Natural Questions
PulseAugur coverage of Natural Questions — every cluster mentioning Natural Questions across labs, papers, and developer communities, ranked by signal.
3 day(s) with sentiment data
-
New ReDSI framework improves DSI reproducibility for document retrieval
Researchers have introduced ReDSI, an open-source implementation of the differentiable search index (DSI) framework, designed to address issues of reproducibility and evaluation consistency in generative retrieval. The …
-
New TRIS defense system combats knowledge poisoning in RAG models
Researchers have developed TRIS, a Tri-Layer Retrieval Integrity Sieve, to combat knowledge poisoning in retrieval-augmented generation (RAG) systems. This middleware defense system sanitizes retrieved evidence by emplo…
-
New PruneShift framework evaluates AI model pruning decision reliability
Researchers have introduced PruneShift, a new framework designed to evaluate the reliability of decisions made during structured pruning in machine learning models. Unlike previous methods that focused on average surrog…
-
New research probes RAG reliability, utility, and hallucination risks · 8 sources tracked
Recent research explores the nuances of Retrieval-Augmented Generation (RAG) systems, focusing on improving their reliability and utility. One paper details a system for the LLMs4OL 2026 Challenge that uses retrieval-au…
-
New audit method reveals hidden answer churn in retrieval-augmented QA systems
A new research paper introduces the Snapshot Compatibility Audit, a method to detect "accuracy-blind answer churn" in retrieval-augmented QA systems. This phenomenon occurs when system updates, such as index expansion, …
-
New benchmark reveals RAG models struggle with misleading context
A new study published on arXiv introduces GRAB-RAG, a benchmark designed to evaluate retrieval-augmented generation (RAG) models' ability to distinguish between missing and misleading context. The research found that ev…
-
Edge RAG systems can save energy with adaptive compression, study finds
A new research paper explores adaptive compression techniques for retrieval-augmented generation (RAG) systems operating on edge devices. The study, conducted on an NVIDIA Jetson AGX Thor, demonstrates that dynamically …
-
New research explores static pruning and LLM-based query expansion for retrieval systems
Two new research papers explore methods to improve information retrieval systems. The first paper, "Static Pruning Across Sparse Retrieval Regimes," investigates how static pruning techniques can be applied across diffe…
-
SAGE system optimizes RAG retrieval for latency and cost · 2 sources tracked
Researchers have developed SAGE, a new adaptive retrieval policy for production Retrieval-Augmented Generation (RAG) systems. SAGE dynamically adjusts the number of passages retrieved per query based on estimated query …
-
TAPR refines LLM prompts to boost benchmark accuracy
TAPR, a new system, automatically refines user prompts for large language models using reinforcement learning. This process enhances the accuracy of LLM responses, particularly on benchmarks like Natural Questions and GSM8K.
-
New RAG defense frameworks combat data poisoning attacks · 3 sources tracked
Researchers have developed new defense frameworks to protect Retrieval-Augmented Generation (RAG) systems from data poisoning attacks. RAGuard, presented in two papers, employs a layered approach including adversarial r…
-
SmartRAG enables LLMs on mobile devices with graph-based RAG
Researchers have developed SmartRAG, a novel on-device framework designed to enable large language models (LLMs) to function as personal assistants on mobile devices. This system decomposes intelligence into four module…
-
User distills DeepSeek V4 Pro into Gemma 26B MoE and 12B dense models
A user detailed their process of distilling the DeepSeek V4 Pro model into two versions of Gemma: a 26B parameter MoE model and a 12B parameter dense model. The distillation process, which involved repopulating Natural …
-
New RAG research enhances LLM retrieval, unlearning, and faithfulness
Multiple research papers are exploring advancements in retrieval-augmented generation (RAG) to improve the performance and efficiency of large language models. Apple's CLaRa framework unifies retrieval and generation in…
-
New indexing framework SPI boosts RAG performance in vector databases
Researchers have introduced Semantic Pyramid Indexing (SPI), a novel indexing framework for vector databases designed to enhance retrieval-augmented generation (RAG) pipelines. SPI adapts the retrieval depth based on qu…
-
CONCORD framework enhances device-cloud RAG with asynchronous sparse aggregation
Researchers have introduced CONCORD, a new framework designed to optimize retrieval-augmented generation (RAG) in a device-cloud collaborative setting where private documents are kept on local devices and public knowled…
-
SilentRetrieval attack hijacks RAG systems with poisoned documents
Researchers have developed "SilentRetrieval," a novel two-stage attack designed to compromise Retrieval-Augmented Generation (RAG) systems. This method uses adversarial data poisoning to inject manipulated documents tha…
-
PersonalAI 2.0 enhances LLMs with knowledge graphs and planning
Researchers have developed PersonalAI 2.0 (PAI-2), a new framework that improves large language model (LLM) systems by integrating external knowledge graphs. PAI-2 employs a dynamic, multistage query processing pipeline…
-
RAG system architectures show varied robustness to knowledge base poisoning
Researchers have investigated the vulnerability of Retrieval-Augmented Generation (RAG) systems to knowledge base poisoning, finding that system architecture significantly impacts adversarial robustness. Evaluations on …
-
Researchers propose Parametric Memory Head to improve generative retrieval models
Researchers have developed a novel approach called Post-Adaptation Memory Tuning (PAMT) to address the challenge of catastrophic forgetting in generative information retrieval models. PAMT introduces a modular parametri…