BGE-large
PulseAugur coverage of BGE-large — every cluster mentioning BGE-large across labs, papers, and developer communities, ranked by signal.
1 day(s) with sentiment data
-
DualView framework enhances multi-hop QA with adaptive fusion
A research paper introduces DualView, a novel framework designed to improve multi-hop question answering by efficiently reranking documents. The system uses a dual-view approach, combining a local scorer for fine-graine…
-
New research explores full-duplex dialogue models, memory, and turn-taking
Researchers are developing new methods to improve full-duplex spoken dialogue models, which allow for simultaneous listening and speaking. One approach, PERSIST, introduces a memory system that tracks who said what and …
-
RAGFlip paper measures negative flips in retriever upgrades
A new research paper, RAGFlip, introduces a method for evaluating retriever upgrades by focusing on query-level negative flips. These flips occur when a new retriever fails to find a relevant passage that a previous ret…
-
DocuSearch system enhances enterprise search with hybrid RAG and KG expansion
A new research paper details DocuSearch, an enterprise document search system designed to improve accuracy and grounding for complex queries. DocuSearch integrates semantic search with BGE-Large embeddings, BM25 full-te…
-
New research reveals fundamental limits in RAG defenses against coordinated poisoning attacks
Researchers have demonstrated a fundamental limitation in current defenses against coordinated poisoning attacks on vector retrieval systems used in retrieval-augmented generation (RAG). These admission-time defenses, w…
-
RAG system debugging reveals noise, retrieval failures, and model knowledge leaks
A developer detailed a challenging debugging process involving a retrieval-augmented generation (RAG) system. Initially, the system appeared to regress in performance, but a meticulous byte-by-byte comparison of request…
-
New Credence framework enhances AI fact-checking with semantic metrics · 2 sources tracked
Researchers have introduced Credence, a new framework designed to improve the accuracy of automated fact-checking by decomposing complex sentences into atomic claims. This framework utilizes a novel Semantic-F1 metric, …
-
New framework reveals LLM memory asymmetry
Researchers have developed a new diagnostic framework to analyze user-side memory in large language models, revealing that personalization capabilities are not a single metric but rather factor into distinct axes: behav…
-
ConvMemory: Lightweight AI Memory Reranker Offers Cost-Effective Performance
A new research paper introduces ConvMemory, a lightweight 3.6M-parameter reranker designed for conversational long-term memory retrieval. The model demonstrates competitive performance against larger cross-encoders in t…