Papers
Research papers from arXiv and related sources
nchellwig at SemEval-2026 Task 3: Self-Consistent Structured Generation (SCSG) for Dimensional Aspect-Based Sentiment Analysis using Large Language Models
We present Self-Consistent Structured Generation (SCSG) for Dimensional Aspect-Based Sentiment Analysis in SemEval-2026 Task 3 (Track A). SCSG enhances prediction reliability by executing a LoRA-ad...
Nils Constantin Hellwig, Jakob Fehle, Udo Kruschwitz, Christian Wolff
Information and communications technologies for carbon sinks from economics and engineering perspectives
Climate change has intensified the urgency of effective carbon sink solutions, yet the integration of Information and Communications Technologies (ICT) in these systems remains fragmented despite i...
Yuze Dong, Jinsong Wu
Co-Evolutionary Multi-Modal Alignment via Structured Adversarial Evolution
Adversarial behavior plays a central role in aligning large language models with human values. However, existing alignment methods largely rely on static adversarial settings, which fundamentally l...
Guoxin Shi, Haoyu Wang, Zaihui Yang, Yuxing Wang, Yongzhe Chang
LLM-as-an-Annotator: Training Lightweight Models with LLM-Annotated Examples for Aspect Sentiment Tuple Prediction
Training models for Aspect-Based Sentiment Analysis (ABSA) tasks requires manually annotated data, which is expensive and time-consuming to obtain. This paper introduces LA-ABSA, a novel approach t...
Nils Constantin Hellwig, Jakob Fehle, Udo Kruschwitz, Christian Wolff
Search for the charmonium weak decay $ψ(2S)\to D_s^-π^+ + c.c.$ and $ψ(2S)\to D_s^-ρ^+ + c.c.$
We search for the weak decays $ψ(2S)\to D_s^-π^+ + c.c.$ and $ψ(2S)\to D_s^-ρ^+ + c.c.$ for the first time. The search is based on $(2712.4\pm14.3)\times 10^6$ events containing the charmonium stat...
BESIII Collaboration, M. Ablikim, M. N. Achasov, P. Adlarson, X. C. Ai, C. S. Akondi, R. Alibert...
FreeAct: Freeing Activations for LLM Quantization
Quantization is pivotal for mitigating the significant memory and computational overhead of Large Language Models (LLMs). While emerging transformation-based methods have successfully enhanced quan...
Xiaohao Liu, Xiaobo Xia, Manyi Zhang, Ji-Fu Li, Xianzhi Yu, Fei Shen, Xiu Su, See-Kiong Ng, Tat-S...
Beyond the Resumé: A Rubric-Aware Automatic Interview System for Information Elicitation
Effective hiring is integral to the success of an organisation, but it is very challenging to find the most suitable candidates because expert evaluation (e.g.\ interviews conducted by a technical ...
Harry Stuart, Masahiro Kaneko, Timothy Baldwin
AnnoABSA: A Web-Based Annotation Tool for Aspect-Based Sentiment Analysis with Retrieval-Augmented Suggestions
We introduce AnnoABSA, the first web-based annotation tool to support the full spectrum of Aspect-Based Sentiment Analysis (ABSA) tasks. The tool is highly customizable, enabling flexible configura...
Nils Constantin Hellwig, Jakob Fehle, Udo Kruschwitz, Christian Wolff
CHLU: The Causal Hamiltonian Learning Unit as a Symplectic Primitive for Deep Learning
Current deep learning primitives dealing with temporal dynamics suffer from a fundamental dichotomy: they are either discrete and unstable (LSTMs) \citep{pascanu_difficulty_2013}, leading to explod...
Pratik Jawahar, Maurizio Pierini
Efficient Test-Time Optimization for Depth Completion via Low-Rank Decoder Adaptation
Zero-shot depth completion has gained attention for its ability to generalize across environments without sensor-specific datasets or retraining. However, most existing approaches rely on diffusion...
Minseok Seo, Wonjun Lee, Jaehyuk Jang, Changick Kim
Federated Agentic AI for Wireless Networks: Fundamentals, Approaches, and Applications
Agentic artificial intelligence (AI) presents a promising pathway toward realizing autonomous and self-improving wireless network services. However, resource-constrained, widely distributed, and da...
Lingyi Cai, Yu Zhang, Ruichen Zhang, Yinqiu Liu, Tao Jiang, Dusit Niyato, Wei Ni, Abbas Jamalipour
Bootstrapping Embeddings for Low Resource Languages
Embedding models are crucial to modern NLP. However, the creation of the most effective models relies on carefully constructed supervised finetuning data. For high resource languages, such as Engli...
Merve Basoz, Andrew Horne, Mattia Opper
Solving Inverse PDE Problems using Minimization Methods and AI
Many physical and engineering systems require solving direct problems to predict behavior and inverse problems to determine unknown parameters from measurement. In this work, we study both aspects ...
Noura Helwani, Sophie Moufawad, Georges Sakr
Learning Domain-Aware Task Prompt Representations for Multi-Domain All-in-One Image Restoration
Recently, significant breakthroughs have been made in all-in-one image restoration (AiOIR), which can handle multiple restoration tasks with a single model. However, existing methods typically focu...
Guanglu Dong, Chunlei Li, Chao Ren, Jingliang Hu, Yilei Shi, Xiao Xiang Zhu, Lichao Mou
GMP: A Benchmark for Content Moderation under Co-occurring Violations and Dynamic Rules
Online content moderation is essential for maintaining a healthy digital environment, and reliance on AI for this task continues to grow. Consider a user comment using national stereotypes to insul...
Houde Dong, Yifei She, Kai Ye, Liangcai Su, Chenxiong Qian, Jie Hao
Changes in Manuscript Length, Research Team Size, and International Collaboration in the Post-2022 Period: Evidence from PLOS ONE
Large language models (LLMs) have diffused rapidly into academic writing since late 2022. Using the complete population of 109,393 research articles published in \textit{PLOS ONE} between 2019 and ...
Yossi Ben-Zion, Eden Cohen, Nitza Davidovitch
FT-Dojo: Towards Autonomous LLM Fine-Tuning with Language Agents
Fine-tuning large language models for vertical domains remains a labor-intensive and expensive process, requiring domain experts to curate data, configure training, and iteratively diagnose model b...
Qizheng Li, Yifei Zhang, Xiao Yang, Xu Yang, Zhuo Wang, Weiqing Liu, Jiang Bian
Legal RAG Bench: an end-to-end benchmark for legal RAG
We introduce Legal RAG Bench, a benchmark and evaluation methodology for assessing the end-to-end performance of legal RAG systems. As a benchmark, Legal RAG Bench consists of 4,876 passages from t...
Abdur-Rahman Butler, Umar Butler
Reasoning as Gradient: Scaling MLE Agents Beyond Tree Search
LLM-based agents for machine learning engineering (MLE) predominantly rely on tree search, a form of gradient-free optimization that uses scalar validation scores to rank candidates. As LLM reasoni...
Yifei Zhang, Xu Yang, Xiao Yang, Bowen Xian, Qizheng Li, Shikai Fang, Jingyuan Li, Jian Wang, Min...
Building a Strong Instruction Language Model for a Less-Resourced Language
Large language models (LLMs) have become an essential tool for natural language processing and artificial intelligence in general. Current open-source models are primarily trained on English texts,...
Domen Vreš, Tjaša Arčon, Timotej Petrič, Dario Vajda, Marko Robnik-Šikonja, Iztok Lebar Bajec