AI Briefing#information-retrieval
The latest AI and developer news about #information-retrieval, with the original source and a short summary.
The latest AI and developer news about #information-retrieval, with the original source and a short summary.
The framework achieves a KL divergence of 1.01 against real user queries, a 9.2x improvement over previous baselines.
Cohere has introduced Rubric-Calibrated Preferences nDCG@10 (RCP-nDCG@10), a new evaluation methodology that uses a calibrated AI judge to assess retrieval relevance, addressing coverage gaps in traditional nDCG benchmarks.
Q2D-Web has released a large-scale web search retriever evaluation benchmark featuring 190 million documents and 10 languages.
A method using Synthetic Query Probing has been proposed to compare similarity scores and search thresholds across embedding models.
DeepAmbigQA combines ambiguity and multi-hop reasoning to evaluate the answer completeness of LLMs.
An open-source embedding leaderboard has launched, enabling objective comparison of Korean RAG and retrieval performance.
This introduces PromptRank, a technique that uses LLMs to find efficient document paths for complex Multi-hop Question Answering (MQA).
PromptRank is a technique that combines unsupervised retrieval with an LLM reranker to improve data efficiency in multi-hop question answering.
Apple Music has introduced a semantic retrieval system based on a Siamese bi-encoder to improve multilingual search quality.
Introduces a technique that uses asymmetric quantization to dramatically lower the storage cost of Late Interaction models while preserving retrieval quality.
A new high-performance Reranker model with a novel architecture that separates query and passage computation to improve computational efficiency has been released.
The study demonstrated that in agent-based search, Grep-style keyword search can show higher accuracy than vector search.
Hugging Face released 6 Ettin-based rerankers along with the training recipe.
Ramp made Fast Ask faster and more accurate through Prime-RL post-training.
This compares ChatGPT's search and deep research features and explains how to use each.
This explains how to combine Embedding and Reranker to improve the precision of a search system.
Cohere introduces how Rerank fine-tuning improves search relevance in complex domains.