Hugging Face Blog
Introducing RTEB: A New Standard for Retrieval Evaluation
Read the original on Hugging Face Blog →The Flow has not summarised this story yet — read it at Hugging Face Blog.
Related stories
arXiv AI
Aug 5
Search, Inspect, Fetch: Exploiting Boolean Retrieval for Deep-Research Agents
arXiv:2608. 02751v1 Announce Type: cross Abstract: Existing deep-research agents use a search-visit workflow that retrieves and reads whole pages, without considering the addressable structure that web sources expose through titles, headings, sections, and metadata.
arXiv AI
Jul 31
GuidedRAG: Semantic Steering of Retrieval-Augmented Generation
arXiv:2607. 26071v1 Announce Type: cross Abstract: In this work, we propose GuidedRAG, a novel extension to traditional Retrieval-Augmented Generation (RAG) that introduces a dedicated selection stage and semantic steering during retrieval.
arXiv AI
Jun 30
Sustainable Hybrid Document-Routed Retrieval for Financial RAG: Resolving the Robustness-Precision Trade-off
arXiv:2603. 26815v3 Announce Type: replace-cross Abstract: Retrieval-Augmented Generation (RAG) systems for financial document QA typically follow a chunk-based paradigm: documents are split into fragments, embedded, and retrieved by similarity.
arXiv AI
Jul 1
One Retrieval to Cover Them All: Co-occurrence-Aware Knowledge Base Reorganization for Session-Level RAG
arXiv:2606. 31156v1 Announce Type: cross Abstract: RAG systems retrieve documents optimized for answering one query at a time.
Hugging Face Trending Papers
Jul 21
PLAID-PRF: Pseudo-Relevance Feedback with Centroid-like Tokens in PLAID
Multi-vector dense retrieval models, such as ColBERT, achieve strong retrieval effectiveness by modelling fine-grained token-level interactions between queries and documents. Methods such as PLAID use centroid-based quantisation of each token's vector to reduce the index size and speed up retrieval while maintaining strong effectiveness.
arXiv Computation and Language
Sep 15
TF-IDF and BM25 Are Exact KL Divergences
arXiv:2609.14016v1 Announce Type: cross Abstract: TF-IDF and BM25 are two of the most widely used methods for scoring query-document relevance, yet neither has a standard probabilistic derivation tha...