conftrace_

long-context retrieval

7 papers

Explore in graph

Co-occurring keywords · papers mentioning both

large language model (4) information retrieval (2) multi-fact retrieval (1) iterative rewriting (1) context rewriting (1) iterative context rewriting (1) retrieval quality (1) pretraining data mixture (1) m2-bert (1) monarch mixer (1)

Papers

FACT: Examining the Effectiveness of Iterative Context Rewriting for Multi-fact Retrieval NAACL 2025 Length-Induced Embedding Collapse in PLM-based Models ACL 2025 Ref-Long: Benchmarking the Long-context Referencing Capability of Long-context Language Models ACL 2025 SEAL: Scaling to Emphasize Attention for Long-Context Retrieval ACL 2025 Training with “Paraphrasing the Original Text” Teaches LLM to Better Retrieve in Long-Context Tasks AAAI 2025 You Only Use Reactive Attention Slice When Retrieving From Long Context EMNLP 2025 Benchmarking and Building Long-Context Retrieval Models with LoCo and M2-BERT ICML 2024