Offline Reinforcement Learning for LLM Multi-Step Reasoning
Paper
•
2412.16145
•
Published
•
38
my-fav-papers
-
-
SPLADE-v3: New baselines for SPLADE
Paper • 2403.06789 • Published • 5 -
MMTEB: Massive Multilingual Text Embedding Benchmark
Paper • 2502.13595 • Published • 41 -
Reducing the Footprint of Multi-Vector Retrieval with Minimal Performance Impact via Token Pooling
Paper • 2409.14683 • Published • 12 -
Rank1: Test-Time Compute for Reranking in Information Retrieval
Paper • 2502.18418 • Published • 28 -
Rank-DistiLLM: Closing the Effectiveness Gap Between Cross-Encoders and LLMs for Passage Re-Ranking
Paper • 2405.07920 • Published • 3 -
Distillation and Refinement of Reasoning in Small Language Models for Document Re-ranking
Paper • 2504.03947 • Published • 4 -
DyVo: Dynamic Vocabularies for Learned Sparse Retrieval with Entities
Paper • 2410.07722 • Published • 15