Cross-Layer Attention Probing for Fine-Grained Hallucination Detection

[ad_1] arXiv:2509.09700v1 Announce Type: new Abstract: With the large-scale adoption of Large Language Models (LLMs) in various applications, there is ...
Read more
[2509.09722] Improving MLLM Historical Record Extraction with Test-Time Image

[ad_1] arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both ...
Read more
SimpleVLA-RL: Scaling VLA Training via Reinforcement Learning

[ad_1] arXiv:2509.09674v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) models have recently emerged as a powerful paradigm for robotic manipulation. Despite ...
Read more
A Robust Sentence-Level Similarity-Based Watermarking Algorithm for Large Language Models

[ad_1] [Submitted on 5 Feb 2025 (v1), last revised 11 Sep 2025 (this version, v2)] View a PDF of the ...
Read more
Inversion Learning for Highly Effective NLG Evaluation Prompts

[ad_1] [Submitted on 29 Apr 2025 (v1), last revised 10 Sep 2025 (this version, v3)] View a PDF of the ...
Read more
A Knowledge-Intensive Dataset for Paired and Interleaved Multimodal Documents

[ad_1] [Submitted on 20 Jun 2024 (v1), last revised 9 Sep 2025 (this version, v3)] Authors:Junjie Wang, Yuxiang Zhang, Minghao ...
Read more
The ML-SUPERB 2.0 Challenge: Towards Inclusive ASR Benchmarking for All Language Varieties

[ad_1] arXiv:2509.07139v1 Announce Type: new Abstract: Recent improvements in multilingual ASR have not been equally distributed across languages and language ...
Read more
LLMs Can be Good Tutors in English Education

[ad_1] [Submitted on 8 Feb 2025 (v1), last revised 6 Sep 2025 (this version, v2)] Authors:Jingheng Ye, Shen Wang, Deqing ...
Read more
A Scalable Approach Guided by Domain Expertise

[ad_1] [Submitted on 17 Dec 2024 (v1), last revised 8 Sep 2025 (this version, v3)] Authors:Hanyin Wang, Chufan Gao, Qiping ...
Read more
A High-Quality and Diverse Dataset for Classical Arabic to English Translation

[ad_1] [Submitted on 29 Jul 2024 (v1), last revised 4 Sep 2025 (this version, v2)] View a PDF of the ...
Read more









