2WikiMultiHopQA
PulseAugur coverage of 2WikiMultiHopQA — every cluster mentioning 2WikiMultiHopQA across labs, papers, and developer communities, ranked by signal.
8 day(s) with sentiment data
-
Lightfoot system streamlines GraphRAG with efficient document deletion
A new system called Lightfoot has been developed for graph-based retrieval-augmented generation (GraphRAG), specifically addressing the challenges of graph construction and document deletion in deployed systems. Lightfo…
-
New RAG methods QueryFlow and EAGR enhance multi-hop QA capabilities
Two new research papers, QueryFlow and EAGR, introduce novel approaches to multi-hop retrieval-augmented generation (RAG) for question answering. QueryFlow models the coupled evolution of evidence representations and qu…
-
New on-policy training method improves multi-hop retrieval for complex questions
Researchers have developed a new on-policy training method for embedding models used in multi-hop retrieval-augmented generation. This approach trains the model on its own potentially erroneous retrievals, aiming to imp…
-
New DeFT-RAG framework improves multi-hop question answering accuracy
Researchers have developed DeFT-RAG, a new framework designed to improve retrieval-augmented generation (RAG) for complex, multi-hop questions. Unlike existing methods that struggle with chaining facts across documents,…
-
New DeFT-RAG framework improves LLM multi-hop question answering
Researchers have introduced DeFT-RAG, a novel framework designed to improve retrieval-augmented generation (RAG) for complex, multi-hop questions. Unlike existing methods that struggle with chaining facts across documen…
-
New HyperAddress method boosts multi-hop RAG performance
Researchers have developed HyperAddress, a novel approach to Graph-based Retrieval-Augmented Generation (GraphRAG) that enhances multi-hop question answering. Unlike existing methods that either accumulate relevance err…
-
New RAG framework reduces AI hallucinations using attention rewards
Researchers have developed a new framework for retrieval-augmented generation (RAG) systems designed to reduce hallucinations. This approach utilizes a multi-agent system where agents are trained not only on task comple…
-
TokenGate speeds up LLM long-context prefill up to 11.3x with learned token pruning
Researchers from Stanford University and UC Berkeley have developed TokenGate, a novel module designed to accelerate the prefill process for large language models (LLMs) with long contexts. By employing a learned token …
-
New ThreadRAG framework improves RAG with semantic topology and energy pathfinding
Researchers have introduced ThreadRAG, a novel framework designed to enhance retrieval-augmented generation (RAG) by addressing semantic loss and modality mismatch issues. ThreadRAG utilizes a Semantic Topology Mapper t…
-
New SAG2 system enables efficient embedding-free multi-hop retrieval
Researchers have developed SAG2, a novel embedding-free retrieval architecture designed for efficient multi-hop question answering. This system utilizes a single SQLite database, the BM25 algorithm, and contextual evide…
-
MemReread enhances AI long-context reasoning with memory-guided rereading
Researchers have developed MemReread, a novel agent-memory approach designed to enhance long-context reasoning in AI models. This method utilizes a streaming reading technique that triggers question decomposition and ta…
-
New RAG methods tackle evidence retrieval for LLMs · 2 papers tracked
Two new research papers explore advancements in retrieval-augmented generation (RAG) for large language models (LLMs). The first paper introduces ExecutionRAG, a method to distinguish between retrieval failures and sear…
-
New Pleias-RAG models offer citation and grounding for smaller LLMs
Researchers have introduced the Pleias-RAG model family, featuring smaller reasoning models designed for retrieval-augmented generation (RAG), search, and source summarization. These models, Pleias-RAG-350m and Pleias-R…
-
UNREAL model unifies retrieval and long-context evidence selection
Researchers have introduced UNREAL, a novel framework that unifies retrieval-augmented generation (RAG) and long-context inference within a single model. This approach uses a frozen LLM's internal representations to sel…
-
New Hop-Decayed Influence attack targets GraphRAG pipelines
A new attack vector, termed Hop-Decayed Influence (HDI), has been identified that exploits vulnerabilities in the auxiliary structures of GraphRAG pipelines. This attack targets schema-level components rather than indiv…
-
Study questions rationale effectiveness in AI QA systems
A new study published on arXiv investigates the communication effectiveness of rationales in role-specialized Question Answering (QA) pipelines. Researchers found that while rationales do not significantly improve answe…
-
Abstract pretraining boosts LLM reasoning beyond perplexity
A new paper explores the impact of abstract pretraining on language models, demonstrating that even a small amount of abstract data can significantly improve reasoning capabilities without affecting perplexity. The stud…
-
Abstract pre-training boosts language model reasoning and efficiency
Researchers are exploring novel pre-training techniques for language models that go beyond standard perplexity metrics. One study demonstrates that a brief warm-up on abstract, stack-manipulation tasks can significantly…
-
New STITCH-RAG framework enhances multi-hop retrieval for AI generation
Researchers have introduced STITCH-RAG, a novel framework designed to improve multi-hop retrieval-augmented generation. This system utilizes a hypergraph to encode topic participation and entity states, addressing limit…
-
Mosaic framework enhances GraphRAG with query-aware exploration policies
Researchers have introduced Mosaic, a novel framework designed to enhance Graph Retrieval-Augmented Generation (GraphRAG) by adapting exploration policies on a per-query basis. Unlike existing systems that use uniform e…