Adaptive Attention Sparsity with Hierarchical Top-$p$ Pruning
[Submitted on 4 Feb 2025 (v1), last revised 6 Feb 2025 (this version, v2)] View a PDF of the paper ...
Read more A Fine-grained Metric for Video Question Answering Data Quality Evaluation
[Submitted on 11 Nov 2024 (v1), last revised 6 Feb 2025 (this version, v3)] View a PDF of the paper ...
Read more Combining Base and Instruction-Tuned Language Models for Better Synthetic Data Generation
[Submitted on 3 Feb 2025 (v1), last revised 5 Feb 2025 (this version, v2)] View a PDF of the paper ...
Read more Rule-Guided Retrieval-Augmented Generation with Language Models for Question Answering
[Submitted on 15 Oct 2024 (v1), last revised 5 Feb 2025 (this version, v2)] View a PDF of the paper ...
Read more An Integrated Toolkit for Evaluating Jailbreak Attempts Against Large Language Models
[Submitted on 13 Jun 2024 (v1), last revised 4 Feb 2025 (this version, v2)] View a PDF of the paper ...
Read more Exploring the Role of Punctuation in Semantic Processing
[Submitted on 10 Jan 2025 (v1), last revised 2 Feb 2025 (this version, v3)] View a PDF of the paper ...
Read more [2501.07927] Gandalf the Red: Adaptive Security for LLMs
[Submitted on 14 Jan 2025 (v1), last revised 2 Feb 2025 (this version, v2)] Authors:Niklas Pfister, Václav Volhejn, Manuel Knott, ...
Read more Language Bias in Self-Supervised Learning For Automatic Speech Recognition
arXiv:2501.19321v1 Announce Type: cross Abstract: Self-supervised learning (SSL) is used in deep learning to train on large datasets without the ...
Read more Representation Space Guided Reinforcement Learning for Interpretable LLM Jailbreaking
[Submitted on 28 Jan 2025 (v1), last revised 30 Jan 2025 (this version, v2)] View a PDF of the paper ...
Read more DFPE: A Diverse Fingerprint Ensemble for Enhancing LLM Performance
arXiv:2501.17479v1 Announce Type: cross Abstract: Large Language Models (LLMs) have shown remarkable capabilities across various natural language processing tasks but ...
Read more