This paper presents an overview of the fourteenth edition of the BioASQ challenge, organized in the context of the Conference and Labs of the Evaluation Forum (CLEF) 2026. BioASQ is an international challenge series that supports progress in biomedical language processing tasks ranging from semantic indexing and inform...
Anastasios Nentidis, Georgios Katsimpras, Anastasia Krithara et al.· 0 citations
Hour-scale audio-visual question answering is constrained by a context dilemma: dense whole-recording encoding rapidly exhausts context limits, whereas uniform temporal compression severely dilutes fine-grained acoustic and visual evidence. We introduce LEAP, a framework where the model retrieves its own evidence witho...
Ju-Yi Lin, Zhi-Qiang Lao, Jia-Li Cui et al.· 0 citations
Role prompting elicits specialized behavior from large language models through an expert identity, offering a lightweight way to guide reasoning on demanding tasks. However, evaluating or distilling complete role-prompted answers can miss useful next-token preferences when the sampled solution remains incorrect. Transf...
Wei-Jie Ren, Yan-Wen Zhang, Hao Li et al.· 0 citations
We investigate the problem of role-capability leakage (RCL), in which a role-prompted reasoning model generates convincing in-role text while continuing to exhibit capabilities on benchmarks that exceed those implied by the assigned role. For example, when a model is prompted to assume the role of a kindergarten studen...
Pakhapoom Sarapat, Saksorn Ruangtanusak, Kunat Pipatanakul et al.· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
Pre-pretraining (PPT) on synthetic non-natural language data improves token efficiency during language model pre-training (PT). Prior work attributes this gain to a grammatical prior, i.e., a structural inductive bias learned during PPT that transfers to natural language grammar. However, PPT has only been tested on mo...
Atsuki Yamaguchi, Tatsuro Inaba, Joel Niklaus et al.· 0 citations
Lie detection probes aim to predict from a language model's internal states whether its output is truthful or dishonest. However, role-play complicates what"truth"means for an LLM: language models can adopt a wide range of personas that take very different claims to be true, including personas whose beliefs clearly con...
Maximilian von Klinski, S. Lapuschkin, Wojciech Samek et al.· 0 citations
Multimodal encoders such as CLIP underlie many downstream systems, but their web-scale training data embed harmful associations that safety alignment must suppress without unnecessarily changing benign representations. Because ethical and practical constraints prevent collecting real unsafe content at scale, existing d...
Tobia Poppi, Silvia Cappelletti, Samuele Poppi et al.· 0 citations
Multi-agent collaboration lets large language models (LLMs) improve question answering through deliberation and feedback. Yet shared discussion couples correction with exposure to the same mistakes, which can erode the diversity needed for voting. Self-consistency offers sampling diversity without feedback, while singl...
Weijie Ren, Yanwen Zhang, Hao Li et al.· 0 citations
Cross-lingual transfer describes how knowledge in a source language benefits a target language. Measuring it quantitatively requires broad multilingual pre-training, as prior work has done with cross-lingual transfer matrices. We ask whether transfer is predictable from freely available typological features, and whethe...
Dalton Raphael Harmsen, Swier Garst, Thomas van Osch et al.· 0 citations
As Large Language Model (LLM) agents are increasingly deployed in complex environments, multi-turn interaction attacks have become a significant security challenge. Existing detection methods typically rely on historical context. However, this retrospective logic struggles to identify deep malicious intents that are sp...
Ze-Zhong Wang, Xue-Yang Tang, Rui Lian et al.· 1 citation
Speech emotion recognition (SER) is the task of assigning emotion labels to utterances. Early systems relied on acoustic features, whereas recent approaches combine multiple modalities, most commonly speech and text. Still, performance remains poor on many datasets. Large language models (LLMs) have therefore attracted...
Argument Mining (AM) is a critical NLP task that remains significantly under-resourced in Arabic. This paper presents $\testtt{STAR-Ar}$, a BERT-BiLSTM-CRF architecture for argument discourse detection and classification, as our system for Daleel 2026, the inaugural Arabic argument mining shared task. The task requires...
Bhuvanesh Verma, Ali Abusaleh, Alexander Mehler· 0 citations
A new method, called CW-Net, translates the reasoning process of an autonomous vehicle’s AI system into understandable concepts that explain its behavior.
MIT News · Artificial Intelligence· news.mit.eduAug 31, 2026
With millions of users across the world, Julia has been used to conduct cutting-edge research and to design new drugs, jet engines, heat pumps, and more.
