Research

Papers

Research papers from arXiv and related sources

Total: 4513 AI/LLM: 2483 Testing: 2030
AI LLM

DaPT: A Dual-Path Framework for Multilingual Multi-hop Question Answering

Retrieval-augmented generation (RAG) systems have made significant progress in solving complex multi-hop question answering (QA) tasks in the English scenario. However, RAG systems inevitably face ...

Yilin Wang, Yuchun Fan, Jiaoyang Li, Ziming Zhu, Yongyu Mu, Qiaozhi He, Tong Xiao, Jingbo Zhu

2603.19097 2026-03-19
AI LLM

Follow the Rules (or Not): Community Norms and AI-Generated Support in Online Health Communities

Generative AI (GenAI) is increasingly being integrated into the online ecosystem, including online health communities (OHCs), where people with diverse health conditions exchange social support. Fo...

Shravika Mittal, Erin Kasson, Layna Paraboschi, Eleanor Laufenberg, Jiawei Zhou, Patricia A. Cava...

2603.19093 2026-03-19
AI LLM

Serendipity by Design: Evaluating the Impact of Cross-domain Mappings on Human and LLM Creativity

Are large language models (LLMs) creative in the same way humans are, and can the same interventions increase creativity in both? We evaluate a promising but largely untested intervention for creat...

Qiawen Ella Liu, Marina Dubova, Henry Conklin, Takumi Harada, Thomas L. Griffiths

2603.19087 2026-03-19
AI LLM

A Dataset and Resources for Identifying Patient Health Literacy Information from Clinical Notes

Health literacy is a critical determinant of patient outcomes, yet current screening tools are not always feasible and differ considerably in the number of items, question format, and dimensions of...

Madeline Bittner, Dina Demner-Fushman, Yasmeen Shabazz, Davis Bartels, Dukyong Yoon, Brad Quitada...

2603.19082 2026-03-19
AI LLM

Parallelograms Strike Back: LLMs Generate Better Analogies than People

Four-term word analogies (A:B::C:D) are classically modeled geometrically as ''parallelograms,'' yet recent work suggests this model poorly captures how humans produce analogies, with simple local-...

Qiawen Ella Liu, Raja Marjieh, Jian-Qiao Zhu, Adele E. Goldberg, Thomas L. Griffiths

2603.19066 2026-03-19
AI LLM

SignAgent: Agentic LLMs for Linguistically-Grounded Sign Language Annotation and Dataset Curation

This paper introduces SignAgent, a novel agentic framework that utilises Large Language Models (LLMs) for scalable, linguistically-grounded Sign Language (SL) annotation and dataset curation. Tradi...

Oliver Cory, Ozge Mercanoglu Sincan, Richard Bowden

2603.19059 2026-03-19
AI LLM

Mitigating the Bandwidth Wall via Data-Streaming System-Accelerator Co-Design

Transformers have revolutionized AI in natural language processing and computer vision, but their large computation and memory demands pose major challenges for hardware acceleration. In practice, ...

Qunyou Liu, Marina Zapater, David Atienza

2603.19057 2026-03-19
AI LLM

The Simplicity of the Hodge Bundle

This paper shows that the Hodge bundle over the moduli space of genus $g \geq 2$ curves does not contain any non-trivial sub-bundles. Notably, the mathematical content was generated by Aletheia, a ...

Anand Patel

2603.19052 2026-03-19
AI LLM

MoRI: Learning Motivation-Grounded Reasoning for Scientific Ideation in Large Language Models

Scientific ideation aims to propose novel solutions within a given scientific context. Existing LLM-based agentic approaches emulate human research workflows, yet inadequately model scientific reas...

Chenyang Gu, Jiahao Cheng, Meicong Zhang, Pujun Zheng, Jinquan Zheng, Guoxiu He

2603.19044 2026-03-19
AI LLM

Man and machine: artificial intelligence and judicial decision making

The integration of artificial intelligence (AI) technologies into judicial decision-making - particularly in pretrial, sentencing, and parole contexts - has generated substantial concerns about tra...

