FECT: Factuality Evaluation of Interpretive AI-Generated Claims in Contact Center Conversation Transcripts
arXiv:2508.00889v1 Announce Type: new Abstract: Large language models (LLMs) are known to hallucinate, producing natural language outputs that are not ...
Read more
A Reasoning-Enhanced LLM Agent for Automotive Software Release Analytics
[Submitted on 27 Mar 2025 (v1), last revised 1 Aug 2025 (this version, v2)] View a PDF of the paper ...
Read more
Activation-Guided Local Editing for Jailbreaking Attacks
arXiv:2508.00555v1 Announce Type: cross Abstract: Jailbreaking is an essential adversarial technique for red-teaming these models to uncover and patch security ...
Read more
A Dataset for Mistake Action Detection from Egocentric Videos referring to Procedural Texts
[Submitted on 7 Oct 2024 (v1), last revised 31 Jul 2025 (this version, v3)] View a PDF of the paper ...
Read more
A Pre-trained Model for Document Understanding with Relative Polar Coordinate Encoding of Layout Structures
[Submitted on 11 Jul 2025 (v1), last revised 31 Jul 2025 (this version, v3)] View a PDF of the paper ...
Read more
A Generative Framework Using LLMs
[Submitted on 13 Dec 2024 (v1), last revised 29 Jul 2025 (this version, v3)] View a PDF of the paper ...
Read more
A Survey of Tasks, Datasets, Models, and Challenges
[Submitted on 25 Oct 2024 (v1), last revised 30 Jul 2025 (this version, v3)] View a PDF of the paper ...
Read more
Navigating Ideologies of Large Language Models
[Submitted on 24 Jun 2025 (v1), last revised 29 Jul 2025 (this version, v2)] View a PDF of the paper ...
Read more
Dissecting Persona-Driven Reasoning in Language Models via Activation Patching
arXiv:2507.20936v1 Announce Type: cross Abstract: Large language models (LLMs) exhibit remarkable versatility in adopting diverse personas. In this study, we ...
Read more
Unveiling the reasoning behaviour of medical Large Language Models
[Submitted on 20 Dec 2024 (v1), last revised 28 Jul 2025 (this version, v2)] View a PDF of the paper ...
Read more
