Papers
Research papers from arXiv and related sources
Via Negativa for AI Alignment: Why Negative Constraints Are Structurally Superior to Positive Preferences
Recent empirical results have demonstrated that training large language models (LLMs) with negative-only feedback can match or exceed standard reinforcement learning from human feedback (RLHF). Neg...
Quan Cheng
IndexRAG: Bridging Facts for Cross-Document Reasoning at Index Time
Multi-hop question answering (QA) requires reasoning across multiple documents, yet existing retrieval-augmented generation (RAG) approaches address this either through graph-based methods requirin...
Zhenghua Bao, Yi Shi
Trained Persistent Memory for Frozen Encoder--Decoder LLMs: Six Architectural Methods
Frozen encoder--decoder language models are stateless: the latent representation is discarded after every forward pass, so no information persists across sessions. This paper presents a \textbf{pro...
Hong Jeong
RECOVER: Robust Entity Correction via agentic Orchestration of hypothesis Variants for Evidence-based Recovery
Entity recognition in Automatic Speech Recognition (ASR) is challenging for rare and domain-specific terms. In domains such as finance, medicine, and air traffic control, these errors are costly. I...
Abhishek Kumar, Aashraya Sachdeva
PlotTwist: A Creative Plot Generation Framework with Small Language Models
Creative plot generation presents a fundamental challenge for language models: transforming a concise premise into a coherent narrative that sustains global structure, character development, and em...
Abhinav Thorat, Ravi Kolla, Jyotin Goel, Niranjan Pedanekar
Who Benchmarks the Benchmarks? A Case Study of LLM Evaluation in Icelandic
This paper evaluates current Large Language Model (LLM) benchmarking for Icelandic, identifies problems, and calls for improved evaluation methods in low/medium-resource languages in particular. We...
Finnur Ágúst Ingimundarson, Steinunn Rut Friðriksdóttir, Bjarki Ármannsson, Iris Edda Nowenstein,...
Fanar 2.0: Arabic Generative AI Stack
We present Fanar 2.0, the second generation of Qatar's Arabic-centric Generative AI platform. Sovereignty is a first-class design principle: every component, from data pipelines to deployment infra...
FANAR TEAM, Ummar Abbas, Mohammad Shahmeer Ahmad, Minhaj Ahmad, Abdulaziz Al-Homaid, Anas Al-Nua...
Rotated Robustness: A Training-Free Defense against Bit-Flip Attacks on Large Language Models
Hardware faults, specifically bit-flips in quantized weights, pose a severe reliability threat to Large Language Models (LLMs), often triggering catastrophic model collapses. We demonstrate that th...
Deng Liu, Song Chen
InViC: Intent-aware Visual Cues for Medical Visual Question Answering
Medical visual question answering (Med-VQA) aims to answer clinically relevant questions grounded in medical images. However, existing multimodal large language models (MLLMs) often exhibit shortcu...
Zhisong Wang, Ziyang Chen, Zanting Ye, Hongze Zhu, Yefeng Zheng, Yong Xia
FactorEngine: A Program-level Knowledge-Infused Factor Mining Framework for Quantitative Investment
We study alpha factor mining, the automated discovery of predictive signals from noisy, non-stationary market data-under a practical requirement that mined factors be directly executable and audita...
Qinhong Lin, Ruitao Feng, Yinglun Feng, Zhenxin Huang, Yukun Chen, Zhongliang Yang, Linna Zhou, B...
One Kiss: Emojis as Agents of Genre Flux in Generative Comics
Generative AI has made visual storytelling widely accessible, yet current prompt-based interactions often force users into a trade-off between precise control and creative flow. We present One Kiss...
Xiruo Wang, Xinyi Jiang, Ziqi Lyu
Beyond Grading Accuracy: Exploring Alignment of TAs and LLMs
In this paper, we investigate the potential of open-source Large Language Models (LLMs) for grading Unified Modeling Language (UML) class diagrams. In contrast to existing work, which primarily eva...
Matthijs Jansen op de Haar, Nacir Bouali, Faizan Ahmed
Toward Experimentation-as-a-Service in 5G/6G: The Plaza6G Prototype for AI-Assisted Trials
This paper presents Plaza6G, the first operational Experiment-as-a-Service (ExaS) platform unifying cloud resources with next-generation wireless infrastructure. Developed at CTTC in Barcelona, Pla...
Sergio Barrachina-Muñoz, Marc Carrascosa-Zamacois, Horacio Bleda, Umair Riaz, Yasir Maqsood, Xavi...
PashtoCorp: A 1.25-Billion-Word Corpus, Evaluation Suite, and Reproducible Pipeline for Low-Resource Language Development
We present PashtoCorp, a 1.25-billion-word corpus for Pashto, a language spoken by 60 million people that remains severely underrepresented in NLP. The corpus is assembled from 39 sources spanning ...
Hanif Rahman
Automated identification of Ichneumonoidea wasps via YOLO-based deep learning: Integrating HiresCam for Explainable AI
Accurate taxonomic identification of parasitoid wasps within the superfamily Ichneumonoidea is essential for biodiversity assessment, ecological monitoring, and biological control programs. However...
Joao Manoel Herrera Pinheiro, Gabriela Do Nascimento Herrera, Alvaro Doria Dos Santos, Luciana Bu...
Prompts Blend Requirements and Solutions: From Intent to Implementation
AI coding assistants are reshaping software development by shifting focus from writing code to formulating prompts. In chat-focused approaches such as vibe coding, prompts become the primary arbite...
Shalini Chakraborty, Jan-Philipp Steghöfer
An Interpretable Machine Learning Framework for Non-Small Cell Lung Cancer Drug Response Analysis
Lung cancer is a condition where there is abnormal growth of malignant cells that spread in an uncontrollable fashion in the lungs. Some common treatment strategies are surgery, chemotherapy, and r...
Ann Rachel, Pranav M Pawar, Mithun Mukharjee, Raja M, Tojo Mathew
A Human-Centred Architecture for Large Language Models-Cognitive Assistants in Manufacturing within Quality Management Systems
Large Language Models-Cognitive Assistants (LLM-CAs) can enhance Quality Management Systems (QMS) in manufacturing, fostering continuous process improvement and knowledge management. However, there...
Marcos Galdino, Johanna Grahl, Tobias Hamann, Anas Abdelrazeq, Ingrid Isenhardt
Learning to Predict, Discover, and Reason in High-Dimensional Discrete Event Sequences
Electronic control units (ECUs) embedded within modern vehicles generate a large number of asynchronous events known as diagnostic trouble codes (DTCs). These discrete events form complex temporal ...
Hugo Math
Omnilingual MT: Machine Translation for 1,600 Languages
High-quality machine translation (MT) can scale to hundreds of languages, setting a high bar for multilingual systems. However, compared to the world's 7,000 languages, current systems still offer ...
Omnilingual MT Team, Belen Alastruey, Niyati Bafna, Andrea Caciolai, Kevin Heffernan, Artyom Koz...