially effective in open-domain settings.

The recent emergence of large language models (LLMs) such as GPT-3 has marked a significant paradigm shift in machine learning. Trained on massive corpora of data, these models demonstrate remarkable capabilities in language understanding, generation, summarization, and reasoning, transforming how intelligent systems process and interact with human language. Although LLMs may still seem like a recent breakthrough, the field is already witnessing the rise of a new and more general category: multi-modal, multi-task foundation models (M3T FMs). These models go beyond language and can process heterogeneous data types/modalities, such as time-series measurements, audio, imagery, tabular records, and unstructured logs, while supporting a broad range of downstream tasks spanning forecasting, classification, control, and retrieval. When combined with federated learning (FL), they give rise to M3T Federated Foundation Models (FedFMs): a highly recent and largely unexplored class of models that enable scalable, privacy-preserving model training/fine-tuning across distributed data sources. In this paper, we take one of the first steps toward introducing these models to the power systems research community by offering a bidirectional perspective: (i) M3T FedFMs for smart grids and (ii) smart grids for FedFMs. In the former, we explore how M3T FedFMs can enhance key grid functions, such as load/demand forecasting and fault detection, by learning from distributed, heterogeneous data available at the grid edge in a privacy-preserving manner. In the latter, we investigate how the constraints and structure of smart grids, spanning energy, communication, and regulatory dimensions, shape the design, training, and deployment of M3T FedFMs.

Dialogue is one of the landmark abilities of large language models (LLMs). Despite its ubiquity, few studies actually distinguish specific ingredients underpinning dialogue behavior emerging during post-training. We employ a comprehensive suite of model-based metrics, each targeting a distinct fine-grained aspect of dialogue, motivated by linguistic theory. We evaluate how the performance of pre-trained Pythia models changes with respect to each of those dimensions, depending on model size and as a result of supervised fine-tuning on conversational datasets. We observe only a mild impact of raw model size on most metrics, whereas fine-tuning quickly saturates the scores for all but the smallest models tested. Somewhat contrary to our expectations, many metrics show very similar trends, especially if they are all rooted in the same evaluator model, which raises the question of their reliability in measuring a specific dimension. To that end, we conduct additional analyses of score distributions, metric correlations, and term frequencies in generated responses to help explain our observations.

While prior studies have questioned whether intrinsic bias in LLMs affects fairness at the downstream task level, this work empirically investigates the connection. We present a unified evaluation framework to compare intrinsic bias mitigation via concept unlearning with extrinsic bias mitigation via counterfactual data augmentation (CDA). We examine this relationship through real-world financial classification tasks, including salary prediction, employment status, and creditworthiness assessment. Using three open-source LLMs, we evaluate models both as frozen embedding extractors and as fine-tuned classifiers. Our results show that intrinsic bias mitigation through unlearning reduces intrinsic gender bias by up to 94.9%, while also improving downstream task fairness metrics, such as demographic parity by up to 82%, without compromising accuracy. Our framework offers practical guidance on where mitigation efforts can be most effective and highlights the importance of applying early-stage mitigation before downstream deployment.

Semantic identifiers (IDs) have proven effective in adapting large language models for generative recommendation and retrieval. However, existing methods often suffer from semantic ID conflicts, where semantically similar documents (or items) are assigned identical IDs. A common strategy to avoid conflicts is to append a non-semantic token to distinguish them, which introduces randomness and expands the search space, therefore hurting performance. In this paper, we propose purely semantic indexing to generate unique, semantic-preserving IDs without appending non-semantic tokens. We enable unique ID assignment by relaxing the strict nearest-centroid selection and introduce two model-agnostic algorithms: exhaustive candidate matching (ECM) and recursive residual searching (RRS). Extensive experiments on sequential recommendation, product search, and document retrieval tasks demonstrate that our methods improve both overall and cold-start performance, highlighting the effectiveness of ensuring ID uniqueness.