The paper introduces Knowledge-Weighted Fine‑Tuning, a method that estimates an instance‑level knowledge score through multi‑sampled inference and uses it to scale the learning signal. This approach encourages large language models to explicitly say "I don't know" on out‑of‑scope queries while preserving accuracy on known questions. The authors also propose new evaluation metrics for uncertainty, demonstrating that better discrimination between known and unknown instances improves overall performance.
By Joosung Lee, Hwiyeol Jo, Donghyeon Ko, Kyubyung Chae, Cheonbok Park, Jeonghoon Kim
arXiv:2604.08649v2 Announce Type: replace-cross
Abstract: Modern financial systems generate vast quantities of transactional and event-level data that encode rich economic signals. This paper present...
By Maxim Ostroukhov, Ruslan Mikhailov, Vladimir Iashin, Artem Sokolov, Andrei Akshonov, Vitaly Protasov, Andrey Goncharov, Dmitrii Beloborodov, Vince Mullin, Roman Yokunda Enzmann, Georgios Kolovos, Jason Renders, Pavel Nesterov, Anton Repushko
The paper evaluates Large Language Models for automatically analyzing responses in digital teacher simulations. Experiments compare DeBERTaV3 and Llama 3 across zero‑shot, few‑shot, and fine‑tuning settings, revealing that performance varies by characteristic and that Llama 3 consistently outperforms DeBERTaV3, especially when new characteristics must be identified. The findings suggest Llama 3 is preferable for dynamic simulation environments where teacher educators introduce new evaluation criteria.
By David de-Fitero-Dominguez, Mariano Albaladejo-Gonz\'alez, Antonio Garcia-Cabot, Eva Garcia-Lopez, Antonio Moreno-Cediel, Erin Barno, Justin Reich
Dynamic Embedded Topic Models (D-ETM) are extended to enable stable cross‑corpus temporal analysis by first learning a shared dynamic topic space—called the shared backbone—over a merged multi‑corpus collection. Corpus‑specific residual adaptation is then applied around this frozen backbone, allowing each corpus to specialize lexically without creating separate latent topic spaces. Experiments on three corpora spanning 97 years show that this approach yields much stronger alignment of topic trajectories (97.5 ± 0.7 % Retrieval@1) compared to full fine‑tuning or independent training with post‑hoc matching.
By Ruoxuan Li, Bruce Kogut
The paper introduces STReason, a modular multitask reasoning framework that combines large language models with spatio‑temporal models to handle complex natural language queries without task‑specific fine‑tuning. STReason decomposes queries into interpretable programs, executes them to produce numerical results and detailed, computation‑grounded explanations, thereby reducing hallucinations. The authors evaluate the system on a new benchmark and show it outperforms advanced LLM baselines, with human studies confirming its credibility and practical utility.
By Kethmi Hirushini Hettige, Jiahao Ji, Cheng Long, Shili Xiang, Gao Cong, Jingyuan Wang
The paper introduces Entropy-Valley (EV), a training‑free method for selecting target length in masked diffusion machine translation. EV evaluates candidate canvases by mean predictive entropy from all‑mask forward passes, choosing the length the model is best prepared to fill. Compared to a baseline that uses training‑corpus length statistics, EV recovers a substantial portion of the COMET‑22 gain across En→Zh, Zh→En, and En→De, and expert evaluation confirms adequacy improvements, especially for Zh→En.
By Yan Zhan, Mengkai Hou, Wanting Zhang, Zhijun Gao
arXiv:2608.22316v1 Announce Type: cross
Abstract: Whether an intermediate stage of modern Arabic handwriting helps or hurts historical Arabic HTR is usually decided from one implementation and one co...
By Sumaih Almarshad, Maram Alamri, Dona Aloraini, Fares Altuwaim, AlJawharh AlOtaibi, Reem Alyabis, Rayah Aldawsari
The paper introduces a framework to tackle modality imbalance in multimodal learning by focusing on sample-level variations. It defines a Modality Gap metric to measure prediction discrepancies, models the resulting bimodal distribution with a Gaussian Mixture Model, and uses Bayesian probabilities for soft separation of balanced and imbalanced samples. A two‑stage training process—Warm‑up and Adaptive Training—reallocates loss weights based on the GMM, strengthening alignment for imbalanced samples while favoring fusion for balanced ones, and shows superior performance over existing baselines.
By Zhiwen Yu, Zhaocheng Liu, Xiaoqing Liu, Huanqiang Zeng, C. L. Philip Chen
arXiv:2508.02609v3 Announce Type: replace-cross
Abstract: Graph Neural Networks (GNN) have been extensively applied to industry recommendation systems, as seen in models like GraphSage\cite{GraphSage...
