HotpotQA
PulseAugur coverage of HotpotQA — every cluster mentioning HotpotQA across labs, papers, and developer communities, ranked by signal.
7 day(s) with sentiment data
-
LoRA adapter KV cache reuse explored for quality vs. serving cost
Researchers have investigated the trade-offs between maintaining task quality and reducing serving costs when reusing the KV cache across multiple LoRA adapters in a shared backbone model. Their experiments on a Qwen3-1…
-
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…
-
New RAG framework enhances multi-hop QA with contrastive evidence exploration · 2 sources tracked
Researchers have developed a new framework for multi-hop question answering that improves retrieval-augmented generation (RAG) by addressing limitations in existing one-shot query expansion methods. This training-free a…
-
Query rewriting boosts RAG performance when combined, study finds
A new research paper explores query rewriting techniques to enhance retrieval-augmented generation (RAG) systems. The study found that combining multiple rewriting strategies, alongside strong baselines like HyDE and Qu…
-
New ESPO method optimizes LLM prompts, boosting accuracy and reducing length
Researchers have developed ESPO (Error-Structured Prompt Optimization), a new method to improve the efficiency and accuracy of evolutionary prompt optimizers. ESPO addresses issues like prompt bloat by decomposing optim…
-
KV-cache quantization in RAG systems degrades faithfulness, study finds
A new research paper from arXiv investigates the impact of KV-cache quantization on retrieval-augmented generation (RAG) systems. The study found that while INT8 quantization has a minimal effect on faithfulness, INT4 q…
-
New methods compress long contexts for LLMs beyond text and vision · 2 sources tracked
Two new research papers introduce novel methods for compressing long contexts in large language models. LatentPress utilizes continuous memory tokens, bypassing text reconstruction for faster and more efficient processi…
-
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 PRISM framework uses LLM agents for precise multi-hop question answering
Researchers have introduced PRISM, a novel agentic retrieval framework designed to enhance multi-hop question answering by leveraging large language models. PRISM breaks down complex queries into sub-questions using a Q…
-
New research tackles multi-hop QA challenges with evidence sufficiency and query refinement · 5 sources tracked
Two new research papers address challenges in multi-hop question answering systems. The first, "Learning Evidence Sufficiency Boundaries for Selective Answering in Grounded Multi-Hop QA," introduces a training framework…
-
New protocol evaluates language model agent confidence and retrieval strategies
Researchers have developed a new protocol called matched trajectory replay to evaluate how language model agents use confidence signals to decide between answering, retrieving information, or deferring. This method was …
-
New FCPRAG framework improves LLM evidence fusion for RAG
Researchers have developed FCPRAG, a novel framework for retrieval-augmented generation (RAG) that enhances how large language models (LLMs) integrate retrieved information. FCPRAG uses a lightweight controller to dynam…
-
New RAG evaluation methods emerge for Turkish and domain-specific data · 4 sources tracked
Researchers are developing new methods to evaluate and improve Retrieval-Augmented Generation (RAG) systems. One study compares different chunking and embedding strategies for Turkish RAG, finding that layout-aware chun…
-
New MEMONDEMAND system enhances enterprise data retrieval
Researchers have developed MEMONDEMAND, a novel memory management system designed to improve data retrieval from large-scale enterprise repositories. The system addresses challenges in efficient access, source-faithful …
-
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 …
-
RAG extensions amplify ASR errors, new research finds · 6 sources tracked
Research indicates that advanced retrieval-augmented generation (RAG) techniques, while improving overall performance, can amplify errors originating from Automatic Speech Recognition (ASR) systems. Specifically, multi-…
-
New retrieval method DBRR improves evidence recovery within fixed budget
Researchers have introduced Dual-Bounded Relational Recall (DBRR), a novel retrieval method designed to enhance information recovery within a fixed budget. DBRR allocates retrieval resources between initial relevance-ra…
-
New method adapts dense retrieval models using agent search traces
Researchers have developed Navigation-Informed Embeddings (NIE), a novel method to adapt dense retrieval models using traces from agentic search workflows. This approach leverages query, retrieval, and stopping traces t…
-
LineageRAG enhances GraphRAG with explicit evidence lineages · arXiv
Researchers have introduced LineageRAG, a novel approach to enhance Graph-based Retrieval-Augmented Generation (GraphRAG) by explicitly constructing evidence lineages. This method connects evidence discovery with source…