PrivacyAlign: Contextual Privacy Alignment for LLM Agents Paper • 2606.21710 • Published 15 days ago • 3
FaithBench: A Diverse Hallucination Benchmark for Summarization by Modern LLMs Paper • 2410.13210 • Published Oct 17, 2024
Conventional Contrastive Learning Often Falls Short: Improving Dense Retrieval with Cross-Encoder Listwise Distillation and Synthetic Data Paper • 2505.19274 • Published May 25, 2025
Unifying Adversarial Robustness and Training Across Text Scoring Models Paper • 2602.00857 • Published Jan 31
PrivacyAlign: Contextual Privacy Alignment for LLM Agents Paper • 2606.21710 • Published 15 days ago • 3
Rethinking Agentic Search with Pi-Serini: Is Lexical Retrieval Sufficient? Paper • 2605.10848 • Published May 11 • 5
Injecting Domain Adaptation with Learning-to-hash for Effective and Efficient Zero-shot Dense Retrieval Paper • 2205.11498 • Published May 23, 2022
ORBIT: Scalable and Verifiable Data Generation for Search Agents on a Tight Budget Paper • 2604.01195 • Published Apr 1 • 4
Don't "Overthink" Passage Reranking: Is Reasoning Truly Necessary? Paper • 2505.16886 • Published May 22, 2025 • 6