reciprocal rank fusion
PulseAugur coverage of reciprocal rank fusion — every cluster mentioning reciprocal rank fusion across labs, papers, and developer communities, ranked by signal.
9 day(s) with sentiment data
-
MolBioKG system grounds unregistered molecules in biomedical knowledge graphs
Researchers have developed MolBioKG, a novel two-layer system designed to connect unregistered molecules to biomedical knowledge graphs. This system addresses the challenge of 'out-of-graph molecules' by using multi-res…
-
Hybrid Search Fuses BM25 and Dense Vectors for Improved Information Retrieval
A new approach to information retrieval combines lexical search (BM25) with dense vector search to overcome the limitations of each. BM25 excels at matching exact keywords and rare terms, while dense vectors capture sem…
-
BioASQ team enhances biomedical QA with novel reranking and recovery strategies
Researchers from the DS@GT ARC BioASQ team have developed a novel pipeline for biomedical question answering, enhancing performance on the BioASQ Task 14b. Their system integrates multi-source query expansion, a fine-tu…
-
New chunking methods boost RAG accuracy by respecting semantic and structural boundaries
Researchers are exploring advanced methods for document chunking to improve the effectiveness of retrieval-augmented generation (RAG) systems. One novel approach, Right Reset (RR), identifies semantic boundaries by anal…
-
LLM billing assistant struggles with number narration, not retrieval
A WhatsApp assistant for an internet service provider was developed to answer billing questions, but encountered issues not with retrieval accuracy, but with the language model misrepresenting correct numerical data. Th…
-
Developer details on-prem text-to-SQL agent to prevent LLM join errors
A developer detailed how they built an on-premises text-to-SQL agent to query a large 900-table database, overcoming challenges with local LLMs inventing incorrect joins. The solution separates table selection from join…
-
Octocode improves LLM code search by fusing reasoning with hybrid retrieval
Octocode, an open-source code search engine, initially saw performance degradation when integrating an LLM for reranking search results. The first attempt, which relied solely on the LLM to determine relevance, reduced …
-
New workflow optimizes customer-service LLM agents with evidence grounding
Researchers have developed an Evidence-Grounded Customer-Service Agent Workflow designed to improve the quality of responses from customer-service bots. This system ensures that large language models adhere to evidence …
-
BioASQ 2026 system uses GPT-5.5 and novel retrieval for medical QA
A research paper details a system designed for the BioASQ Task 14B 2026, focusing on retrieval and multi-model combination strategies. The system employs a hybrid retrieval pipeline incorporating dense models, BM25, and…
-
Hippo toolkit enables local hybrid search for LLMs, bypassing cloud APIs
A new open-source toolkit called Hippo has been developed to enable local, privacy-focused hybrid search for large language model (LLM) applications. Unlike traditional methods that rely on cloud-based embedding APIs an…
-
RAG evaluation metrics: Hit Rate and MRR improve search quality
This article details a method for evaluating Retrieval-Augmented Generation (RAG) systems using Hit Rate and Mean Reciprocal Rank (MRR) metrics. The author created a benchmark with 360 questions and 72 lesson pages, tes…
-
New research explores temporal retrieval for evolving scientific document collections
A new paper analyzes temporal retrieval for scientific document collections that grow over time, using the LongEval-Sci benchmark. The research found that temporal full-text retrieval methods, particularly those incorpo…
-
HAKARI-Bench offers lightweight evaluation for retrieval models · 2 sources tracked
Researchers have introduced HAKARI-Bench, a lightweight benchmark designed to streamline the evaluation of retrieval architectures and efficiency settings for retrieval-augmented generation and semantic search. This new…
-
Vortex system enhances video retrieval with multi-modal fusion · 1 source tracked
The Vortex system, developed by the FocusOnFun team for the Ho Chi Minh City AI Challenge 2025, enhances intelligent video retrieval through multi-modal fusion. It integrates adaptive keyframe extraction, vision-languag…
-
RAG-Fusion enhances LLM retrieval by fusing multiple query ranks
RAG-Fusion is a technique designed to improve the accuracy of retrieval-augmented generation (RAG) systems by addressing the limitations of single-query phrasing. It involves having a large language model generate multi…
-
New RAG framework automates maritime accident root cause analysis
Researchers have developed a novel retrieval-augmented generation (RAG) framework designed to automate the root cause analysis (RCA) of maritime accidents. This system utilizes a structured knowledge base derived from o…
-
Spring AI and Pgvector enable native hybrid search in PostgreSQL
This article details how to implement native hybrid search within PostgreSQL using the pgvector extension and Spring AI. It advocates for consolidating search functionalities into a single database, eliminating the need…
-
Hybrid search with RRF and LLM reranker improves RAG accuracy
This article details how dense retrieval methods in Retrieval-Augmented Generation (RAG) systems can fail to find relevant information, particularly for exact keywords or proper nouns. It proposes a hybrid search approa…
-
RAG pipelines need more than embeddings for peak accuracy
To enhance the accuracy of Retrieval Augmented Generation (RAG) pipelines, relying solely on embeddings is insufficient. Developers should incorporate BM25, fuse it with Reciprocal Rank Fusion (RRF), and consider adding…
-
RAG pipeline struggles with citations, developer proposes fix
A developer detailed a sophisticated Parent-Child RAG pipeline on GitHub, which, despite its advanced components like hybrid vector stores and LangGraph, suffered from inaccurate citations and hallucinations. The core i…