Arthur Dyevre, Ahmad Shahvaroughi

2603.19042 2026-03-19
AI LLM

LLMs Aren't Human: A Critical Perspective on LLM Personality

A growing body of research examines personality traits in Large Language Models (LLMs), particularly in human-agent collaboration. Prior work has frequently applied the Big Five inventory to assess...

Kim Zierahn, Cristina Cachero, Anna Korhonen, Nuria Oliver

2603.19030 2026-03-19
AI LLM

SEM: Sparse Embedding Modulation for Post-Hoc Debiasing of Vision-Language Models

Models that bridge vision and language, such as CLIP, are key components of multimodal AI, yet their large-scale, uncurated training data introduce severe social and spurious biases. Existing post-...

Quentin Guimard, Federico Bartsch, Simone Caldarella, Rahaf Aljundi, Elisa Ricci, Massimiliano Ma...

2603.19028 2026-03-19
AI LLM

Rethinking MLLM Itself as a Segmenter with a Single Segmentation Token

Recent segmentation methods leveraging Multi-modal Large Language Models (MLLMs) have shown reliable object-level segmentation and enhanced spatial perception. However, almost all previous methods ...

Anqi Zhang, Xiaokang Ji, Guangyu Gao, Jianbo Jiao, Chi Harold Liu, Yunchao Wei

2603.19026 2026-03-19
AI LLM

Towards Verifiable AI with Lightweight Cryptographic Proofs of Inference

When large AI models are deployed as cloud-based services, clients have no guarantee that responses are correct or were produced by the intended model. Rerunning inference locally is infeasible for...

Pranay Anchuri, Matteo Campanelli, Paul Cesaretti, Rosario Gennaro, Tushar M. Jois, Hasan S. Kaym...

2603.19025 2026-03-19
AI LLM

Behavioral Fingerprints for LLM Endpoint Stability and Identity

The consistency of AI-native applications depends on the behavioral consistency of the model endpoints that power them. Traditional reliability metrics such as uptime, latency and throughput do not...

Jonah Leshin, Manish Shah, Ian Timmis, Daniel Kang

2603.19022 2026-03-19
AI LLM

What Really Controls Temporal Reasoning in Large Language Models: Tokenisation or Representation of Time?

We present MultiTempBench, a multilingual temporal reasoning benchmark spanning three tasks, date arithmetic, time zone conversion, and temporal relation extraction across five languages (English, ...

Gagan Bhatia, Ahmad Muhammad Isa, Maxime Peyrard, Wei Zhao

2603.19017 2026-03-19
AI LLM

Generalized Hand-Object Pose Estimation with Occlusion Awareness

Generalized 3D hand-object pose estimation from a single RGB image remains challenging due to the large variations in object appearances and interaction patterns, especially under heavy occlusion. ...

Hui Yang, Wei Sun, Jian Liu, Jian Xiao Tao Xie, Hossein Rahmani, Ajmal Saeed mian, Nicu Sebe, Gim...

2603.19013 2026-03-19
AI LLM

Security awareness in LLM agents: the NDAI zone case

NDAI zones let inventor and investor agents negotiate inside a Trusted Execution Environment (TEE) where any disclosed information is deleted if no deal is reached. This makes full IP disclosure th...

Enrico Bottazzi, Pia Park

2603.19011 2026-03-19
AI LLM

Hypothesis-Conditioned Query Rewriting for Decision-Useful Retrieval

Retrieval-Augmented Generation (RAG) improves Large Language Models (LLMs) by grounding generation in external, non-parametric knowledge. However, when a task requires choosing among competing opti...

Hangeol Chang, Changsun Lee, Seungjoon Rho, Junho Yeo, Jong Chul Ye

2603.19008 2026-03-19
AI LLM

AgentDS Technical Report: Benchmarking the Future of Human-AI Collaboration in Domain-Specific Data Science

Data science plays a critical role in transforming complex data into actionable insights across numerous domains. Recent developments in large language models (LLMs) and artificial intelligence (AI...

An Luo, Jin Du, Xun Xian, Robert Specht, Fangqiao Tian, Ganghua Wang, Xuan Bi, Charles Fleming, A...

2603.19005 2026-03-19