By Jiayin Jin, Erika Sun, Zhimeng Pan, Yang Tang, Jiarui Feng, Kungang Li, Chongyuan Xiang, Jiacheng Li, Runze Su, Siping Ji, Han Sun, Ling Leng, Prathibha Deshikachar
arXiv:2608.23241v1 Announce Type: cross
Abstract: Identifying and classifying environmental mitigation obligations in Federal Energy Regulatory Commission hydropower licensing documents is a labor-in...
By Hong-Jun Yoon, Tom Ruggles, Joanna Lee, Debjani Singh
AI University (AI‑U) is a flexible framework that uses a fine‑tuned large language model (LLM) combined with retrieval‑augmented generation (RAG) and a reasoning synthesis model to produce style‑aligned responses from lecture videos, notes, and textbooks. In a graduate‑level finite‑element‑method (FEM) course, the authors created a pipeline to generate course‑grounded training data, fine‑tuned an open‑source LLM with Low‑Rank Adaptation (LoRA), and applied RAG‑based synthesis. Evaluation through cosine similarity, LLM‑based assessment, expert review, and user studies showed that the expert model outperformed the base model in alignment with course materials, with 86 % of test cases scoring higher and human users preferring the expert model roughly twice as often.
whyItMatters":"The study demonstrates a practical method for building course‑specific learning assistants that improve alignment with instructional content, offering a template that can be extended across STEM fields."
By Mostafa Faghih Shojaei, Rahul Gulati, Benjamin A. Jasperson, Shangshang Wang, Simone Cimolato, Manas Vardhan, Dangli Cao, Willie Neiswanger, Krishna Garikipati
arXiv:2608.21372v1 Announce Type: new
Abstract: This report summarizes the work conducted on the Game of Hidden Rules (GOHR), focusing on reinforcement learning agents trained to infer hidden rules f...
By Christo Mathew, Wentian Wang, Jacob Feldman, Lazaros K. Gallos, Paul B. Kantor, Vladimir Menkov, Hao Wang
arXiv:2608.21761v1 Announce Type: new
Abstract: Large collections of street-view imagery provide rich visual information about urban environments, but extracting fine-grained geographic information f...
By Changyu Lee, Yeonsoo Park, Abdullah Alfarrarjeh, Seon Ho Kim
The paper introduces ADN‑Agent, an architecture that uses a large language model to orchestrate multiple domain‑specific models (DSMs) for active distribution network (ADN) management. It features adaptive intent recognition, task decomposition, and a unified communication interface for heterogeneous DSMs, along with a pipeline for fine‑tuning small language models on language‑intensive subtasks. Experiments show ADN‑Agent outperforms existing LLM application paradigms in coordinating DSMs for complex ADN operations.
By Xu Yang, Chenhui Lin, Haotian Liu, Qi Wang, Yue Yang, Wenchuan Wu
arXiv:2608.22797v1 Announce Type: new
Abstract: Background This study was designed to evaluate whether a domain-specific large language model (LLM) trained exclusively on patient education resources...
By Alexander J. Hish, Arjun Nagendran, Scott N. Compton
arXiv:2608.23256v1 Announce Type: new
Abstract: Recent work proposes next-chunk reasoning RL for leveraging no-CoT data---corpora such as worked solutions and textbook derivations that contain reason...
By Yinhao Tang, Youqing Fang, Yanan Sun, Jiangning Liu, Ziyi Wang, Xun Zhao, Weiming Zhang, Bin Liu, Kuikun Liu, Wenwei Zhang, Kai Chen
arXiv:2608.23373v1 Announce Type: new
Abstract: Forecasting long-range influenza-like illness (ILI) matters for public health readiness. Publicly available surveillance datasets typically pair numeri...
By Seyed Mohammad Hossein Hashemi, Mohsen Hooshmand, Parvin Razzaghi
arXiv:2608.23475v1 Announce Type: new
Abstract: As large language models are increasingly used in data-scarce and evolving task scenarios, few-shot in-context learning (ICL) has become a key paradigm...
By Jinghan Tan, Yuanzheng Wang, Lu Chen, Zijun Chen, Yuqian Wang, Maosong Sun
arXiv:2608.22215v1 Announce Type: new
Abstract: Large language model (LLM) agents operate in dynamic environments where knowledge continuously evolves. Existing memory systems typically treat externa...
By Wenzhi Li, Dong Nie, Rui Lan, Tongtong Lyu, Peiyao Wang, Lingzi Hong, Weihang Pan, Boyuan Pan, Yao Hu
arXiv:2608.23493v1 Announce Type: new
Abstract: Self-reflection is a powerful mechanism for credit assignment in human learning, converting sparse outcome feedback into actionable guidance. However,...
By Jialong Liu, Yuling Shi, Ning Yang, Xiaodong Gu, Zuchao Li