TAC-CoT: Tool-Empowered Implicit Chain-of-Thought via Interleaving Explicit Tokens Paper • 2611.01926 • Published 17 days ago • 17
Don't Scroll Back: Missing-Evidence Memory for Streaming Dialogue Summarization Paper • 2608.09043 • Published Aug 10 • 6
Towards a Holistic and Automated Evaluation Framework for Multi-Level Comprehension of LLMs in Book-Length Contexts Paper • 2508.19578 • Published Aug 27, 2025
Towards Multi-dimensional Evaluation of LLM Summarization across Domains and Languages Paper • 2506.00549 • Published May 31, 2025
Completing Missing Annotation: Multi-Agent Debate for Accurate and Scalable Relevant Assessment for IR Benchmarks Paper • 2602.06526 • Published Feb 6
Don't Scroll Back: Missing-Evidence Memory for Streaming Dialogue Summarization Paper • 2608.09043 • Published Aug 10 • 6
UniSumEval: Towards Unified, Fine-Grained, Multi-Dimensional Summarization Evaluation for LLMs Paper • 2409.19898 • Published Sep 30, 2024 • 1
Rethinking RAG in Long Videos: What to Retrieve and How to Use It? Paper • 2606.13141 • Published Jun 11 • 35
Towards Multi-dimensional Evaluation of LLM Summarization across Domains and Languages Paper • 2506.00549 • Published May 31, 2025
Towards a Holistic and Automated Evaluation Framework for Multi-Level Comprehension of LLMs in Book-Length Contexts Paper • 2508.19578 • Published Aug 27, 2025
Rethinking RAG in Long Videos: What to Retrieve and How to Use It? Paper • 2606.13141 • Published Jun 11 • 35
CARVE: Certified Affordable Repair of Vetoed Maneuvers via Envelopes for Interactive Driving Paper • 2606.02641 • Published May 31 • 1