Academic

Academic

Academic · 1 min

*-PLUIE: Personalisable metric with Llm Used for Improved Evaluation

arXiv:2602.15778v1 Announce Type: new Abstract: Evaluating the quality of automatically generated text often relies on LLM-as-a-judge (LLM-judge) methods. While effective, these approaches are computationally expensive …

Quentin Lemesle, L\'eane Jourdan, Daisy Munson, Pierre Alain, Jonathan Chevelu, Arnaud Delhay, Damien Lolive
62 views
Academic · 1 min

Avey-B

arXiv:2602.15814v1 Announce Type: new Abstract: Compact pretrained bidirectional encoders remain the backbone of industrial NLP under tight compute and memory budgets. Their effectiveness stems from …

Devang Acharya, Mohammad Hammoud
26 views
Academic · 1 min

Seeing to Generalize: How Visual Data Corrects Binding Shortcuts

arXiv:2602.15183v1 Announce Type: cross Abstract: Vision Language Models (VLMs) are designed to extend Large Language Models (LLMs) with visual capabilities, yet in this work we …

Nicolas Buzeta, Felipe del Rio, Cristian Hinostroza, Denis Parra, Hans Lobel, Rodrigo Toro Icarte
38 views
Academic · 1 min

Weight space Detection of Backdoors in LoRA Adapters

arXiv:2602.15195v1 Announce Type: cross Abstract: LoRA adapters let users fine-tune large language models (LLMs) efficiently. However, LoRA adapters are shared through open repositories like Hugging …

David Puertolas Merenciano, Ekaterina Vasyagina, Raghav Dixit, Kevin Zhu, Ruizhe Li, Javier Ferrando, Maheep Chaudhary
23 views
Academic · 1 min

Colosseum: Auditing Collusion in Cooperative Multi-Agent Systems

arXiv:2602.15198v1 Announce Type: cross Abstract: Multi-agent systems, where LLM agents communicate through free-form language, enable sophisticated coordination for solving complex cooperative tasks. This surfaces a …

Mason Nakamura, Abhinav Kumar, Saswat Das, Sahar Abdelnabi, Saaduddin Mahmud, Ferdinando Fioretto, Shlomo Zilberstein, Eugene Bagdasarian
37 views
Academic · 1 min

How to Train Your Long-Context Visual Document Model

arXiv:2602.15257v1 Announce Type: cross Abstract: We present the first comprehensive, large-scale study of training long-context vision language models up to 344K context, targeting long-document visual …

Austin Veselka
25 views
Academic · 1 min

The Information Geometry of Softmax: Probing and Steering

arXiv:2602.15293v1 Announce Type: cross Abstract: This paper concerns the question of how AI systems encode semantic structure into the geometric structure of their representation spaces. …

Kiho Park, Todd Nief, Yo Joong Choe, Victor Veitch
20 views