Exploring Knowledge Integration and Controllable Generation
[Submitted on 26 May 2025 (v1), last revised 27 Oct 2025 (this version, v3)] View a PDF of the paper ...
Read more
Eliciting the Agent to Deeply Think within the Response
[Submitted on 21 Oct 2025 (v1), last revised 24 Oct 2025 (this version, v2)] View a PDF of the paper ...
Read more
[2509.21798] Evaluating and Improving Cultural Awareness of Reward Models for LLM Alignment
[Submitted on 26 Sep 2025 (v1), last revised 24 Oct 2025 (this version, v2)] View a PDF of the paper ...
Read more
[2506.05735] Do LLMs Really Forget? Evaluating Unlearning with Knowledge Correlation and Confidence Awareness
[Submitted on 6 Jun 2025 (v1), last revised 22 Oct 2025 (this version, v4)] Authors:Rongzhe Wei, Peizhi Niu, Hans Hao-Hsun ...
Read more
Integrating Causal Graphs into Retrieval-Augmented Generation
[Submitted on 25 Mar 2025 (v1), last revised 21 Oct 2025 (this version, v3)] View a PDF of the paper ...
Read more
A Large-Scale and Multigenre Benchmark Dataset for Arabic LLM-Generated Text Detection
[Submitted on 3 Oct 2025 (v1), last revised 21 Oct 2025 (this version, v2)] View a PDF of the paper ...
Read more
Reasoning Refinement for Efficient and Effective Test-time Scaling
[Submitted on 25 May 2025 (v1), last revised 21 Oct 2025 (this version, v2)] View a PDF of the paper ...
Read more
[2509.04501] Understanding Reinforcement Learning for Model Training, and future directions with GRAPE
[Submitted on 2 Sep 2025 (v1), last revised 21 Oct 2025 (this version, v2)] View a PDF of the paper ...
Read more
Benchmarking Super Heros in Role-Playing Across Multiversal Contexts
[Submitted on 16 Oct 2025 (v1), last revised 18 Oct 2025 (this version, v2)] View a PDF of the paper ...
Read more
[2509.20859] Concise and Sufficient Sub-Sentence Citations for Retrieval-Augmented Generation
[Submitted on 25 Sep 2025 (v1), last revised 18 Oct 2025 (this version, v2)] View a PDF of the paper ...
Read more
