HotpotQA
PulseAugur coverage of HotpotQA — every cluster mentioning HotpotQA across labs, papers, and developer communities, ranked by signal.
13 day(s) with sentiment data
-
ProvenAI framework enhances transparency in AI-generated answers
Researchers have introduced ProvenAI, a framework designed to enhance transparency in retrieval-augmented question-answering systems. This framework measures transparency across three distinct layers: answer correctness…
-
New RAG framework improves multi-step QA accuracy and efficiency
Researchers have introduced Grounded Delta Planning RAG (GDP-RAG), a novel framework designed to improve the efficiency and accuracy of multi-step question answering in Retrieval-Augmented Generation (RAG) systems. Unli…
-
RAG compression evaluation flawed, hides model performance differences
A new research paper published on arXiv highlights a critical flaw in how Retrieval-Augmented Generation (RAG) compression is evaluated. The study demonstrates that fixed compression methods can mask significant perform…
-
Local 7B model study dissects agentic RAG for multi-hop QA
Researchers have conducted an ablation study on agentic retrieval-augmented generation (RAG) systems, specifically focusing on multi-hop question answering with a local 7B parameter model, Qwen2.5-7B-Instruct. The study…
-
CalVerT enhances LLM agents with telemetry for better QA performance
Researchers have introduced CalVerT, a novel method to enhance Large Language Model (LLM) agents in knowledge-intensive question answering tasks. CalVerT augments agents with calibrated self-confidence and grounding ver…
-
New SAG architecture enhances LLM knowledge retrieval with dynamic SQL joins
A new paper introduces SAG (SQL-Retrieval Augmented Generation), an architecture designed to enhance large language models' ability to access external knowledge. Unlike traditional RAG methods that rely on dense similar…
-
AI agents leverage ReAct paradigm for autonomous task execution
AI agents are emerging as a dominant application paradigm for large language models, moving beyond simple chatbots to autonomously perceive, reason, and act in their environment. These agents utilize a loop of thought, …
-
Latent Memory cuts QA token use by 3x-10x
Researchers have developed a new method called Latent Memory to improve question answering systems for resource-constrained environments. This approach compresses multimodal evidence, such as text and images, into singl…
-
LEVI system offers AlphaEvolve capabilities at fraction of cost
A new open-source system named LEVI has been developed to emulate AlphaEvolve's capabilities at a significantly reduced cost, reportedly up to 35 times cheaper. LEVI's core principle is that smaller language models can …
-
New method predicts and mitigates order sensitivity in AI adjudication
Researchers have developed a new method called Quantified Martingale Violation (QMV) to address order sensitivity in transformer models used for evidence-based decision-making. This approach aims to reduce unreliable an…
-
New LLM context compression techniques boost efficiency and accuracy
Researchers are developing new methods for context compression in large language models to improve efficiency and performance. One approach, "Telegraph English," rewrites retrieved passages into structured entity-relati…
-
RAG rewriting gains driven by answer presence, not curation
Researchers have investigated the gains seen in retrieval-augmented question-answering (RAG) pipelines, specifically focusing on the role of a "rewriter" LLM. Their findings suggest that the observed improvements in F1 …
-
New HKVM-RAG method boosts multi-hop RAG performance
Researchers have developed HKVM-RAG, a novel approach to enhance multi-hop Retrieval Augmented Generation (RAG) systems. This method organizes retrieved text into hypergraph structures, using these structures as keys fo…
-
New HKVM-RAG method enhances multi-hop retrieval for LLMs
Researchers have developed HKVM-RAG, a novel method for organizing retrieved text to improve multi-hop retrieval-augmented generation (RAG) systems. This approach separates key-value pairs, using hypergraph structures t…
-
Hugging Face paper: Answer presence, not rewriting, drives RAG gains
A new paper from Hugging Face investigates the effectiveness of retrieval-augmented generation (RAG) in question-answering systems. The research reveals that the presence of the correct answer within rewritten contexts …
-
Hybrid defense framework boosts LLM accuracy and robustness
Researchers have developed a novel hybrid defense framework to combat both hallucinations and adversarial manipulation in large language models. This approach integrates entropy-based methods for reducing hallucinations…
-
RAG research focuses on cost, intent, and chunking for better AI retrieval
Researchers are developing new methods to optimize Retrieval-Augmented Generation (RAG) systems for efficiency and accuracy. One approach, Cost-Aware RAG (CA-RAG), dynamically routes queries to different retrieval depth…
-
New SLMs achieve faithful question answering with multi-hop reasoning
Researchers have developed OCC-RAG, a family of small language models (SLMs) designed for faithful question answering. These models are trained on a novel dataset of over three million examples, focusing on multi-hop re…
-
AdaptR1 framework cuts LLM reasoning costs with RL
Researchers have developed AdaptR1, a novel framework that uses reinforcement learning to optimize reasoning in large language models for multi-hop question answering. This approach dynamically allocates reasoning budge…
-
BEAR framework optimizes multi-document reasoning with budgeted evidence allocation
Researchers have introduced BEAR, a framework designed to optimize multi-document reasoning by efficiently allocating a limited evidence budget. Unlike full-context inference or simple chunk retrieval, BEAR builds hiera…